| 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/lockd/svc.c * * This is the central lockd service. * * FIXME: Separate the lockd NFS server functionality from the lockd NFS * client functionality. Oh why didn't Sun create two separate * services in the first place? * * Authors: Olaf Kirch (okir@monad.swb.de) * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/init.h> #include <linux/sysctl.h> #include <linux/moduleparam.h> #include <linux/sched/signal.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/uio.h> #include <linux/smp.h> #include <linux/mutex.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/inetdevice.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svc_xprt.h> #include <net/ip.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <linux/lockd/lockd.h> #include <linux/nfs.h> #include "netns.h" #include "procfs.h" #define NLMDBG_FACILITY NLMDBG_SVC #define LOCKD_BUFSIZE (1024 + NLMSVC_XDRSIZE) #define ALLOWED_SIGS (sigmask(SIGKILL)) static struct svc_program nlmsvc_program; const struct nlmsvc_binding *nlmsvc_ops; EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; static struct svc_serv *nlmsvc_serv; unsigned long nlmsvc_timeout; unsigned int lockd_net_id; /* * These can be set at insmod time (useful for NFS as root filesystem), * and also changed through the sysctl interface. -- Jamie Lokier, Aug 2003 */ static unsigned long nlm_grace_period; static unsigned long nlm_timeout = LOCKD_DFLT_TIMEO; static int nlm_udpport, nlm_tcpport; /* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */ static unsigned int nlm_max_connections = 1024; /* * Constants needed for the sysctl interface. */ static const unsigned long nlm_grace_period_min = 0; static const unsigned long nlm_grace_period_max = 240; static const unsigned long nlm_timeout_min = 3; static const unsigned long nlm_timeout_max = 20; static const int nlm_port_min = 0, nlm_port_max = 65535; #ifdef CONFIG_SYSCTL static struct ctl_table_header * nlm_sysctl_table; #endif static unsigned long get_lockd_grace_period(void) { /* Note: nlm_timeout should always be nonzero */ if (nlm_grace_period) return roundup(nlm_grace_period, nlm_timeout) * HZ; else return nlm_timeout * 5 * HZ; } static void grace_ender(struct work_struct *grace) { struct delayed_work *dwork = to_delayed_work(grace); struct lockd_net *ln = container_of(dwork, struct lockd_net, grace_period_end); locks_end_grace(&ln->lockd_manager); } static void set_grace_period(struct net *net) { unsigned long grace_period = get_lockd_grace_period(); struct lockd_net *ln = net_generic(net, lockd_net_id); locks_start_grace(net, &ln->lockd_manager); cancel_delayed_work_sync(&ln->grace_period_end); schedule_delayed_work(&ln->grace_period_end, grace_period); } static void restart_grace(void) { if (nlmsvc_ops) { struct net *net = &init_net; struct lockd_net *ln = net_generic(net, lockd_net_id); cancel_delayed_work_sync(&ln->grace_period_end); locks_end_grace(&ln->lockd_manager); nlmsvc_invalidate_all(); set_grace_period(net); } } /* * This is the lockd kernel thread */ static int lockd(void *vrqstp) { int err = 0; struct svc_rqst *rqstp = vrqstp; struct net *net = &init_net; struct lockd_net *ln = net_generic(net, lockd_net_id); /* try_to_freeze() is called from svc_recv() */ set_freezable(); /* Allow SIGKILL to tell lockd to drop all of its locks */ allow_signal(SIGKILL); dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); /* * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. */ while (!kthread_should_stop()) { long timeout = MAX_SCHEDULE_TIMEOUT; RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); /* update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nlm_max_connections; if (signalled()) { flush_signals(current); restart_grace(); continue; } timeout = nlmsvc_retry_blocked(); /* * Find a socket with data available and call its * recvfrom routine. */ err = svc_recv(rqstp, timeout); if (err == -EAGAIN || err == -EINTR) continue; dprintk("lockd: request from %s\n", svc_print_addr(rqstp, buf, sizeof(buf))); svc_process(rqstp); } flush_signals(current); if (nlmsvc_ops) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); cancel_delayed_work_sync(&ln->grace_period_end); locks_end_grace(&ln->lockd_manager); dprintk("lockd_down: service stopped\n"); svc_exit_thread(rqstp); return 0; } static int create_lockd_listener(struct svc_serv *serv, const char *name, struct net *net, const int family, const unsigned short port, const struct cred *cred) { struct svc_xprt *xprt; xprt = svc_find_xprt(serv, name, net, family, 0); if (xprt == NULL) return svc_xprt_create(serv, name, net, family, port, SVC_SOCK_DEFAULTS, cred); svc_xprt_put(xprt); return 0; } static int create_lockd_family(struct svc_serv *serv, struct net *net, const int family, const struct cred *cred) { int err; err = create_lockd_listener(serv, "udp", net, family, nlm_udpport, cred); if (err < 0) return err; return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport, cred); } /* * Ensure there are active UDP and TCP listeners for lockd. * * Even if we have only TCP NFS mounts and/or TCP NFSDs, some * local services (such as rpc.statd) still require UDP, and * some NFS servers do not yet support NLM over TCP. * * Returns zero if all listeners are available; otherwise a * negative errno value is returned. */ static int make_socks(struct svc_serv *serv, struct net *net, const struct cred *cred) { static int warned; int err; err = create_lockd_family(serv, net, PF_INET, cred); if (err < 0) goto out_err; err = create_lockd_family(serv, net, PF_INET6, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_err; warned = 0; return 0; out_err: if (warned++ == 0) printk(KERN_WARNING "lockd_up: makesock failed, error=%d\n", err); svc_xprt_destroy_all(serv, net); svc_rpcb_cleanup(serv, net); return err; } static int lockd_up_net(struct svc_serv *serv, struct net *net, const struct cred *cred) { struct lockd_net *ln = net_generic(net, lockd_net_id); int error; if (ln->nlmsvc_users++) return 0; error = svc_bind(serv, net); if (error) goto err_bind; error = make_socks(serv, net, cred); if (error < 0) goto err_bind; set_grace_period(net); dprintk("%s: per-net data created; net=%x\n", __func__, net->ns.inum); return 0; err_bind: ln->nlmsvc_users--; return error; } static void lockd_down_net(struct svc_serv *serv, struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); if (ln->nlmsvc_users) { if (--ln->nlmsvc_users == 0) { nlm_shutdown_hosts_net(net); cancel_delayed_work_sync(&ln->grace_period_end); locks_end_grace(&ln->lockd_manager); svc_xprt_destroy_all(serv, net); svc_rpcb_cleanup(serv, net); } } else { pr_err("%s: no users! net=%x\n", __func__, net->ns.inum); BUG(); } } static int lockd_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sockaddr_in sin; if (event != NETDEV_DOWN) goto out; if (nlmsvc_serv) { dprintk("lockd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin); } out: return NOTIFY_DONE; } static struct notifier_block lockd_inetaddr_notifier = { .notifier_call = lockd_inetaddr_event, }; #if IS_ENABLED(CONFIG_IPV6) static int lockd_inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sockaddr_in6 sin6; if (event != NETDEV_DOWN) goto out; if (nlmsvc_serv) { dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ifa->addr; if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin6); } out: return NOTIFY_DONE; } static struct notifier_block lockd_inet6addr_notifier = { .notifier_call = lockd_inet6addr_event, }; #endif static int lockd_get(void) { struct svc_serv *serv; int error; if (nlmsvc_serv) { nlmsvc_users++; return 0; } /* * Sanity check: if there's no pid, * we should be the first user ... */ if (nlmsvc_users) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); if (!nlm_timeout) nlm_timeout = LOCKD_DFLT_TIMEO; nlmsvc_timeout = nlm_timeout * HZ; serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, lockd); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); return -ENOMEM; } serv->sv_maxconn = nlm_max_connections; error = svc_set_num_threads(serv, NULL, 1); /* The thread now holds the only reference */ svc_put(serv); if (error < 0) return error; nlmsvc_serv = serv; register_inetaddr_notifier(&lockd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&lockd_inet6addr_notifier); #endif dprintk("lockd_up: service created\n"); nlmsvc_users++; return 0; } static void lockd_put(void) { if (WARN(nlmsvc_users <= 0, "lockd_down: no users!\n")) return; if (--nlmsvc_users) return; unregister_inetaddr_notifier(&lockd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&lockd_inet6addr_notifier); #endif svc_set_num_threads(nlmsvc_serv, NULL, 0); nlmsvc_serv = NULL; dprintk("lockd_down: service destroyed\n"); } /* * Bring up the lockd process if it's not already up. */ int lockd_up(struct net *net, const struct cred *cred) { int error; mutex_lock(&nlmsvc_mutex); error = lockd_get(); if (error) goto err; error = lockd_up_net(nlmsvc_serv, net, cred); if (error < 0) { lockd_put(); goto err; } err: mutex_unlock(&nlmsvc_mutex); return error; } EXPORT_SYMBOL_GPL(lockd_up); /* * Decrement the user count and bring down lockd if we're the last. */ void lockd_down(struct net *net) { mutex_lock(&nlmsvc_mutex); lockd_down_net(nlmsvc_serv, net); lockd_put(); mutex_unlock(&nlmsvc_mutex); } EXPORT_SYMBOL_GPL(lockd_down); #ifdef CONFIG_SYSCTL /* * Sysctl parameters (same as module parameters, different interface). */ static struct ctl_table nlm_sysctls[] = { { .procname = "nlm_grace_period", .data = &nlm_grace_period, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = (unsigned long *) &nlm_grace_period_min, .extra2 = (unsigned long *) &nlm_grace_period_max, }, { .procname = "nlm_timeout", .data = &nlm_timeout, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = (unsigned long *) &nlm_timeout_min, .extra2 = (unsigned long *) &nlm_timeout_max, }, { .procname = "nlm_udpport", .data = &nlm_udpport, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (int *) &nlm_port_min, .extra2 = (int *) &nlm_port_max, }, { .procname = "nlm_tcpport", .data = &nlm_tcpport, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (int *) &nlm_port_min, .extra2 = (int *) &nlm_port_max, }, { .procname = "nsm_use_hostnames", .data = &nsm_use_hostnames, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dobool, }, { .procname = "nsm_local_state", .data = &nsm_local_state, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static struct ctl_table nlm_sysctl_dir[] = { { .procname = "nfs", .mode = 0555, .child = nlm_sysctls, }, { } }; static struct ctl_table nlm_sysctl_root[] = { { .procname = "fs", .mode = 0555, .child = nlm_sysctl_dir, }, { } }; #endif /* CONFIG_SYSCTL */ /* * Module (and sysfs) parameters. */ #define param_set_min_max(name, type, which_strtol, min, max) \ static int param_set_##name(const char *val, const struct kernel_param *kp) \ { \ char *endp; \ __typeof__(type) num = which_strtol(val, &endp, 0); \ if (endp == val || *endp || num < (min) || num > (max)) \ return -EINVAL; \ *((type *) kp->arg) = num; \ return 0; \ } static inline int is_callback(u32 proc) { return proc == NLMPROC_GRANTED || proc == NLMPROC_GRANTED_MSG || proc == NLMPROC_TEST_RES || proc == NLMPROC_LOCK_RES || proc == NLMPROC_CANCEL_RES || proc == NLMPROC_UNLOCK_RES || proc == NLMPROC_NSM_NOTIFY; } static int lockd_authenticate(struct svc_rqst *rqstp) { rqstp->rq_client = NULL; switch (rqstp->rq_authop->flavour) { case RPC_AUTH_NULL: case RPC_AUTH_UNIX: rqstp->rq_auth_stat = rpc_auth_ok; if (rqstp->rq_proc == 0) return SVC_OK; if (is_callback(rqstp->rq_proc)) { /* Leave it to individual procedures to * call nlmsvc_lookup_host(rqstp) */ return SVC_OK; } return svc_set_client(rqstp); } rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } param_set_min_max(port, int, simple_strtol, 0, 65535) param_set_min_max(grace_period, unsigned long, simple_strtoul, nlm_grace_period_min, nlm_grace_period_max) param_set_min_max(timeout, unsigned long, simple_strtoul, nlm_timeout_min, nlm_timeout_max) MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_DESCRIPTION("NFS file locking service version " LOCKD_VERSION "."); MODULE_LICENSE("GPL"); module_param_call(nlm_grace_period, param_set_grace_period, param_get_ulong, &nlm_grace_period, 0644); module_param_call(nlm_timeout, param_set_timeout, param_get_ulong, &nlm_timeout, 0644); module_param_call(nlm_udpport, param_set_port, param_get_int, &nlm_udpport, 0644); module_param_call(nlm_tcpport, param_set_port, param_get_int, &nlm_tcpport, 0644); module_param(nsm_use_hostnames, bool, 0644); module_param(nlm_max_connections, uint, 0644); static int lockd_init_net(struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender); INIT_LIST_HEAD(&ln->lockd_manager.list); ln->lockd_manager.block_opens = false; INIT_LIST_HEAD(&ln->nsm_handles); return 0; } static void lockd_exit_net(struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); WARN_ONCE(!list_empty(&ln->lockd_manager.list), "net %x %s: lockd_manager.list is not empty\n", net->ns.inum, __func__); WARN_ONCE(!list_empty(&ln->nsm_handles), "net %x %s: nsm_handles list is not empty\n", net->ns.inum, __func__); WARN_ONCE(delayed_work_pending(&ln->grace_period_end), "net %x %s: grace_period_end was not cancelled\n", net->ns.inum, __func__); } static struct pernet_operations lockd_net_ops = { .init = lockd_init_net, .exit = lockd_exit_net, .id = &lockd_net_id, .size = sizeof(struct lockd_net), }; /* * Initialising and terminating the module. */ static int __init init_nlm(void) { int err; #ifdef CONFIG_SYSCTL err = -ENOMEM; nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root); if (nlm_sysctl_table == NULL) goto err_sysctl; #endif err = register_pernet_subsys(&lockd_net_ops); if (err) goto err_pernet; err = lockd_create_procfs(); if (err) goto err_procfs; return 0; err_procfs: unregister_pernet_subsys(&lockd_net_ops); err_pernet: #ifdef CONFIG_SYSCTL unregister_sysctl_table(nlm_sysctl_table); err_sysctl: #endif return err; } static void __exit exit_nlm(void) { /* FIXME: delete all NLM clients */ nlm_shutdown_hosts(); lockd_remove_procfs(); unregister_pernet_subsys(&lockd_net_ops); #ifdef CONFIG_SYSCTL unregister_sysctl_table(nlm_sysctl_table); #endif } module_init(init_nlm); module_exit(exit_nlm); /** * nlmsvc_dispatch - Process an NLM Request * @rqstp: incoming request * @statp: pointer to location of accept_stat field in RPC Reply buffer * * Return values: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; svcxdr_init_decode(rqstp); if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; *statp = procp->pc_func(rqstp); if (*statp == rpc_drop_reply) return 0; if (*statp != rpc_success) return 1; svcxdr_init_encode(rqstp); if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; return 1; out_decode_err: *statp = rpc_garbage_args; return 1; out_encode_err: *statp = rpc_system_err; return 1; } /* * Define NLM program and procedures */ static unsigned int nlmsvc_version1_count[17]; static const struct svc_version nlmsvc_version1 = { .vs_vers = 1, .vs_nproc = 17, .vs_proc = nlmsvc_procedures, .vs_count = nlmsvc_version1_count, .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; static unsigned int nlmsvc_version3_count[24]; static const struct svc_version nlmsvc_version3 = { .vs_vers = 3, .vs_nproc = 24, .vs_proc = nlmsvc_procedures, .vs_count = nlmsvc_version3_count, .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 static unsigned int nlmsvc_version4_count[24]; static const struct svc_version nlmsvc_version4 = { .vs_vers = 4, .vs_nproc = 24, .vs_proc = nlmsvc_procedures4, .vs_count = nlmsvc_version4_count, .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif static const struct svc_version *nlmsvc_version[] = { [1] = &nlmsvc_version1, [3] = &nlmsvc_version3, #ifdef CONFIG_LOCKD_V4 [4] = &nlmsvc_version4, #endif }; #define NLM_NRVERS ARRAY_SIZE(nlmsvc_version) static struct svc_program nlmsvc_program = { .pg_prog = NLM_PROGRAM, /* program number */ .pg_nvers = NLM_NRVERS, /* number of entries in nlmsvc_version */ .pg_vers = nlmsvc_version, /* version table */ .pg_name = "lockd", /* service name */ .pg_class = "nfsd", /* share authentication with nfsd */ .pg_authenticate = &lockd_authenticate, /* export authentication */ .pg_init_request = svc_generic_init_request, .pg_rpcbind_set = svc_generic_rpcbind_set, }; |
| 2349 2354 2349 264 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * tsacct.c - System accounting over taskstats interface * * Copyright (C) Jay Lan, <jlan@sgi.com> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sched/cputime.h> #include <linux/tsacct_kern.h> #include <linux/acct.h> #include <linux/jiffies.h> #include <linux/mm.h> /* * fill in basic accounting fields */ void bacct_add_tsk(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; u64 utime, stime, utimescaled, stimescaled; u64 delta; time64_t btime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); /* calculate task elapsed time in nsec */ delta = ktime_get_ns() - tsk->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); stats->ac_etime = delta; /* Convert to seconds for btime (note y2106 limit) */ btime = ktime_get_real_seconds() - div_u64(delta, USEC_PER_SEC); stats->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); stats->ac_btime64 = btime; if (tsk->flags & PF_EXITING) stats->ac_exitcode = tsk->exit_code; if (thread_group_leader(tsk) && (tsk->flags & PF_FORKNOEXEC)) stats->ac_flag |= AFORK; if (tsk->flags & PF_SUPERPRIV) stats->ac_flag |= ASU; if (tsk->flags & PF_DUMPCORE) stats->ac_flag |= ACORE; if (tsk->flags & PF_SIGNALED) stats->ac_flag |= AXSIG; stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); rcu_read_lock(); tcred = __task_cred(tsk); stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); stats->ac_gid = from_kgid_munged(user_ns, tcred->gid); stats->ac_ppid = pid_alive(tsk) ? task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; rcu_read_unlock(); task_cputime(tsk, &utime, &stime); stats->ac_utime = div_u64(utime, NSEC_PER_USEC); stats->ac_stime = div_u64(stime, NSEC_PER_USEC); task_cputime_scaled(tsk, &utimescaled, &stimescaled); stats->ac_utimescaled = div_u64(utimescaled, NSEC_PER_USEC); stats->ac_stimescaled = div_u64(stimescaled, NSEC_PER_USEC); stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm)); } #ifdef CONFIG_TASK_XACCT #define KB 1024 #define MB (1024*KB) #define KB_MASK (~(KB-1)) /* * fill in extended accounting fields */ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) { struct mm_struct *mm; /* convert pages-nsec/1024 to Mbyte-usec, see __acct_update_integrals */ stats->coremem = p->acct_rss_mem1 * PAGE_SIZE; do_div(stats->coremem, 1000 * KB); stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE; do_div(stats->virtmem, 1000 * KB); mm = get_task_mm(p); if (mm) { /* adjust to KB unit */ stats->hiwater_rss = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB; stats->hiwater_vm = get_mm_hiwater_vm(mm) * PAGE_SIZE / KB; mmput(mm); } stats->read_char = p->ioac.rchar & KB_MASK; stats->write_char = p->ioac.wchar & KB_MASK; stats->read_syscalls = p->ioac.syscr & KB_MASK; stats->write_syscalls = p->ioac.syscw & KB_MASK; #ifdef CONFIG_TASK_IO_ACCOUNTING stats->read_bytes = p->ioac.read_bytes & KB_MASK; stats->write_bytes = p->ioac.write_bytes & KB_MASK; stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes & KB_MASK; #else stats->read_bytes = 0; stats->write_bytes = 0; stats->cancelled_write_bytes = 0; #endif } #undef KB #undef MB static void __acct_update_integrals(struct task_struct *tsk, u64 utime, u64 stime) { u64 time, delta; if (!likely(tsk->mm)) return; time = stime + utime; delta = time - tsk->acct_timexpd; if (delta < TICK_NSEC) return; tsk->acct_timexpd = time; /* * Divide by 1024 to avoid overflow, and to avoid division. * The final unit reported to userspace is Mbyte-usecs, * the rest of the math is done in xacct_add_tsk. */ tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10; tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10; } /** * acct_update_integrals - update mm integral fields in task_struct * @tsk: task_struct for accounting */ void acct_update_integrals(struct task_struct *tsk) { u64 utime, stime; unsigned long flags; local_irq_save(flags); task_cputime(tsk, &utime, &stime); __acct_update_integrals(tsk, utime, stime); local_irq_restore(flags); } /** * acct_account_cputime - update mm integral after cputime update * @tsk: task_struct for accounting */ void acct_account_cputime(struct task_struct *tsk) { __acct_update_integrals(tsk, tsk->utime, tsk->stime); } /** * acct_clear_integrals - clear the mm integral fields in task_struct * @tsk: task_struct whose accounting fields are cleared */ void acct_clear_integrals(struct task_struct *tsk) { tsk->acct_timexpd = 0; tsk->acct_rss_mem1 = 0; tsk->acct_vm_mem1 = 0; } #endif |
| 32 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/shm.c * Copyright (C) 1992, 1993 Krishna Balasubramanian * Many improvements/fixes by Bruno Haible. * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. * * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * BIGMEM support, Andrea Arcangeli <andrea@suse.de> * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> * HIGHMEM support, Ingo Molnar <mingo@redhat.com> * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Better ipc lock (kern_ipc_perm.lock) handling * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013. */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/shm.h> #include <linux/init.h> #include <linux/file.h> #include <linux/mman.h> #include <linux/shmem_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/mount.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; time64_t shm_atim; time64_t shm_dtim; time64_t shm_ctim; struct pid *shm_cprid; struct pid *shm_lprid; struct ucounts *mlock_ucounts; /* * The task created the shm object, for * task_lock(shp->shm_creator) */ struct task_struct *shm_creator; /* * List by creator. task_lock(->shm_creator) required for read/write. * If list_empty(), then the creator is dead already. */ struct list_head shm_clist; struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ struct shm_file_data { int id; struct ipc_namespace *ns; struct file *file; const struct vm_operations_struct *vm_ops; }; #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) #define shm_unlock(shp) \ ipc_unlock(&(shp)->shm_perm) static int newseg(struct ipc_namespace *, struct ipc_params *); static void shm_open(struct vm_area_struct *vma); static void shm_close(struct vm_area_struct *vma); static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp); #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it); #endif void shm_init_ns(struct ipc_namespace *ns) { ns->shm_ctlmax = SHMMAX; ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_rmid_forced = 0; ns->shm_tot = 0; ipc_init_ids(&shm_ids(ns)); } /* * Called with shm_ids.rwsem (writer) and the shp structure locked. * Only shm_ids.rwsem remains locked on exit. */ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; /* Do not find it any more */ ipc_set_key_private(&shm_ids(ns), &shp->shm_perm); shm_unlock(shp); } else shm_destroy(ns, shp); } #ifdef CONFIG_IPC_NS void shm_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &shm_ids(ns), do_shm_rmid); idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht); } #endif static int __init ipc_ns_init(void) { shm_init_ns(&init_ipc_ns); return 0; } pure_initcall(ipc_ns_init); void __init shm_init(void) { ipc_init_proc_interface("sysvipc/shm", #if BITS_PER_LONG <= 32 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #else " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #endif IPC_SHM_IDS, sysvipc_shm_proc_show); } static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } /* * shm_lock_(check_) routines are called in the paths where the rwsem * is not necessarily held. */ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp; rcu_read_lock(); ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) goto err; ipc_lock_object(ipcp); /* * ipc_rmid() may have already freed the ID while ipc_lock_object() * was spinning: here verify that the structure is still valid. * Upon races with RMID, return -EIDRM, thus indicating that * the ID points to a removed identifier. */ if (ipc_valid_object(ipcp)) { /* return a locked ipc object upon success */ return container_of(ipcp, struct shmid_kernel, shm_perm); } ipc_unlock_object(ipcp); ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* * Callers of shm_lock() must validate the status of the returned ipc * object pointer and error out as appropriate. */ return ERR_CAST(ipcp); } static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) { rcu_read_lock(); ipc_lock_object(&ipcp->shm_perm); } static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, rcu); struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(&shp->shm_perm); kfree(shp); } /* * It has to be called with shp locked. * It must be called before ipc_rmid() */ static inline void shm_clist_rm(struct shmid_kernel *shp) { struct task_struct *creator; /* ensure that shm_creator does not disappear */ rcu_read_lock(); /* * A concurrent exit_shm may do a list_del_init() as well. * Just do nothing if exit_shm already did the work */ if (!list_empty(&shp->shm_clist)) { /* * shp->shm_creator is guaranteed to be valid *only* * if shp->shm_clist is not empty. */ creator = shp->shm_creator; task_lock(creator); /* * list_del_init() is a nop if the entry was already removed * from the list. */ list_del_init(&shp->shm_clist); task_unlock(creator); } rcu_read_unlock(); } static inline void shm_rmid(struct shmid_kernel *s) { shm_clist_rm(s); ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); if (IS_ERR(shp)) return PTR_ERR(shp); if (shp->shm_file != sfd->file) { /* ID was reused */ shm_unlock(shp); return -EINVAL; } shp->shm_atim = ktime_get_real_seconds(); ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_nattch++; shm_unlock(shp); return 0; } /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { int err = __shm_open(vma); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ WARN_ON_ONCE(err); } /* * shm_destroy - free the struct shmid_kernel * * @ns: namespace * @shp: struct to free * * It has to be called with shp and shm_ids.rwsem (writer) locked, * but returns with shp unlocked and freed. */ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) { struct file *shm_file; shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); else if (shp->mlock_ucounts) user_shm_unlock(i_size_read(file_inode(shm_file)), shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* * shm_may_destroy - identifies whether shm segment should be destroyed now * * Returns true if and only if there are no active users of the segment and * one of the following is true: * * 1) shmctl(id, IPC_RMID, NULL) was called for this shp * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } /* * remove the attach descriptor vma. * free memory for segment if it is marked destroyed. * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ static void shm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ if (WARN_ON_ONCE(IS_ERR(shp))) goto done; /* no-op */ ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); done: up_write(&shm_ids(ns).rwsem); } /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { struct ipc_namespace *ns = data; struct kern_ipc_perm *ipcp = p; struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm); /* * We want to destroy segments without users and with already * exit'ed originating process. * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ if (!list_empty(&shp->shm_clist)) return 0; if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } return 0; } void shm_destroy_orphaned(struct ipc_namespace *ns) { down_write(&shm_ids(ns).rwsem); if (shm_ids(ns).in_use) idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns); up_write(&shm_ids(ns).rwsem); } /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { for (;;) { struct shmid_kernel *shp; struct ipc_namespace *ns; task_lock(task); if (list_empty(&task->sysvshm.shm_clist)) { task_unlock(task); break; } shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, shm_clist); /* * 1) Get pointer to the ipc namespace. It is worth to say * that this pointer is guaranteed to be valid because * shp lifetime is always shorter than namespace lifetime * in which shp lives. * We taken task_lock it means that shp won't be freed. */ ns = shp->ns; /* * 2) If kernel.shm_rmid_forced is not set then only keep track of * which shmids are orphaned, so that a later set of the sysctl * can clean them up. */ if (!ns->shm_rmid_forced) goto unlink_continue; /* * 3) get a reference to the namespace. * The refcount could be already 0. If it is 0, then * the shm objects will be free by free_ipc_work(). */ ns = get_ipc_ns_not_zero(ns); if (!ns) { unlink_continue: list_del_init(&shp->shm_clist); task_unlock(task); continue; } /* * 4) get a reference to shp. * This cannot fail: shm_clist_rm() is called before * ipc_rmid(), thus the refcount cannot be 0. */ WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); /* * 5) unlink the shm segment from the list of segments * created by current. * This must be done last. After unlinking, * only the refcounts obtained above prevent IPC_RMID * from destroying the segment or the namespace. */ list_del_init(&shp->shm_clist); task_unlock(task); /* * 6) we have all references * Thus lock & if needed destroy shp. */ down_write(&shm_ids(ns).rwsem); shm_lock_by_ptr(shp); /* * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's * safe to call ipc_rcu_putref here */ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); if (ipc_valid_object(&shp->shm_perm)) { if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); } else { /* * Someone else deleted the shp from namespace * idr/kht while we have waited. * Just unlock and continue. */ shm_unlock(shp); } up_write(&shm_ids(ns).rwsem); put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ } } static vm_fault_t shm_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); return sfd->vm_ops->fault(vmf); } static int shm_may_split(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->may_split) return sfd->vm_ops->may_split(vma, addr); return 0; } static unsigned long shm_pagesize(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->pagesize) return sfd->vm_ops->pagesize(vma); return PAGE_SIZE; } #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); int err = 0; if (sfd->vm_ops->set_policy) err = sfd->vm_ops->set_policy(vma, new); return err; } static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct mempolicy *pol = NULL; if (sfd->vm_ops->get_policy) pol = sfd->vm_ops->get_policy(vma, addr); else if (vma->vm_policy) pol = vma->vm_policy; return pol; } #endif static int shm_mmap(struct file *file, struct vm_area_struct *vma) { struct shm_file_data *sfd = shm_file_data(file); int ret; /* * In case of remap_file_pages() emulation, the file can represent an * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ ret = __shm_open(vma); if (ret) return ret; ret = call_mmap(sfd->file, vma); if (ret) { shm_close(vma); return ret; } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; return 0; } static int shm_release(struct inode *ino, struct file *file) { struct shm_file_data *sfd = shm_file_data(file); put_ipc_ns(sfd->ns); fput(sfd->file); shm_file_data(file) = NULL; kfree(sfd); return 0; } static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fsync) return -EINVAL; return sfd->file->f_op->fsync(sfd->file, start, end, datasync); } static long shm_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fallocate) return -EOPNOTSUPP; return sfd->file->f_op->fallocate(file, mode, offset, len); } static unsigned long shm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct shm_file_data *sfd = shm_file_data(file); return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len, pgoff, flags); } static const struct file_operations shm_file_operations = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; /* * shm_file_operations_huge is now identical to shm_file_operations, * but we keep it distinct for the sake of is_file_shm_hugepages(). */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; bool is_file_shm_hugepages(struct file *file) { return file->f_op == &shm_file_operations_huge; } static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .may_split = shm_may_split, .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, #endif }; /** * newseg - Create a new shared memory segment * @ns: namespace * @params: ptr to the structure that contains key, size and shmflg * * Called with shm_ids.rwsem held as a writer. */ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) { key_t key = params->key; int shmflg = params->flg; size_t size = params->u.size; int error; struct shmid_kernel *shp; size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; struct file *file; char name[13]; vm_flags_t acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; if (numpages << PAGE_SHIFT < size) return -ENOSPC; if (ns->shm_tot + numpages < ns->shm_tot || ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; shp->shm_perm.mode = (shmflg & S_IRWXUGO); shp->mlock_ucounts = NULL; shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); if (error) { kfree(shp); return error; } sprintf(name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { struct hstate *hs; size_t hugesize; hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); if (!hs) { error = -EINVAL; goto no_file; } hugesize = ALIGN(size, huge_page_size(hs)); /* hugetlb_file_setup applies strict accounting */ if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, hugesize, acctflag, &shp->mlock_ucounts, HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) acctflag = VM_NORESERVE; file = shmem_kernel_file_setup(name, size, acctflag); } error = PTR_ERR(file); if (IS_ERR(file)) goto no_file; shp->shm_cprid = get_pid(task_tgid(current)); shp->shm_lprid = NULL; shp->shm_atim = shp->shm_dtim = 0; shp->shm_ctim = ktime_get_real_seconds(); shp->shm_segsz = size; shp->shm_nattch = 0; shp->shm_file = file; shp->shm_creator = current; /* ipc_addid() locks shp upon success. */ error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); if (error < 0) goto no_id; shp->ns = ns; task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. * proc-ps tools use this. Changing this will break them. */ file_inode(file)->i_ino = shp->shm_perm.id; ns->shm_tot += numpages; error = shp->shm_perm.id; ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); return error; no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); if (is_file_hugepages(file) && shp->mlock_ucounts) user_shm_unlock(size, shp->mlock_ucounts); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; no_file: call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } /* * Called with shm_ids.rwsem and ipcp locked. */ static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); if (shp->shm_segsz < params->u.size) return -EINVAL; return 0; } long ksys_shmget(key_t key, size_t size, int shmflg) { struct ipc_namespace *ns; static const struct ipc_ops shm_ops = { .getnew = newseg, .associate = security_shm_associate, .more_checks = shm_more_checks, }; struct ipc_params shm_params; ns = current->nsproxy->ipc_ns; shm_params.key = key; shm_params.flg = shmflg; shm_params.u.size = size; return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); } SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { return ksys_shmget(key, size, shmflg); } static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shmid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); out.shm_segsz = in->shm_segsz; out.shm_atime = in->shm_atime; out.shm_dtime = in->shm_dtime; out.shm_ctime = in->shm_ctime; out.shm_cpid = in->shm_cpid; out.shm_lpid = in->shm_lpid; out.shm_nattch = in->shm_nattch; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct shmid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->shm_perm.uid = tbuf_old.shm_perm.uid; out->shm_perm.gid = tbuf_old.shm_perm.gid; out->shm_perm.mode = tbuf_old.shm_perm.mode; return 0; } default: return -EINVAL; } } static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shminfo out; if (in->shmmax > INT_MAX) out.shmmax = INT_MAX; else out.shmmax = (int)in->shmmax; out.shmmin = in->shmmin; out.shmmni = in->shmmni; out.shmseg = in->shmseg; out.shmall = in->shmall; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } /* * Calculate and add used RSS and swap pages of a shm. * Called with shm_ids.rwsem held as a reader */ static void shm_add_rss_swap(struct shmid_kernel *shp, unsigned long *rss_add, unsigned long *swp_add) { struct inode *inode; inode = file_inode(shp->shm_file); if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_file(shp->shm_file); *rss_add += pages_per_huge_page(h) * mapping->nrpages; } else { #ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock_irq(&info->lock); *rss_add += inode->i_mapping->nrpages; *swp_add += info->swapped; spin_unlock_irq(&info->lock); #else *rss_add += inode->i_mapping->nrpages; #endif } } /* * Called with shm_ids.rwsem held as a reader */ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, unsigned long *swp) { int next_id; int total, in_use; *rss = 0; *swp = 0; in_use = shm_ids(ns).in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { struct kern_ipc_perm *ipc; struct shmid_kernel *shp; ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); if (ipc == NULL) continue; shp = container_of(ipc, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, rss, swp); total++; } } /* * This function handles some shmctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *shmid64) { struct kern_ipc_perm *ipcp; struct shmid_kernel *shp; int err; down_write(&shm_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd, &shmid64->shm_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } shp = container_of(ipcp, struct shmid_kernel, shm_perm); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&shp->shm_perm); /* do_shm_rmid unlocks the ipc object and rcu */ do_shm_rmid(ns, ipcp); goto out_up; case IPC_SET: ipc_lock_object(&shp->shm_perm); err = ipc_update_perm(&shmid64->shm_perm, ipcp); if (err) goto out_unlock0; shp->shm_ctim = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&shm_ids(ns).rwsem); return err; } static int shmctl_ipc_info(struct ipc_namespace *ns, struct shminfo64 *shminfo) { int err = security_shm_shmctl(NULL, IPC_INFO); if (!err) { memset(shminfo, 0, sizeof(*shminfo)); shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni; shminfo->shmmax = ns->shm_ctlmax; shminfo->shmall = ns->shm_ctlall; shminfo->shmmin = SHMMIN; down_read(&shm_ids(ns).rwsem); err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_shm_info(struct ipc_namespace *ns, struct shm_info *shm_info) { int err = security_shm_shmctl(NULL, SHM_INFO); if (!err) { memset(shm_info, 0, sizeof(*shm_info)); down_read(&shm_ids(ns).rwsem); shm_info->used_ids = shm_ids(ns).in_use; shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp); shm_info->shm_tot = ns->shm_tot; shm_info->swap_attempts = 0; shm_info->swap_successes = 0; err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_stat(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *tbuf) { struct shmid_kernel *shp; int err; memset(tbuf, 0, sizeof(*tbuf)); rcu_read_lock(); if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) { shp = shm_obtain_object(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } else { /* IPC_STAT */ shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } /* * Semantically SHM_STAT_ANY ought to be identical to * that functionality provided by the /proc/sysvipc/ * interface. As such, only audit these calls and * do not do traditional S_IRUGO permission checks on * the ipc object. */ if (cmd == SHM_STAT_ANY) audit_ipc_obj(&shp->shm_perm); else { err = -EACCES; if (ipcperms(ns, &shp->shm_perm, S_IRUGO)) goto out_unlock; } err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); tbuf->shm_segsz = shp->shm_segsz; tbuf->shm_atime = shp->shm_atim; tbuf->shm_dtime = shp->shm_dtim; tbuf->shm_ctime = shp->shm_ctim; #ifndef CONFIG_64BIT tbuf->shm_atime_high = shp->shm_atim >> 32; tbuf->shm_dtime_high = shp->shm_dtim >> 32; tbuf->shm_ctime_high = shp->shm_ctim >> 32; #endif tbuf->shm_cpid = pid_vnr(shp->shm_cprid); tbuf->shm_lpid = pid_vnr(shp->shm_lprid); tbuf->shm_nattch = shp->shm_nattch; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SHM_STAT and SHM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = shp->shm_perm.id; } ipc_unlock_object(&shp->shm_perm); out_unlock: rcu_read_unlock(); return err; } static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) { struct shmid_kernel *shp; struct file *shm_file; int err; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock1; } audit_ipc_obj(&(shp->shm_perm)); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { err = -EIDRM; goto out_unlock0; } if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) { kuid_t euid = current_euid(); if (!uid_eq(euid, shp->shm_perm.uid) && !uid_eq(euid, shp->shm_perm.cuid)) { err = -EPERM; goto out_unlock0; } if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) { err = -EPERM; goto out_unlock0; } } shm_file = shp->shm_file; if (is_file_hugepages(shm_file)) goto out_unlock0; if (cmd == SHM_LOCK) { struct ucounts *ucounts = current_ucounts(); err = shmem_lock(shm_file, 1, ucounts); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { shp->shm_perm.mode |= SHM_LOCKED; shp->mlock_ucounts = ucounts; } goto out_unlock0; } /* SHM_UNLOCK */ if (!(shp->shm_perm.mode & SHM_LOCKED)) goto out_unlock0; shmem_lock(shm_file, 0, shp->mlock_ucounts); shp->shm_perm.mode &= ~SHM_LOCKED; shp->mlock_ucounts = NULL; get_file(shm_file); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); shmem_unlock_mapping(shm_file->f_mapping); fput(shm_file); return err; out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); return err; } static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) { int err; struct ipc_namespace *ns; struct shmid64_ds sem64; if (cmd < 0 || shmid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_shminfo_to_user(buf, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (copy_to_user(buf, &shm_info, sizeof(shm_info))) err = -EFAULT; return err; } case SHM_STAT: case SHM_STAT_ANY: case IPC_STAT: { err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_shmid_to_user(buf, &sem64, version)) err = -EFAULT; return err; } case IPC_SET: if (copy_shmid_from_user(&sem64, buf, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } } SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_shmctl(shmid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_shmctl(shmid, cmd, buf, version); } SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_old_shmctl(shmid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_shmid_ds { struct compat_ipc_perm shm_perm; int shm_segsz; old_time32_t shm_atime; old_time32_t shm_dtime; old_time32_t shm_ctime; compat_ipc_pid_t shm_cpid; compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; unsigned short shm_unused; compat_uptr_t shm_unused2; compat_uptr_t shm_unused3; }; struct compat_shminfo64 { compat_ulong_t shmmax; compat_ulong_t shmmin; compat_ulong_t shmmni; compat_ulong_t shmseg; compat_ulong_t shmall; compat_ulong_t __unused1; compat_ulong_t __unused2; compat_ulong_t __unused3; compat_ulong_t __unused4; }; struct compat_shm_info { compat_int_t used_ids; compat_ulong_t shm_tot, shm_rss, shm_swp; compat_ulong_t swap_attempts, swap_successes; }; static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { if (in->shmmax > INT_MAX) in->shmmax = INT_MAX; if (version == IPC_64) { struct compat_shminfo64 info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } else { struct shminfo info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } } static int put_compat_shm_info(struct shm_info *ip, struct compat_shm_info __user *uip) { struct compat_shm_info info; memset(&info, 0, sizeof(info)); info.used_ids = ip->used_ids; info.shm_tot = ip->shm_tot; info.shm_rss = ip->shm_rss; info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { if (version == IPC_64) { struct compat_shmid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm); v.shm_atime = lower_32_bits(in->shm_atime); v.shm_atime_high = upper_32_bits(in->shm_atime); v.shm_dtime = lower_32_bits(in->shm_dtime); v.shm_dtime_high = upper_32_bits(in->shm_dtime); v.shm_ctime = lower_32_bits(in->shm_ctime); v.shm_ctime_high = upper_32_bits(in->shm_ctime); v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_shmid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.shm_perm, &in->shm_perm); v.shm_perm.key = in->shm_perm.key; v.shm_atime = in->shm_atime; v.shm_dtime = in->shm_dtime; v.shm_ctime = in->shm_ctime; v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } } static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_shmid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm); } else { struct compat_shmid_ds __user *p = buf; return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm); } } static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; struct shmid64_ds sem64; int err; ns = current->nsproxy->ipc_ns; if (cmd < 0 || shmid < 0) return -EINVAL; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_compat_shminfo_to_user(uptr, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (put_compat_shm_info(&shm_info, uptr)) err = -EFAULT; return err; } case IPC_STAT: case SHM_STAT_ANY: case SHM_STAT: err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_compat_shmid_to_user(uptr, &sem64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_shmid_from_user(&sem64, uptr, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } return err; } COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_shmctl(shmid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_old_shmctl(shmid, cmd, uptr); } #endif #endif /* * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. * * NOTE! Despite the name, this is NOT a direct system call entrypoint. The * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr = (unsigned long)shmaddr; unsigned long size; struct file *file, *base; int err; unsigned long flags = MAP_SHARED; unsigned long prot; int acc_mode; struct ipc_namespace *ns; struct shm_file_data *sfd; int f_flags; unsigned long populate = 0; err = -EINVAL; if (shmid < 0) goto out; if (addr) { if (addr & (shmlba - 1)) { if (shmflg & SHM_RND) { addr &= ~(shmlba - 1); /* round down */ /* * Ensure that the round-down is non-nil * when remapping. This can happen for * cases when addr < shmlba. */ if (!addr && (shmflg & SHM_REMAP)) goto out; } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif goto out; } flags |= MAP_FIXED; } else if ((shmflg & SHM_REMAP)) goto out; if (shmflg & SHM_RDONLY) { prot = PROT_READ; acc_mode = S_IRUGO; f_flags = O_RDONLY; } else { prot = PROT_READ | PROT_WRITE; acc_mode = S_IRUGO | S_IWUGO; f_flags = O_RDWR; } if (shmflg & SHM_EXEC) { prot |= PROT_EXEC; acc_mode |= S_IXUGO; } /* * We cannot rely on the fs check since SYSV IPC does have an * additional creator id... */ ns = current->nsproxy->ipc_ns; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } err = -EACCES; if (ipcperms(ns, &shp->shm_perm, acc_mode)) goto out_unlock; err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } /* * We need to take a reference to the real shm file to prevent the * pointer from becoming stale in cases where the lifetime of the outer * file extends beyond that of the shm segment. It's not usually * possible, but it can happen during remap_file_pages() emulation as * that unmaps the memory, then does ->mmap() via file reference only. * We'll deny the ->mmap() if the shm segment was since removed, but to * detect shm ID reuse we need to compare the file pointers. */ base = get_file(shp->shm_file); shp->shm_nattch++; size = i_size_read(file_inode(base)); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); err = -ENOMEM; sfd = kzalloc(sizeof(*sfd), GFP_KERNEL); if (!sfd) { fput(base); goto out_nattch; } file = alloc_file_clone(base, f_flags, is_file_hugepages(base) ? &shm_file_operations_huge : &shm_file_operations); err = PTR_ERR(file); if (IS_ERR(file)) { kfree(sfd); fput(base); goto out_nattch; } sfd->id = shp->shm_perm.id; sfd->ns = get_ipc_ns(ns); sfd->file = base; sfd->vm_ops = NULL; file->private_data = sfd; err = security_mmap_file(file, prot, flags); if (err) goto out_fput; if (mmap_write_lock_killable(current->mm)) { err = -EINTR; goto out_fput; } if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; if (addr + size < addr) goto invalid; if (find_vma_intersection(current->mm, addr, addr + size)) goto invalid; } addr = do_mmap(file, addr, size, prot, flags, 0, &populate, NULL); *raddr = addr; err = 0; if (IS_ERR_VALUE(addr)) err = (long)addr; invalid: mmap_write_unlock(current->mm); if (populate) mm_populate(addr, populate); out_fput: fput(file); out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); up_write(&shm_ids(ns).rwsem); return err; out_unlock: rcu_read_unlock(); out: return err; } SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #ifdef CONFIG_COMPAT #ifndef COMPAT_SHMLBA #define COMPAT_SHMLBA SHMLBA #endif COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #endif /* * detach and kill segment if marked destroyed. * The work is done in shm_close. */ long ksys_shmdt(char __user *shmaddr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long addr = (unsigned long)shmaddr; int retval = -EINVAL; #ifdef CONFIG_MMU loff_t size = 0; struct file *file; struct vm_area_struct *next; #endif if (addr & ~PAGE_MASK) return retval; if (mmap_write_lock_killable(mm)) return -EINTR; /* * This function tries to be smart and unmap shm segments that * were modified by partial mlock or munmap calls: * - It first determines the size of the shm segment that should be * unmapped: It searches for a vma that is backed by shm and that * started at address shmaddr. It records it's size and then unmaps * it. * - Then it unmaps all shm vmas that started at shmaddr and that * are within the initially determined size and that are from the * same shm segment from which we determined the size. * Errors from do_munmap are ignored: the function only fails if * it's called with invalid parameters or if it's called to unmap * a part of a vma. Both calls in this function are for full vmas, * the parameters are directly copied from the vma itself and always * valid - therefore do_munmap cannot fail. (famous last words?) */ /* * If it had been mremap()'d, the starting address would not * match the usual checks anyway. So assume all vma's are * above the starting address given. */ vma = find_vma(mm, addr); #ifdef CONFIG_MMU while (vma) { next = vma->vm_next; /* * Check if the starting address would match, i.e. it's * a fragment created by mprotect() and/or munmap(), or it * otherwise it starts at this address with no hassles. */ if ((vma->vm_ops == &shm_vm_ops) && (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { /* * Record the file of the shm segment being * unmapped. With mremap(), someone could place * page from another segment but with equal offsets * in the range we are unmapping. */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next * loop that uses the size information to stop * searching for matching vma's. */ retval = 0; vma = next; break; } vma = next; } /* * We need look no further than the maximum address a fragment * could possibly have landed at. Also cast things to loff_t to * prevent overflows and make comparisons vs. equal-width types. */ size = PAGE_ALIGN(size); while (vma && (loff_t)(vma->vm_end - addr) <= size) { next = vma->vm_next; /* finding a matching vma now does not alter retval */ if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && (vma->vm_file == file)) do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); vma = next; } #else /* CONFIG_MMU */ /* under NOMMU conditions, the exact address to be destroyed must be * given */ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); retval = 0; } #endif mmap_write_unlock(mm); return retval; } SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { return ksys_shmdt(shmaddr); } #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct shmid_kernel *shp; unsigned long rss = 0, swp = 0; shp = container_of(ipcp, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, &rss, &swp); #if BITS_PER_LONG <= 32 #define SIZE_SPEC "%10lu" #else #define SIZE_SPEC "%21lu" #endif seq_printf(s, "%10d %10d %4o " SIZE_SPEC " %5u %5u " "%5lu %5u %5u %5u %5u %10llu %10llu %10llu " SIZE_SPEC " " SIZE_SPEC "\n", shp->shm_perm.key, shp->shm_perm.id, shp->shm_perm.mode, shp->shm_segsz, pid_nr_ns(shp->shm_cprid, pid_ns), pid_nr_ns(shp->shm_lprid, pid_ns), shp->shm_nattch, from_kuid_munged(user_ns, shp->shm_perm.uid), from_kgid_munged(user_ns, shp->shm_perm.gid), from_kuid_munged(user_ns, shp->shm_perm.cuid), from_kgid_munged(user_ns, shp->shm_perm.cgid), shp->shm_atim, shp->shm_dtim, shp->shm_ctim, rss * PAGE_SIZE, swp * PAGE_SIZE); return 0; } #endif |
| 2 1 3 3 3 86 4 62 31 31 | 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 | /* 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. * * Definitions for the UDP module. * * Version: @(#)udp.h 1.0.2 05/07/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Alan Cox : Turned on udp checksums. I don't want to * chase 'memory corruption' bugs that aren't! */ #ifndef _UDP_H #define _UDP_H #include <linux/list.h> #include <linux/bug.h> #include <net/inet_sock.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <linux/ipv6.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/indirect_call_wrapper.h> /** * struct udp_skb_cb - UDP(-Lite) private variables * * @header: private variables used by IPv4/IPv6 * @cscov: checksum coverage length (UDP-Lite only) * @partial_cov: if set indicates partial csum coverage */ struct udp_skb_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; __u16 cscov; __u8 partial_cov; }; #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** * struct udp_hslot - UDP hash slot * * @head: head of list of sockets * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { struct hlist_head head; int count; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; struct udp_hslot *hash2; unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, struct net *net, unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() */ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { return &table->hash2[hash & table->mask]; } extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; extern int sysctl_udp_rmem_min; extern int sysctl_udp_wmem_min; struct sk_buff; /* * Generic checksumming routines for UDP(-Lite) v4 and v6 */ static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb) { return (UDP_SKB_CB(skb)->cscov == skb->len ? __skb_checksum_complete(skb) : __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov)); } static inline int udp_lib_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __udp_lib_checksum_complete(skb); } /** * udp_csum_outgoing - compute UDPv4/v6 checksum over fragments * @sk: socket we are writing to * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) */ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), 0); skb_queue_walk(&sk->sk_write_queue, skb) { csum = csum_add(csum, skb->csum); } return csum; } static inline __wsum udp_csum(struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), skb->csum); for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) { csum = csum_add(csum, skb->csum); } return csum; } static inline __sum16 udp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base); } void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len); static inline void udp_csum_pull_header(struct sk_buff *skb) { if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) skb->csum = csum_partial(skb->data, sizeof(struct udphdr), skb->csum); skb_pull_rcsum(skb, sizeof(struct udphdr)); UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); } typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); void udp_v6_early_demux(struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { struct udphdr *uh; unsigned int hlen, off; off = skb_gro_offset(skb); hlen = off + sizeof(*uh); uh = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) uh = skb_gro_header_slow(skb, hlen, off); return uh; } /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { BUG(); return 0; } void udp_lib_unhash(struct sock *sk); void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr); u32 udp_flow_hashrnd(void); static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, int min, int max, bool use_eth) { u32 hash; if (min >= max) { /* Use default range */ inet_get_local_port_range(net, &min, &max); } hash = skb_get_hash(skb); if (unlikely(!hash)) { if (use_eth) { /* Can't find a normal hash, caller has indicated an * Ethernet packet so use that to compute a hash. */ hash = jhash(skb->data, 2 * ETH_ALEN, (__force u32) skb->protocol); } else { /* Can't derive any sort of hash for the packet, set * to some consistent random value. */ hash = udp_flow_hashrnd(); } } /* Since this is being sent on the wire obfuscate hash a bit * to minimize possbility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ hash ^= hash << 16; return htons((((u64) hash * (max - min)) >> 32) + min); } static inline int udp_rqueue_get(struct sock *sk) { return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } /* net/ipv4/udp.c */ void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *err) { int off = 0; return __skb_recv_udp(sk, flags, noblock, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); int udp_init_sock(struct sock *sk); int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int __udp_disconnect(struct sock *sk, int flags); int udp_disconnect(struct sock *sk, int flags); __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait); struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6); int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); int udp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() */ struct udp_dev_scratch { /* skb->truesize and the stateless bit are embedded in a single field; * do not use a bitfield since the compiler emits better/smaller code * this way */ u32 _tsize_state; #if BITS_PER_LONG == 64 /* len and the bit needed to compute skb_csum_unnecessary * will be on cold cache lines at recvmsg time. * skb->len can be stored on 16 bits since the udp header has been * already validated and pulled. */ u16 len; bool is_linear; bool csum_unnecessary; #endif }; static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb) { return (struct udp_dev_scratch *)&skb->dev_scratch; } #if BITS_PER_LONG == 64 static inline unsigned int udp_skb_len(struct sk_buff *skb) { return udp_skb_scratch(skb)->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return udp_skb_scratch(skb)->csum_unnecessary; } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return udp_skb_scratch(skb)->is_linear; } #else static inline unsigned int udp_skb_len(struct sk_buff *skb) { return skb->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return skb_csum_unnecessary(skb); } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return !skb_is_nonlinear(skb); } #endif static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, struct iov_iter *to) { int n; n = copy_to_iter(skb->data + off, len, to); if (n == len) return 0; iov_iter_revert(to, n); return -EFAULT; } /* * SNMP statistics for UDP and UDP-Lite */ #define UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP6_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #define UDP6_INC_STATS(net, field, __lite) do { \ if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #if IS_ENABLED(CONFIG_IPV6) #define __UDPX_MIB(sk, ipv4) \ ({ \ ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics) : \ (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ sock_net(sk)->mib.udp_stats_in6); \ }) #else #define __UDPX_MIB(sk, ipv4) \ ({ \ IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics; \ }) #endif #define __UDPX_INC_STATS(sk, field) \ __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; struct udp_table *udp_table; }; struct udp_iter_state { struct seq_net_private p; int bucket; struct udp_seq_afinfo *bpf_seq_afinfo; }; void *udp_seq_start(struct seq_file *seq, loff_t *pos); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void udp_seq_stop(struct seq_file *seq, void *v); extern const struct seq_operations udp_seq_ops; extern const struct seq_operations udp6_seq_ops; int udp4_proc_init(void); void udp4_proc_exit(void); #endif /* CONFIG_PROC_FS */ int udpv4_offload_init(void); void udp_init(void); DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); void udp_encap_disable(void); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif static inline struct sk_buff *udp_rcv_segment(struct sock *sk, struct sk_buff *skb, bool ipv4) { netdev_features_t features = NETIF_F_SG; struct sk_buff *segs; /* Avoid csum recalculation by skb_segment unless userspace explicitly * asks for the final checksum values */ if (!inet_get_convert_csum(sk)) features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; /* UDP segmentation expects packets of type CHECKSUM_PARTIAL or * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. * Reset in this specific case, where PARTIAL is both correct and * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; /* the GSO CB lays after the UDP one, no need to save and restore any * CB fragment */ segs = __skb_gso_segment(skb, features, false); if (IS_ERR_OR_NULL(segs)) { int segs_nr = skb_shinfo(skb)->gso_segs; atomic_add(segs_nr, &sk->sk_drops); SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); kfree_skb(skb); return NULL; } consume_skb(skb); return segs; } static inline void udp_post_segment_fix_csum(struct sk_buff *skb) { /* UDP-lite can't land here - no GRO */ WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov); /* UDP packets generated with UDP_SEGMENT and traversing: * * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx) * * can reach an UDP socket with CHECKSUM_NONE, because * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE. * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will * have a valid checksum, as the GRO engine validates the UDP csum * before the aggregation and nobody strips such info in between. * Instead of adding another check in the tunnel fastpath, we can force * a valid csum after the segmentation. * Additionally fixup the UDP CB. */ UDP_SKB_CB(skb)->cscov = skb->len; if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid) skb->csum_valid = 1; } #ifdef CONFIG_BPF_SYSCALL struct sk_psock; struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); #endif #endif /* _UDP_H */ |
| 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 | // SPDX-License-Identifier: GPL-2.0-only /* * IPV4 GSO/GRO offload support * Linux INET implementation * * Copyright (C) 2016 secunet Security Networks AG * Author: Steffen Klassert <steffen.klassert@secunet.com> * * ESP GRO support */ #include <linux/skbuff.h> #include <linux/init.h> #include <net/protocol.h> #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> #include <linux/scatterlist.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/udp.h> static struct sk_buff *esp4_gro_receive(struct list_head *head, struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; struct xfrm_state *x; __be32 seq; __be32 spi; if (!pskb_pull(skb, offset)) return NULL; if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0) goto out; xo = xfrm_offload(skb); if (!xo || !(xo->flags & CRYPTO_DONE)) { struct sec_path *sp = secpath_set(skb); if (!sp) goto out; if (sp->len == XFRM_MAX_DEPTH) goto out_reset; x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ip_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET); if (!x) goto out_reset; skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; sp->olen++; xo = xfrm_offload(skb); if (!xo) goto out_reset; } xo->flags |= XFRM_GRO; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); XFRM_SPI_SKB_CB(skb)->seq = seq; /* We don't need to handle errors from xfrm_input, it does all * the error handling and frees the resources on error. */ xfrm_input(skb, IPPROTO_ESP, spi, -2); return ERR_PTR(-EINPROGRESS); out_reset: secpath_reset(skb); out: skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; return NULL; } static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb) { struct ip_esp_hdr *esph; struct iphdr *iph = ip_hdr(skb); struct xfrm_offload *xo = xfrm_offload(skb); int proto = iph->protocol; skb_push(skb, -skb_network_offset(skb)); esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); xo->proto = proto; } static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { __skb_push(skb, skb->mac_len); return skb_mac_gso_segment(skb, features); } static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct xfrm_offload *xo = xfrm_offload(skb); skb->transport_header += x->props.header_len; ops = rcu_dereference(inet_offloads[xo->proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; u8 proto = xo->proto; skb->transport_header += x->props.header_len; if (x->sel.family != AF_INET6) { if (proto == IPPROTO_BEETPH) { struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; skb->transport_header += ph->hdrlen * 8; proto = ph->nexthdr; } else { skb->transport_header -= IPV4_BEET_PHMAXLEN; } } else { __be16 frag; skb->transport_header += ipv6_skip_exthdr(skb, 0, &proto, &frag); if (proto == IPPROTO_TCP) skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; } if (proto == IPPROTO_IPV6) skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; __skb_pull(skb, skb_transport_offset(skb)); ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: return xfrm4_tunnel_gso_segment(x, skb, features); case XFRM_MODE_TRANSPORT: return xfrm4_transport_gso_segment(x, skb, features); case XFRM_MODE_BEET: return xfrm4_beet_gso_segment(x, skb, features); } return ERR_PTR(-EOPNOTSUPP); } static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct xfrm_state *x; struct ip_esp_hdr *esph; struct crypto_aead *aead; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; if (!xo) return ERR_PTR(-EINVAL); if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP)) return ERR_PTR(-EINVAL); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; aead = x->data; esph = ip_esp_hdr(skb); if (esph->spi != x->id.spi) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) return ERR_PTR(-EINVAL); __skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)); skb->encap_hdr_csum = 1; if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) && !(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM) && !(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM)) esp_features = features & ~(NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; return xfrm4_outer_mode_gso_segment(x, skb, esp_features); } static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb) { struct crypto_aead *aead = x->data; struct xfrm_offload *xo = xfrm_offload(skb); if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead))) return -EINVAL; if (!(xo->flags & CRYPTO_DONE)) skb->ip_summed = CHECKSUM_NONE; return esp_input_done2(skb, 0); } static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { int err; int alen; int blksize; struct xfrm_offload *xo; struct ip_esp_hdr *esph; struct crypto_aead *aead; struct esp_info esp; bool hw_offload = true; __u32 seq; esp.inplace = true; xo = xfrm_offload(skb); if (!xo) return -EINVAL; if ((!(features & NETIF_F_HW_ESP) && !(skb->dev->gso_partial_features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev) { xo->flags |= CRYPTO_FALLBACK; hw_offload = false; } esp.proto = xo->proto; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); esp.tfclen = 0; /* XXX: Add support for tfc padding here. */ blksize = ALIGN(crypto_aead_blocksize(aead), 4); esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize); esp.plen = esp.clen - skb->len - esp.tfclen; esp.tailen = esp.tfclen + esp.plen + alen; esp.esph = ip_esp_hdr(skb); if (!hw_offload || !skb_is_gso(skb)) { esp.nfrags = esp_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; } seq = xo->seq.low; esph = esp.esph; esph->spi = x->id.spi; skb_push(skb, -skb_network_offset(skb)); if (xo->flags & XFRM_GSO_SEGMENT) { esph->seq_no = htonl(seq); if (!skb_is_gso(skb)) xo->seq.low++; else xo->seq.low += skb_shinfo(skb)->gso_segs; } if (xo->seq.low < seq) xo->seq.hi++; esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); if (hw_offload) { if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) return -ENOMEM; xo = xfrm_offload(skb); if (!xo) return -EINVAL; xo->flags |= XFRM_XMIT; return 0; } err = esp_output_tail(x, skb, &esp); if (err) return err; secpath_reset(skb); if (skb_needs_linearize(skb, skb->dev->features) && __skb_linearize(skb)) return -ENOMEM; return 0; } static const struct net_offload esp4_offload = { .callbacks = { .gro_receive = esp4_gro_receive, .gso_segment = esp4_gso_segment, }, }; static const struct xfrm_type_offload esp_type_offload = { .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp_input_tail, .xmit = esp_xmit, .encap = esp4_gso_encap, }; static int __init esp4_offload_init(void) { if (xfrm_register_type_offload(&esp_type_offload, AF_INET) < 0) { pr_info("%s: can't add xfrm type offload\n", __func__); return -EAGAIN; } return inet_add_offload(&esp4_offload, IPPROTO_ESP); } static void __exit esp4_offload_exit(void) { xfrm_unregister_type_offload(&esp_type_offload, AF_INET); inet_del_offload(&esp4_offload, IPPROTO_ESP); } module_init(esp4_offload_init); module_exit(esp4_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP); MODULE_DESCRIPTION("IPV4 GSO/GRO offload support"); |
| 346 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Rewritten and vastly simplified by Rusty Russell for in-kernel * module loader: * Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation */ #ifndef _LINUX_KALLSYMS_H #define _LINUX_KALLSYMS_H #include <linux/errno.h> #include <linux/buildid.h> #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/mm.h> #include <linux/module.h> #include <asm/sections.h> #define KSYM_NAME_LEN 128 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \ (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \ (BUILD_ID_SIZE_MAX * 2) + 1) struct cred; struct module; static inline int is_kernel_inittext(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr <= (unsigned long)_einittext) return 1; return 0; } static inline int is_kernel_text(unsigned long addr) { if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) || arch_is_kernel_text(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) return 1; return in_gate_area_no_mm(addr); } static inline int is_ksym_addr(unsigned long addr) { if (IS_ENABLED(CONFIG_KALLSYMS_ALL)) return is_kernel(addr); return is_kernel_text(addr) || is_kernel_inittext(addr); } static inline void *dereference_symbol_descriptor(void *ptr) { #ifdef HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); if (is_ksym_addr((unsigned long)ptr)) return ptr; preempt_disable(); mod = __module_address((unsigned long)ptr); preempt_enable(); if (mod) ptr = dereference_module_function_descriptor(mod, ptr); #endif return ptr; } #ifdef CONFIG_KALLSYMS int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); /* Lookup an address. modname is set to NULL if it's in the kernel. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf); /* Look up a kernel symbol and return it in a text buffer. */ extern int sprint_symbol(char *buffer, unsigned long address); extern int sprint_symbol_build_id(char *buffer, unsigned long address); extern int sprint_symbol_no_offset(char *buffer, unsigned long address); extern int sprint_backtrace(char *buffer, unsigned long address); extern int sprint_backtrace_build_id(char *buffer, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* How and when do we show kallsyms values? */ extern bool kallsyms_show_value(const struct cred *cred); #else /* !CONFIG_KALLSYMS */ static inline unsigned long kallsyms_lookup_name(const char *name) { return 0; } static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { return 0; } static inline const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { return NULL; } static inline int sprint_symbol(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_symbol_build_id(char *buffer, unsigned long address) { *buffer = '\0'; return 0; } static inline int sprint_symbol_no_offset(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_backtrace(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_backtrace_build_id(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int lookup_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { return -ERANGE; } static inline bool kallsyms_show_value(const struct cred *cred) { return false; } static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { return -EOPNOTSUPP; } #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) { printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ |
| 203 203 8 8 202 149 70 70 71 203 71 149 20 15 21 21 21 21 21 1308 21 21 21 21 21 21 21 97 97 7 16 16 16 16 15 16 16 20 20 4 20 14 20 20 22 22 22 6 21 21 21 16 20 21 22 1292 1299 1298 1290 1295 1294 1298 1298 1217 1226 1223 96 97 80 95 97 97 96 97 97 97 97 97 97 97 96 97 419 422 422 43 422 420 107 98 98 98 107 413 94 421 35 11 35 412 412 412 412 409 412 412 409 410 411 412 412 411 35 35 35 35 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; /* Protecting only lru_rotate.pvec which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct pagevec pvec; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following struct pagevec are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct lru_pvecs { local_lock_t lock; struct pagevec lru_add; struct pagevec lru_deactivate_file; struct pagevec lru_deactivate; struct pagevec lru_lazyfree; #ifdef CONFIG_SMP struct pagevec activate_page; #endif }; static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. */ static void __page_cache_release(struct page *page) { if (PageLRU(page)) { struct lruvec *lruvec; unsigned long flags; lruvec = lock_page_lruvec_irqsave(page, &flags); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); } __ClearPageWaiters(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); free_unref_page(page, 0); } static void __put_compound_page(struct page *page) { /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ if (!PageHuge(page)) __page_cache_release(page); destroy_compound_page(page); } void __put_page(struct page *page) { if (is_zone_device_page(page)) { put_dev_pagemap(page->pgmap); /* * The page belongs to the device that created pgmap. Do * not return it to page allocator. */ return; } if (unlikely(PageCompound(page))) __put_compound_page(page); else __put_single_page(page); } EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * * Release a list of pages which are strung together on page.lru. Currently * used by read_cache_pages() and related error recovery code. */ void put_pages_list(struct list_head *pages) { while (!list_empty(pages)) { struct page *victim; victim = lru_to_page(pages); list_del(&victim->lru); put_page(victim); } } EXPORT_SYMBOL(put_pages_list); /* * get_kernel_pages() - pin kernel pages in memory * @kiov: An array of struct kvec structures * @nr_segs: number of segments to pin * @write: pinning for read/write, currently ignored * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * * Returns number of pages pinned. This may be fewer than the number * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. Each page returned must be released * with a put_page() call when it is finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) { int seg; for (seg = 0; seg < nr_segs; seg++) { if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); get_page(pages[seg]); } return seg; } EXPORT_SYMBOL_GPL(get_kernel_pages); static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec)) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; /* block memcg migration during page moving between lru */ if (!TestClearPageLRU(page)) continue; lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); (*move_fn)(page, lruvec); SetPageLRU(page); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) { if (!PageUnevictable(page)) { del_page_from_lru_list(page, lruvec); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, thp_nr_pages(page)); } } /* return true if pagevec needs to drain */ static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page) { bool ret = false; if (!pagevec_add(pvec, page) || PageCompound(page) || lru_cache_disabled()) ret = true; return ret; } /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the * inactive list. * * rotate_reclaimable_page() must disable IRQs, to prevent nasty races. */ void rotate_reclaimable_page(struct page *page) { if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { do { unsigned long lrusize; /* * Hold lruvec->lru_lock is safe here, since * 1) The pinned lruvec in reclaim, or * 2) From a pre-LRU page during refault (which also holds the * rcu lock, so would be safe even if the page was on the LRU * and could move simultaneously to a new lruvec). */ spin_lock_irq(&lruvec->lru_lock); /* Record cost event */ if (file) lruvec->file_cost += nr_pages; else lruvec->anon_cost += nr_pages; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_page(struct page *page) { lru_note_cost(mem_cgroup_page_lruvec(page), page_is_file_lru(page), thp_nr_pages(page)); } static void __activate_page(struct page *page, struct lruvec *lruvec) { if (!PageActive(page) && !PageUnevictable(page)) { int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec); SetPageActive(page); add_page_to_lru_list(page, lruvec); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, __activate_page); } static bool need_activate_page_drain(int cpu) { return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } static void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, __activate_page); local_unlock(&lru_pvecs.lock); } } #else static inline void activate_page_drain(int cpu) { } static void activate_page(struct page *page) { struct lruvec *lruvec; page = compound_head(page); if (TestClearPageLRU(page)) { lruvec = lock_page_lruvec_irq(page); __activate_page(page, lruvec); unlock_page_lruvec_irq(lruvec); SetPageLRU(page); } } #endif static void __lru_cache_activate_page(struct page *page) { struct pagevec *pvec; int i; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); /* * Search backwards on the optimistic assumption that the page being * activated has just been added to this pagevec. Note that only * the local pagevec is examined as a !PageLRU page could be in the * process of being released, reclaimed, migrated or on a remote * pagevec that is currently being drained. Furthermore, marking * a remote pagevec's page PageActive potentially hits a race where * a page is marked PageActive just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; if (pagevec_page == page) { SetPageActive(page); break; } } local_unlock(&lru_pvecs.lock); } /* * Mark a page as having seen activity. * * inactive,unreferenced -> inactive,referenced * inactive,referenced -> active,unreferenced * active,unreferenced -> active,referenced * * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ void mark_page_accessed(struct page *page) { page = compound_head(page); if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ if (PageLRU(page)) activate_page(page); else __lru_cache_activate_page(page); ClearPageReferenced(page); workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); } EXPORT_SYMBOL(mark_page_accessed); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. * * Queue the page for addition to the LRU via pagevec. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * pagevec is drained. This gives a chance for the caller of lru_cache_add() * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { struct pagevec *pvec; VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); if (pagevec_add_and_need_flush(pvec, page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * * Place @page on the inactive or unevictable LRU list, depending on its * evictability. */ void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { bool unevictable; VM_BUG_ON_PAGE(PageLRU(page), page); unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_state because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } /* * If the page can not be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the page isn't page_mapped and dirty/writeback, the page * could reclaim asap using PG_reclaim. * * 1. active, mapped page -> none * 2. active, dirty/writeback page -> inactive, head, PG_reclaim * 3. inactive, mapped page -> none * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, why it moves inactive's head, the VM expects the page would * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) { bool active = PageActive(page); int nr_pages = thp_nr_pages(page); if (PageUnevictable(page)) return; /* Some processes are using the page */ if (page_mapped(page)) return; del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); if (PageWriteback(page) || PageDirty(page)) { /* * PG_reclaim could be raced with end_page_writeback * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ add_page_to_lru_list(page, lruvec); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We move that page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec) { if (PageActive(page) && !PageUnevictable(page)) { int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec) { if (PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); /* * Lazyfree pages are clean anonymous pages. They have * PG_swapbacked flag cleared, to distinguish them from normal * anonymous pages */ ClearPageSwapBacked(page); add_page_to_lru_list(page, lruvec); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); if (pagevec_count(pvec)) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn); pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_fn); pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); } /** * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ void deactivate_file_page(struct page *page) { /* * In a workload with many unevictable page such as mprotect, * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn); local_unlock(&lru_pvecs.lock); } } /* * deactivate_page - deactivate a page * @page: page to deactivate * * deactivate_page() moves @page to the inactive list if @page was on the active * list and was not an unevictable page. This is done to accelerate the reclaim * of @page. */ void deactivate_page(struct page *page) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn); local_unlock(&lru_pvecs.lock); } } /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * * mark_page_lazyfree() moves @page to the inactive file list. * This is done to accelerate the reclaim of @page. */ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); local_unlock(&lru_pvecs.lock); } } void lru_add_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); invalidate_bh_lrus_cpu(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee pagevec counter stores visible by this CPU are visible to * other CPUs before loading the current drain generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the new global * drain generation number is stored before loading pagevec counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (force_all_cpus || pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || need_activate_page_drain(cpu) || has_bh_in_lru(cpu, NULL)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of pages to be migrated using isolate_lru_page(). * It drains pages on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); #ifdef CONFIG_SMP /* * lru_add_drain_all in the force mode will schedule draining on * all online CPUs so any calls of lru_cache_disabled wrapped by * local_lock or preemption disabled would be ordered by that. * The atomic operation doesn't need to have stronger ordering * requirements because that is enforeced by the scheduling * guarantees. */ __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * release_pages - batched put_page() * @pages: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @pages. If it * fell to zero, remove the page from the LRU and free it. */ void release_pages(struct page **pages, int nr) { int i; LIST_HEAD(pages_to_free); struct lruvec *lruvec = NULL; unsigned long flags; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the * same lruvec. The lock is held only if lruvec != NULL. */ if (lruvec && ++lock_batch == SWAP_CLUSTER_MAX) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } page = compound_head(page); if (is_huge_zero_page(page)) continue; if (is_zone_device_page(page)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } /* * ZONE_DEVICE pages that return 'false' from * page_is_devmap_managed() do not require special * processing, and instead, expect a call to * put_page_testzero(). */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); continue; } if (put_page_testzero(page)) put_dev_pagemap(page->pgmap); continue; } if (!put_page_testzero(page)) continue; if (PageCompound(page)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { struct lruvec *prev_lruvec = lruvec; lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); if (prev_lruvec != lruvec) lock_batch = 0; del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); } __ClearPageWaiters(page); list_add(&page->lru, &pages_to_free); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); mem_cgroup_uncharge_list(&pages_to_free); free_unref_page_list(&pages_to_free); } EXPORT_SYMBOL(release_pages); /* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { if (!pvec->percpu_pvec_drained) { lru_add_drain(); pvec->percpu_pvec_drained = true; } release_pages(pvec->pages, pagevec_count(pvec)); pagevec_reinit(pvec); } EXPORT_SYMBOL(__pagevec_release); static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) { int was_unevictable = TestClearPageUnevictable(page); int nr_pages = thp_nr_pages(page); VM_BUG_ON_PAGE(PageLRU(page), page); /* * Page becomes evictable in two ways: * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. * 2) Before acquiring LRU lock to put the page to correct LRU and then * a) do PageLRU check with lock [check_move_unevictable_pages] * b) do PageLRU check before lock [clear_page_mlock] * * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need * following strict ordering: * * #0: __pagevec_lru_add_fn #1: clear_page_mlock * * SetPageLRU() TestClearPageMlocked() * smp_mb() // explicit ordering // above provides strict * // ordering * PageMlocked() PageLRU() * * * if '#1' does not observe setting of PG_lru by '#0' and fails * isolation, the explicit barrier will make sure that page_evictable * check will put the page in correct LRU. Without smp_mb(), SetPageLRU * can be reordered after PageMlocked check and can make '#1' to fail * the isolation of the page whose Mlocked bit is cleared (#0 is also * looking at the same page) and the evictable page will be stranded * in an unevictable LRU. */ SetPageLRU(page); smp_mb__after_atomic(); if (page_evictable(page)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { ClearPageActive(page); SetPageUnevictable(page); if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } add_page_to_lru_list(page, lruvec); trace_mm_lru_insertion(page); } /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. */ void __pagevec_lru_add(struct pagevec *pvec) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); __pagevec_lru_add_fn(page, lruvec); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * * find_get_entries() fills both pages and XArray value entries (aka * exceptional entries) into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ void pagevec_remove_exceptionals(struct pagevec *pvec) { int i, j; for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; } /** * pagevec_lookup_range - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search * @start: The starting page index * @end: The final page index * * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE * pages in the mapping starting from index @start and upto index @end * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a * reference against the pages in @pvec. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. We * also update @start to index the next page for the traversal. * * pagevec_lookup_range() returns the number of pages which were found. If this * number is smaller than PAGEVEC_SIZE, the end of specified range has been * reached. */ unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end) { pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_tag); /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } #ifdef CONFIG_DEV_PAGEMAP_OPS void put_devmap_managed_page(struct page *page) { int count; if (WARN_ON_ONCE(!page_is_devmap_managed(page))) return; count = page_ref_dec_return(page); /* * devmap page refcounts are 1-based, rather than 0-based: if * refcount is 1, then the page is free and the refcount is * stable because nobody holds a reference on the page. */ if (count == 1) free_devmap_managed_page(page); else if (!count) __put_page(page); } EXPORT_SYMBOL(put_devmap_managed_page); #endif |
| 152 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tlb #if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TLB_H #include <linux/mm_types.h> #include <linux/tracepoint.h> #define TLB_FLUSH_REASON \ EM( TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" ) \ EM( TLB_REMOTE_SHOOTDOWN, "remote shootdown" ) \ EM( TLB_LOCAL_SHOOTDOWN, "local shootdown" ) \ EM( TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" ) \ EMe( TLB_REMOTE_SEND_IPI, "remote ipi send" ) /* * First define the enums in TLB_FLUSH_REASON to be exported to userspace * via TRACE_DEFINE_ENUM(). */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); TLB_FLUSH_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } TRACE_EVENT(tlb_flush, TP_PROTO(int reason, unsigned long pages), TP_ARGS(reason, pages), TP_STRUCT__entry( __field( int, reason) __field(unsigned long, pages) ), TP_fast_assign( __entry->reason = reason; __entry->pages = pages; ), TP_printk("pages:%ld reason:%s (%d)", __entry->pages, __print_symbolic(__entry->reason, TLB_FLUSH_REASON), __entry->reason) ); #endif /* _TRACE_TLB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 7 7 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> */ #ifndef IEEE80211_RATE_H #define IEEE80211_RATE_H #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" #include "driver-ops.h" struct rate_control_ref { const struct rate_control_ops *ops; void *priv; }; void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_tx_rate_control *txrc); void rate_control_tx_status(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct ieee80211_tx_status *st); void rate_control_rate_init(struct sta_info *sta); void rate_control_rate_update(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct sta_info *sta, u32 changed); static inline void *rate_control_alloc_sta(struct rate_control_ref *ref, struct sta_info *sta, gfp_t gfp) { spin_lock_init(&sta->rate_ctrl_lock); return ref->ops->alloc_sta(ref->priv, &sta->sta, gfp); } static inline void rate_control_free_sta(struct sta_info *sta) { struct rate_control_ref *ref = sta->rate_ctrl; struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; ref->ops->free_sta(ref->priv, ista, priv_sta); } static inline void rate_control_add_sta_debugfs(struct sta_info *sta) { #ifdef CONFIG_MAC80211_DEBUGFS struct rate_control_ref *ref = sta->rate_ctrl; if (ref && sta->debugfs_dir && ref->ops->add_sta_debugfs) ref->ops->add_sta_debugfs(ref->priv, sta->rate_ctrl_priv, sta->debugfs_dir); #endif } extern const struct file_operations rcname_ops; static inline void rate_control_add_debugfs(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfsdir; if (!local->rate_ctrl) return; if (!local->rate_ctrl->ops->add_debugfs) return; debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); local->debugfs.rcdir = debugfsdir; debugfs_create_file("name", 0400, debugfsdir, local->rate_ctrl, &rcname_ops); local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv, debugfsdir); #endif } void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata); /* Get a reference to the rate control algorithm. If `name' is NULL, get the * first available algorithm. */ int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local, const char *name); void rate_control_deinitialize(struct ieee80211_local *local); /* Rate control algorithms */ #ifdef CONFIG_MAC80211_RC_MINSTREL int rc80211_minstrel_init(void); void rc80211_minstrel_exit(void); #else static inline int rc80211_minstrel_init(void) { return 0; } static inline void rc80211_minstrel_exit(void) { } #endif #endif /* IEEE80211_RATE_H */ |
| 54 55 55 55 54 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / __tlb_remove_page() * - tlb_remove_page_size() / __tlb_remove_page_size() * * __tlb_remove_page_size() is the basic primitive that queues a page for * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a * boolean indicating if the queue is (now) full and a call to * tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() * which does the actual freeing of these pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[0]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */ /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ #define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page)) #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct page *pages[0]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) #error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #define tlb_end_vma tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush #if defined(tlb_start_vma) || defined(tlb_end_vma) #error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() #endif /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); } #else static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds)) return; tlb_flush(tlb); mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, page_size)) tlb_flush_mmu(tlb); } static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page_size(tlb, page, PAGE_SIZE); } /* tlb_remove_page * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when * required. */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ #ifndef tlb_start_vma static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); flush_cache_range(vma, vma->vm_start, vma->vm_end); } #endif #ifndef tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } #endif /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 Google LLC. */ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/binfmts.h> #include <linux/lsm_hooks.h> #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> #include <linux/btf_ids.h> #include <linux/ima.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. */ #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ { \ return DEFAULT; \ } #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) BTF_SET_START(bpf_lsm_hooks) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { if (!prog->gpl_compatible) { bpf_log(vlog, "LSM programs must have a GPL compatible license\n"); return -EINVAL; } if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; } return 0; } /* Mask for all the currently supported BPRM option flags */ #define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) { if (flags & ~BPF_F_BRPM_OPTS_MASK) return -EINVAL; bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); return 0; } BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) static const struct bpf_func_proto bpf_bprm_opts_set_proto = { .func = bpf_bprm_opts_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) { return ima_inode_hash(inode, dst, size); } static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) { return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); } BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) static const struct bpf_func_proto bpf_ima_inode_hash_proto = { .func = bpf_ima_inode_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .allowed = bpf_ima_inode_hash_allowed, }; static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_inode_storage_get: return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; #ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; case BPF_FUNC_ima_inode_hash: return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } } /* The set of hooks which are called without pagefaults disabled and are allowed * to "sleep" and thus can be used for sleepable BPF programs. */ BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) BTF_ID(func, bpf_lsm_bpf_map_alloc_security) BTF_ID(func, bpf_lsm_bpf_map_free_security) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) BTF_ID(func, bpf_lsm_bprm_creds_for_exec) BTF_ID(func, bpf_lsm_bprm_creds_from_file) BTF_ID(func, bpf_lsm_capget) BTF_ID(func, bpf_lsm_capset) BTF_ID(func, bpf_lsm_cred_prepare) BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) BTF_ID(func, bpf_lsm_inode_getxattr) BTF_ID(func, bpf_lsm_inode_mknod) BTF_ID(func, bpf_lsm_inode_need_killpriv) BTF_ID(func, bpf_lsm_inode_post_setxattr) BTF_ID(func, bpf_lsm_inode_readlink) BTF_ID(func, bpf_lsm_inode_rename) BTF_ID(func, bpf_lsm_inode_rmdir) BTF_ID(func, bpf_lsm_inode_setattr) BTF_ID(func, bpf_lsm_inode_setxattr) BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernfs_init_security) #ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) #endif /* CONFIG_KEYS */ BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) BTF_ID(func, bpf_lsm_release_secctx) BTF_ID(func, bpf_lsm_sb_alloc_security) BTF_ID(func, bpf_lsm_sb_eat_lsm_opts) BTF_ID(func, bpf_lsm_sb_kern_mount) BTF_ID(func, bpf_lsm_sb_mount) BTF_ID(func, bpf_lsm_sb_remount) BTF_ID(func, bpf_lsm_sb_set_mnt_opts) BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) BTF_ID(func, bpf_lsm_socket_create) BTF_ID(func, bpf_lsm_socket_getpeername) BTF_ID(func, bpf_lsm_socket_getpeersec_dgram) BTF_ID(func, bpf_lsm_socket_getsockname) BTF_ID(func, bpf_lsm_socket_getsockopt) BTF_ID(func, bpf_lsm_socket_listen) BTF_ID(func, bpf_lsm_socket_post_create) BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) BTF_ID(func, bpf_lsm_task_to_inode) BTF_SET_END(sleepable_lsm_hooks) bool bpf_lsm_is_sleepable_hook(u32 btf_id) { return btf_id_set_contains(&sleepable_lsm_hooks, btf_id); } const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; |
| 45 44 45 45 45 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * HT handling * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright 2017 Intel Deutschland GmbH * Copyright(c) 2020-2021 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/export.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "rate.h" static void __check_htcap_disable(struct ieee80211_ht_cap *ht_capa, struct ieee80211_ht_cap *ht_capa_mask, struct ieee80211_sta_ht_cap *ht_cap, u16 flag) { __le16 le_flag = cpu_to_le16(flag); if (ht_capa_mask->cap_info & le_flag) { if (!(ht_capa->cap_info & le_flag)) ht_cap->cap &= ~flag; } } static void __check_htcap_enable(struct ieee80211_ht_cap *ht_capa, struct ieee80211_ht_cap *ht_capa_mask, struct ieee80211_sta_ht_cap *ht_cap, u16 flag) { __le16 le_flag = cpu_to_le16(flag); if ((ht_capa_mask->cap_info & le_flag) && (ht_capa->cap_info & le_flag)) ht_cap->cap |= flag; } void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_ht_cap *ht_cap) { struct ieee80211_ht_cap *ht_capa, *ht_capa_mask; u8 *scaps, *smask; int i; if (!ht_cap->ht_supported) return; switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: ht_capa = &sdata->u.mgd.ht_capa; ht_capa_mask = &sdata->u.mgd.ht_capa_mask; break; case NL80211_IFTYPE_ADHOC: ht_capa = &sdata->u.ibss.ht_capa; ht_capa_mask = &sdata->u.ibss.ht_capa_mask; break; default: WARN_ON_ONCE(1); return; } scaps = (u8 *)(&ht_capa->mcs.rx_mask); smask = (u8 *)(&ht_capa_mask->mcs.rx_mask); /* NOTE: If you add more over-rides here, update register_hw * ht_capa_mod_mask logic in main.c as well. * And, if this method can ever change ht_cap.ht_supported, fix * the check in ieee80211_add_ht_ie. */ /* check for HT over-rides, MCS rates first. */ for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) { u8 m = smask[i]; ht_cap->mcs.rx_mask[i] &= ~m; /* turn off all masked bits */ /* Add back rates that are supported */ ht_cap->mcs.rx_mask[i] |= (m & scaps[i]); } /* Force removal of HT-40 capabilities? */ __check_htcap_disable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_SUP_WIDTH_20_40); __check_htcap_disable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_SGI_40); /* Allow user to disable SGI-20 (SGI-40 is handled above) */ __check_htcap_disable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_SGI_20); /* Allow user to disable the max-AMSDU bit. */ __check_htcap_disable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_MAX_AMSDU); /* Allow user to disable LDPC */ __check_htcap_disable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_LDPC_CODING); /* Allow user to enable 40 MHz intolerant bit. */ __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_40MHZ_INTOLERANT); /* Allow user to enable TX STBC bit */ __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_TX_STBC); /* Allow user to configure RX STBC bits */ if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC)) ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) & IEEE80211_HT_CAP_RX_STBC; /* Allow user to decrease AMPDU factor */ if (ht_capa_mask->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_FACTOR) { u8 n = ht_capa->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_FACTOR; if (n < ht_cap->ampdu_factor) ht_cap->ampdu_factor = n; } /* Allow the user to increase AMPDU density. */ if (ht_capa_mask->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_DENSITY) { u8 n = (ht_capa->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_DENSITY) >> IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT; if (n > ht_cap->ampdu_density) ht_cap->ampdu_density = n; } } bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_ht_cap *ht_cap_ie, struct sta_info *sta) { struct ieee80211_sta_ht_cap ht_cap, own_cap; u8 ampdu_info, tx_mcs_set_cap; int i, max_tx_streams; bool changed; enum ieee80211_sta_rx_bandwidth bw; memset(&ht_cap, 0, sizeof(ht_cap)); if (!ht_cap_ie || !sband->ht_cap.ht_supported) goto apply; ht_cap.ht_supported = true; own_cap = sband->ht_cap; /* * If user has specified capability over-rides, take care * of that if the station we're setting up is the AP or TDLS peer that * we advertised a restricted capability set to. Override * our own capabilities and then use those below. */ if (sdata->vif.type == NL80211_IFTYPE_STATION || sdata->vif.type == NL80211_IFTYPE_ADHOC) ieee80211_apply_htcap_overrides(sdata, &own_cap); /* * The bits listed in this expression should be * the same for the peer and us, if the station * advertises more then we can't use those thus * we mask them out. */ ht_cap.cap = le16_to_cpu(ht_cap_ie->cap_info) & (own_cap.cap | ~(IEEE80211_HT_CAP_LDPC_CODING | IEEE80211_HT_CAP_SUP_WIDTH_20_40 | IEEE80211_HT_CAP_GRN_FLD | IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | IEEE80211_HT_CAP_DSSSCCK40)); /* * The STBC bits are asymmetric -- if we don't have * TX then mask out the peer's RX and vice versa. */ if (!(own_cap.cap & IEEE80211_HT_CAP_TX_STBC)) ht_cap.cap &= ~IEEE80211_HT_CAP_RX_STBC; if (!(own_cap.cap & IEEE80211_HT_CAP_RX_STBC)) ht_cap.cap &= ~IEEE80211_HT_CAP_TX_STBC; ampdu_info = ht_cap_ie->ampdu_params_info; ht_cap.ampdu_factor = ampdu_info & IEEE80211_HT_AMPDU_PARM_FACTOR; ht_cap.ampdu_density = (ampdu_info & IEEE80211_HT_AMPDU_PARM_DENSITY) >> 2; /* own MCS TX capabilities */ tx_mcs_set_cap = own_cap.mcs.tx_params; /* Copy peer MCS TX capabilities, the driver might need them. */ ht_cap.mcs.tx_params = ht_cap_ie->mcs.tx_params; /* can we TX with MCS rates? */ if (!(tx_mcs_set_cap & IEEE80211_HT_MCS_TX_DEFINED)) goto apply; /* Counting from 0, therefore +1 */ if (tx_mcs_set_cap & IEEE80211_HT_MCS_TX_RX_DIFF) max_tx_streams = ((tx_mcs_set_cap & IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK) >> IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT) + 1; else max_tx_streams = IEEE80211_HT_MCS_TX_MAX_STREAMS; /* * 802.11n-2009 20.3.5 / 20.6 says: * - indices 0 to 7 and 32 are single spatial stream * - 8 to 31 are multiple spatial streams using equal modulation * [8..15 for two streams, 16..23 for three and 24..31 for four] * - remainder are multiple spatial streams using unequal modulation */ for (i = 0; i < max_tx_streams; i++) ht_cap.mcs.rx_mask[i] = own_cap.mcs.rx_mask[i] & ht_cap_ie->mcs.rx_mask[i]; if (tx_mcs_set_cap & IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION) for (i = IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE; i < IEEE80211_HT_MCS_MASK_LEN; i++) ht_cap.mcs.rx_mask[i] = own_cap.mcs.rx_mask[i] & ht_cap_ie->mcs.rx_mask[i]; /* handle MCS rate 32 too */ if (own_cap.mcs.rx_mask[32/8] & ht_cap_ie->mcs.rx_mask[32/8] & 1) ht_cap.mcs.rx_mask[32/8] |= 1; /* set Rx highest rate */ ht_cap.mcs.rx_highest = ht_cap_ie->mcs.rx_highest; if (ht_cap.cap & IEEE80211_HT_CAP_MAX_AMSDU) sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_7935; else sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_3839; apply: changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); memcpy(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); switch (sdata->vif.bss_conf.chandef.width) { default: WARN_ON_ONCE(1); fallthrough; case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: bw = IEEE80211_STA_RX_BW_20; break; case NL80211_CHAN_WIDTH_40: case NL80211_CHAN_WIDTH_80: case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_160: bw = ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; break; } sta->sta.bandwidth = bw; sta->cur_max_bandwidth = ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { enum ieee80211_smps_mode smps_mode; switch ((ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >> IEEE80211_HT_CAP_SM_PS_SHIFT) { case WLAN_HT_CAP_SM_PS_INVALID: case WLAN_HT_CAP_SM_PS_STATIC: smps_mode = IEEE80211_SMPS_STATIC; break; case WLAN_HT_CAP_SM_PS_DYNAMIC: smps_mode = IEEE80211_SMPS_DYNAMIC; break; case WLAN_HT_CAP_SM_PS_DISABLED: smps_mode = IEEE80211_SMPS_OFF; break; } if (smps_mode != sta->sta.smps_mode) changed = true; sta->sta.smps_mode = smps_mode; } else { sta->sta.smps_mode = IEEE80211_SMPS_OFF; } return changed; } void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason) { int i; mutex_lock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_LEAVE_QBSS, reason != AGG_STOP_DESTROY_STA && reason != AGG_STOP_PEER_REQUEST); for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_tx_ba_session(sta, i, reason); mutex_unlock(&sta->ampdu_mlme.mtx); /* * In case the tear down is part of a reconfigure due to HW restart * request, it is possible that the low level driver requested to stop * the BA session, so handle it to properly clean tid_tx data. */ if(reason == AGG_STOP_DESTROY_STA) { cancel_work_sync(&sta->ampdu_mlme.work); mutex_lock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { struct tid_ampdu_tx *tid_tx = rcu_dereference_protected_tid_tx(sta, i); if (!tid_tx) continue; if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state)) ieee80211_stop_tx_ba_cb(sta, i, tid_tx); } mutex_unlock(&sta->ampdu_mlme.mtx); } } void ieee80211_ba_session_work(struct work_struct *work) { struct sta_info *sta = container_of(work, struct sta_info, ampdu_mlme.work); struct tid_ampdu_tx *tid_tx; bool blocked; int tid; /* When this flag is set, new sessions should be blocked. */ blocked = test_sta_flag(sta, WLAN_STA_BLOCK_BA); mutex_lock(&sta->ampdu_mlme.mtx); for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { if (test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired)) ___ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_TIMEOUT, true); if (test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_stop_requested)) ___ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_UNSPECIFIED, true); if (!blocked && test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF_HT, false, true, NULL); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, 0, false); spin_lock_bh(&sta->lock); tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; if (!blocked && tid_tx) { /* * Assign it over to the normal tid_tx array * where it "goes live". */ sta->ampdu_mlme.tid_start_tx[tid] = NULL; /* could there be a race? */ if (sta->ampdu_mlme.tid_tx[tid]) kfree(tid_tx); else ieee80211_assign_tid_tx(sta, tid, tid_tx); spin_unlock_bh(&sta->lock); ieee80211_tx_ba_session_handle_start(sta, tid); continue; } spin_unlock_bh(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) continue; if (!blocked && test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state)) ieee80211_start_tx_ba_cb(sta, tid, tid_tx); if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) ___ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_LOCAL_REQUEST); if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state)) ieee80211_stop_tx_ba_cb(sta, tid, tid_tx); } mutex_unlock(&sta->ampdu_mlme.mtx); } void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, const u8 *da, u16 tid, u16 initiator, u16 reason_code) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u16 params; skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = skb_put_zero(skb, 24); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN || sdata->vif.type == NL80211_IFTYPE_MESH_POINT) memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_STATION) memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); skb_put(skb, 1 + sizeof(mgmt->u.action.u.delba)); mgmt->u.action.category = WLAN_CATEGORY_BACK; mgmt->u.action.u.delba.action_code = WLAN_ACTION_DELBA; params = (u16)(initiator << 11); /* bit 11 initiator */ params |= (u16)(tid << 12); /* bit 15:12 TID number */ mgmt->u.action.u.delba.params = cpu_to_le16(params); mgmt->u.action.u.delba.reason_code = cpu_to_le16(reason_code); ieee80211_tx_skb(sdata, skb); } void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len) { u16 tid, params; u16 initiator; params = le16_to_cpu(mgmt->u.action.u.delba.params); tid = (params & IEEE80211_DELBA_PARAM_TID_MASK) >> 12; initiator = (params & IEEE80211_DELBA_PARAM_INITIATOR_MASK) >> 11; ht_dbg_ratelimited(sdata, "delba from %pM (%s) tid %d reason code %d\n", mgmt->sa, initiator ? "initiator" : "recipient", tid, le16_to_cpu(mgmt->u.action.u.delba.reason_code)); if (initiator == WLAN_BACK_INITIATOR) __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_INITIATOR, 0, true); else __ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_PEER_REQUEST); } enum nl80211_smps_mode ieee80211_smps_mode_to_smps_mode(enum ieee80211_smps_mode smps) { switch (smps) { case IEEE80211_SMPS_OFF: return NL80211_SMPS_OFF; case IEEE80211_SMPS_STATIC: return NL80211_SMPS_STATIC; case IEEE80211_SMPS_DYNAMIC: return NL80211_SMPS_DYNAMIC; default: return NL80211_SMPS_OFF; } } int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps, const u8 *da, const u8 *bssid) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *action_frame; /* 27 = header + category + action + smps mode */ skb = dev_alloc_skb(27 + local->hw.extra_tx_headroom); if (!skb) return -ENOMEM; skb_reserve(skb, local->hw.extra_tx_headroom); action_frame = skb_put(skb, 27); memcpy(action_frame->da, da, ETH_ALEN); memcpy(action_frame->sa, sdata->dev->dev_addr, ETH_ALEN); memcpy(action_frame->bssid, bssid, ETH_ALEN); action_frame->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); action_frame->u.action.category = WLAN_CATEGORY_HT; action_frame->u.action.u.ht_smps.action = WLAN_HT_ACTION_SMPS; switch (smps) { case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_NUM_MODES: WARN_ON(1); fallthrough; case IEEE80211_SMPS_OFF: action_frame->u.action.u.ht_smps.smps_control = WLAN_HT_SMPS_CONTROL_DISABLED; break; case IEEE80211_SMPS_STATIC: action_frame->u.action.u.ht_smps.smps_control = WLAN_HT_SMPS_CONTROL_STATIC; break; case IEEE80211_SMPS_DYNAMIC: action_frame->u.action.u.ht_smps.smps_control = WLAN_HT_SMPS_CONTROL_DYNAMIC; break; } /* we'll do more on status of this frame */ IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; ieee80211_tx_skb(sdata, skb); return 0; } void ieee80211_request_smps_mgd_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, u.mgd.request_smps_work); sdata_lock(sdata); __ieee80211_request_smps_mgd(sdata, sdata->u.mgd.driver_smps_mode); sdata_unlock(sdata); } void ieee80211_request_smps(struct ieee80211_vif *vif, enum ieee80211_smps_mode smps_mode) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION)) return; if (sdata->u.mgd.driver_smps_mode == smps_mode) return; sdata->u.mgd.driver_smps_mode = smps_mode; ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.request_smps_work); } /* this might change ... don't want non-open drivers using it */ EXPORT_SYMBOL_GPL(ieee80211_request_smps); |
| 170 170 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Expectation handling for nf_conntrack. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> * (c) 2005-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/netfilter.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/kernel.h> #include <linux/siphash.h> #include <linux/moduleparam.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/netns/hash.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_zones.h> unsigned int nf_ct_expect_hsize __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_expect_hsize); struct hlist_head *nf_ct_expect_hash __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_expect_hash); unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static siphash_key_t nf_ct_expect_hashrnd __read_mostly; /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report) { struct nf_conn_help *master_help = nfct_help(exp->master); struct net *net = nf_ct_exp_net(exp); struct nf_conntrack_net *cnet; WARN_ON(!master_help); WARN_ON(timer_pending(&exp->timeout)); hlist_del_rcu(&exp->hnode); cnet = nf_ct_pernet(net); cnet->expect_count--; hlist_del_rcu(&exp->lnode); master_help->expecting[exp->class]--; nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report); nf_ct_expect_put(exp); NF_CT_STAT_INC(net, expect_delete); } EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report); static void nf_ct_expectation_timed_out(struct timer_list *t) { struct nf_conntrack_expect *exp = from_timer(exp, t, timeout); spin_lock_bh(&nf_conntrack_expect_lock); nf_ct_unlink_expect(exp); spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_put(exp); } static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple) { struct { union nf_inet_addr dst_addr; u32 net_mix; u16 dport; u8 l3num; u8 protonum; } __aligned(SIPHASH_ALIGNMENT) combined; u32 hash; get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd)); memset(&combined, 0, sizeof(combined)); combined.dst_addr = tuple->dst.u3; combined.net_mix = net_hash_mix(n); combined.dport = (__force __u16)tuple->dst.u.all; combined.l3num = tuple->src.l3num; combined.protonum = tuple->dst.protonum; hash = siphash(&combined, sizeof(combined), &nf_ct_expect_hashrnd); return reciprocal_scale(hash, nf_ct_expect_hsize); } static bool nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_expect *i, const struct nf_conntrack_zone *zone, const struct net *net) { return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && net_eq(net, nf_ct_net(i->master)) && nf_ct_zone_equal_any(i->master, zone); } bool nf_ct_remove_expect(struct nf_conntrack_expect *exp) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); return true; } return false; } EXPORT_SYMBOL_GPL(nf_ct_remove_expect); struct nf_conntrack_expect * __nf_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i; unsigned int h; if (!cnet->expect_count) return NULL; h = nf_ct_expect_dst_hash(net, tuple); hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) { if (nf_ct_exp_equal(tuple, i, zone, net)) return i; } return NULL; } EXPORT_SYMBOL_GPL(__nf_ct_expect_find); /* Just find a expectation corresponding to a tuple. */ struct nf_conntrack_expect * nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; rcu_read_lock(); i = __nf_ct_expect_find(net, zone, tuple); if (i && !refcount_inc_not_zero(&i->use)) i = NULL; rcu_read_unlock(); return i; } EXPORT_SYMBOL_GPL(nf_ct_expect_find_get); /* If an expectation for this connection is found, it gets delete from * global list then returned. */ struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; if (!cnet->expect_count) return NULL; h = nf_ct_expect_dst_hash(net, tuple); hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) { if (!(i->flags & NF_CT_EXPECT_INACTIVE) && nf_ct_exp_equal(tuple, i, zone, net)) { exp = i; break; } } if (!exp) return NULL; /* If master is not in hash table yet (ie. packet hasn't left this machine yet), how can other end know about expected? Hence these are not the droids you are looking for (if master ct never got confirmed, we'd hold a reference to it and weird things would happen to future packets). */ if (!nf_ct_is_confirmed(exp->master)) return NULL; /* Avoid race with other CPUs, that for exp->master ct, is * about to invoke ->destroy(), or nf_ct_delete() via timeout * or early_drop(). * * The refcount_inc_not_zero() check tells: If that fails, we * know that the ct is being destroyed. If it succeeds, we * can be sure the ct cannot disappear underneath. */ if (unlikely(nf_ct_is_dying(exp->master) || !refcount_inc_not_zero(&exp->master->ct_general.use))) return NULL; if (exp->flags & NF_CT_EXPECT_PERMANENT) { refcount_inc(&exp->use); return exp; } else if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); return exp; } /* Undo exp->master refcnt increase, if del_timer() failed */ nf_ct_put(exp->master); return NULL; } /* delete all expectations for this conntrack */ void nf_ct_remove_expectations(struct nf_conn *ct) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; struct hlist_node *next; /* Optimization: most connection never expect any others. */ if (!help) return; spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { nf_ct_remove_expect(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_remove_expectations); /* Would two expected things clash? */ static inline int expect_clash(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { /* Part covered by intersection of masks must be unequal, otherwise they clash */ struct nf_conntrack_tuple_mask intersect_mask; int count; intersect_mask.src.u.all = a->mask.src.u.all & b->mask.src.u.all; for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){ intersect_mask.src.u3.all[count] = a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { return nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } static bool master_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b, unsigned int flags) { if (flags & NF_CT_EXP_F_SKIP_MASTER) return true; return a->master == b->master; } /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { spin_lock_bh(&nf_conntrack_expect_lock); nf_ct_remove_expect(exp); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_unexpect_related); /* We don't increase the master conntrack refcount for non-fulfilled * conntracks. During the conntrack destruction, the expectations are * always killed before the conntrack itself */ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) { struct nf_conntrack_expect *new; new = kmem_cache_alloc(nf_ct_expect_cachep, GFP_ATOMIC); if (!new) return NULL; new->master = me; refcount_set(&new->use, 1); return new; } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, u_int8_t family, const union nf_inet_addr *saddr, const union nf_inet_addr *daddr, u_int8_t proto, const __be16 *src, const __be16 *dst) { int len; if (family == AF_INET) len = 4; else len = 16; exp->flags = 0; exp->class = class; exp->expectfn = NULL; exp->helper = NULL; exp->tuple.src.l3num = family; exp->tuple.dst.protonum = proto; if (saddr) { memcpy(&exp->tuple.src.u3, saddr, len); if (sizeof(exp->tuple.src.u3) > len) /* address needs to be cleared for nf_ct_tuple_equal */ memset((void *)&exp->tuple.src.u3 + len, 0x00, sizeof(exp->tuple.src.u3) - len); memset(&exp->mask.src.u3, 0xFF, len); if (sizeof(exp->mask.src.u3) > len) memset((void *)&exp->mask.src.u3 + len, 0x00, sizeof(exp->mask.src.u3) - len); } else { memset(&exp->tuple.src.u3, 0x00, sizeof(exp->tuple.src.u3)); memset(&exp->mask.src.u3, 0x00, sizeof(exp->mask.src.u3)); } if (src) { exp->tuple.src.u.all = *src; exp->mask.src.u.all = htons(0xFFFF); } else { exp->tuple.src.u.all = 0; exp->mask.src.u.all = 0; } memcpy(&exp->tuple.dst.u3, daddr, len); if (sizeof(exp->tuple.dst.u3) > len) /* address needs to be cleared for nf_ct_tuple_equal */ memset((void *)&exp->tuple.dst.u3 + len, 0x00, sizeof(exp->tuple.dst.u3) - len); exp->tuple.dst.u.all = *dst; #if IS_ENABLED(CONFIG_NF_NAT) memset(&exp->saved_addr, 0, sizeof(exp->saved_addr)); memset(&exp->saved_proto, 0, sizeof(exp->saved_proto)); #endif } EXPORT_SYMBOL_GPL(nf_ct_expect_init); static void nf_ct_expect_free_rcu(struct rcu_head *head) { struct nf_conntrack_expect *exp; exp = container_of(head, struct nf_conntrack_expect, rcu); kmem_cache_free(nf_ct_expect_cachep, exp); } void nf_ct_expect_put(struct nf_conntrack_expect *exp) { if (refcount_dec_and_test(&exp->use)) call_rcu(&exp->rcu, nf_ct_expect_free_rcu); } EXPORT_SYMBOL_GPL(nf_ct_expect_put); static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) { struct nf_conntrack_net *cnet; struct nf_conn_help *master_help = nfct_help(exp->master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(exp); unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple); /* two references : one for hash insert, one for the timer */ refcount_add(2, &exp->use); timer_setup(&exp->timeout, nf_ct_expectation_timed_out, 0); helper = rcu_dereference_protected(master_help->helper, lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { exp->timeout.expires = jiffies + helper->expect_policy[exp->class].timeout * HZ; } add_timer(&exp->timeout); hlist_add_head_rcu(&exp->lnode, &master_help->expectations); master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); cnet = nf_ct_pernet(net); cnet->expect_count++; NF_CT_STAT_INC(net, expect_create); } /* Race with expectations being used means we could have none to find; OK. */ static void evict_oldest_expect(struct nf_conn *master, struct nf_conntrack_expect *new) { struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_expect *exp, *last = NULL; hlist_for_each_entry(exp, &master_help->expectations, lnode) { if (exp->class == new->class) last = exp; } if (last) nf_ct_remove_expect(last); } static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, unsigned int flags) { const struct nf_conntrack_expect_policy *p; struct nf_conntrack_expect *i; struct nf_conntrack_net *cnet; struct nf_conn *master = expect->master; struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(expect); struct hlist_node *next; unsigned int h; int ret = 0; if (!master_help) { ret = -ESHUTDOWN; goto out; } h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (master_matches(i, expect, flags) && expect_matches(i, expect)) { if (i->class != expect->class || i->master != expect->master) return -EALREADY; if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { ret = -EBUSY; goto out; } } /* Will be over limit? */ helper = rcu_dereference_protected(master_help->helper, lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { p = &helper->expect_policy[expect->class]; if (p->max_expected && master_help->expecting[expect->class] >= p->max_expected) { evict_oldest_expect(master, expect); if (master_help->expecting[expect->class] >= p->max_expected) { ret = -EMFILE; goto out; } } } cnet = nf_ct_pernet(net); if (cnet->expect_count >= nf_ct_expect_max) { net_warn_ratelimited("nf_conntrack: expectation table full\n"); ret = -EMFILE; } out: return ret; } int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, u32 portid, int report, unsigned int flags) { int ret; spin_lock_bh(&nf_conntrack_expect_lock); ret = __nf_ct_expect_check(expect, flags); if (ret < 0) goto out; nf_ct_expect_insert(expect); spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); return 0; out: spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data) { struct nf_conntrack_expect *exp; const struct hlist_node *next; unsigned int i; spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &nf_ct_expect_hash[i], hnode) { if (iter(exp, data) && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } } } spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_expect_iterate_destroy); void nf_ct_expect_iterate_net(struct net *net, bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data, u32 portid, int report) { struct nf_conntrack_expect *exp; const struct hlist_node *next; unsigned int i; spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &nf_ct_expect_hash[i], hnode) { if (!net_eq(nf_ct_exp_net(exp), net)) continue; if (iter(exp, data) && del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, portid, report); nf_ct_expect_put(exp); } } } spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_expect_iterate_net); #ifdef CONFIG_NF_CONNTRACK_PROCFS struct ct_expect_iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *ct_expect_get_first(struct seq_file *seq) { struct ct_expect_iter_state *st = seq->private; struct hlist_node *n; for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { n = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket])); if (n) return n; } return NULL; } static struct hlist_node *ct_expect_get_next(struct seq_file *seq, struct hlist_node *head) { struct ct_expect_iter_state *st = seq->private; head = rcu_dereference(hlist_next_rcu(head)); while (head == NULL) { if (++st->bucket >= nf_ct_expect_hsize) return NULL; head = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket])); } return head; } static struct hlist_node *ct_expect_get_idx(struct seq_file *seq, loff_t pos) { struct hlist_node *head = ct_expect_get_first(seq); if (head) while (pos && (head = ct_expect_get_next(seq, head))) pos--; return pos ? NULL : head; } static void *exp_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return ct_expect_get_idx(seq, *pos); } static void *exp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return ct_expect_get_next(seq, v); } static void exp_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int exp_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_expect *expect; struct nf_conntrack_helper *helper; struct hlist_node *n = v; char *delim = ""; expect = hlist_entry(n, struct nf_conntrack_expect, hnode); if (expect->timeout.function) seq_printf(s, "%ld ", timer_pending(&expect->timeout) ? (long)(expect->timeout.expires - jiffies)/HZ : 0); else seq_puts(s, "- "); seq_printf(s, "l3proto = %u proto=%u ", expect->tuple.src.l3num, expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, nf_ct_l4proto_find(expect->tuple.dst.protonum)); if (expect->flags & NF_CT_EXPECT_PERMANENT) { seq_puts(s, "PERMANENT"); delim = ","; } if (expect->flags & NF_CT_EXPECT_INACTIVE) { seq_printf(s, "%sINACTIVE", delim); delim = ","; } if (expect->flags & NF_CT_EXPECT_USERSPACE) seq_printf(s, "%sUSERSPACE", delim); helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } seq_putc(s, '\n'); return 0; } static const struct seq_operations exp_seq_ops = { .start = exp_seq_start, .next = exp_seq_next, .stop = exp_seq_stop, .show = exp_seq_show }; #endif /* CONFIG_NF_CONNTRACK_PROCFS */ static int exp_proc_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_PROCFS struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; proc = proc_create_net("nf_conntrack_expect", 0440, net->proc_net, &exp_seq_ops, sizeof(struct ct_expect_iter_state)); if (!proc) return -ENOMEM; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif /* CONFIG_NF_CONNTRACK_PROCFS */ return 0; } static void exp_proc_remove(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_PROCFS remove_proc_entry("nf_conntrack_expect", net->proc_net); #endif /* CONFIG_NF_CONNTRACK_PROCFS */ } module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); int nf_conntrack_expect_pernet_init(struct net *net) { return exp_proc_init(net); } void nf_conntrack_expect_pernet_fini(struct net *net) { exp_proc_remove(net); } int nf_conntrack_expect_init(void) { if (!nf_ct_expect_hsize) { nf_ct_expect_hsize = nf_conntrack_htable_size / 256; if (!nf_ct_expect_hsize) nf_ct_expect_hsize = 1; } nf_ct_expect_max = nf_ct_expect_hsize * 4; nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", sizeof(struct nf_conntrack_expect), 0, 0, NULL); if (!nf_ct_expect_cachep) return -ENOMEM; nf_ct_expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (!nf_ct_expect_hash) { kmem_cache_destroy(nf_ct_expect_cachep); return -ENOMEM; } return 0; } void nf_conntrack_expect_fini(void) { rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); kvfree(nf_ct_expect_hash); } |
| 473 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM bpf_trace #if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BPF_TRACE_H #include <linux/tracepoint.h> TRACE_EVENT(bpf_trace_printk, TP_PROTO(const char *bpf_string), TP_ARGS(bpf_string), TP_STRUCT__entry( __string(bpf_string, bpf_string) ), TP_fast_assign( __assign_str(bpf_string, bpf_string); ), TP_printk("%s", __get_str(bpf_string)) ); #endif /* _TRACE_BPF_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE bpf_trace #include <trace/define_trace.h> |
| 1 149 1 1 16 17 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __BEN_VLAN_802_1Q_INC__ #define __BEN_VLAN_802_1Q_INC__ #include <linux/if_vlan.h> #include <linux/u64_stats_sync.h> #include <linux/list.h> /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. */ #define VLAN_GROUP_ARRAY_SPLIT_PARTS 8 #define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS) enum vlan_protos { VLAN_PROTO_8021Q = 0, VLAN_PROTO_8021AD, VLAN_PROTO_NUM, }; struct vlan_group { unsigned int nr_vlan_devs; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM] [VLAN_GROUP_ARRAY_SPLIT_PARTS]; }; struct vlan_info { struct net_device *real_dev; /* The ethernet(like) device * the vlan is attached to. */ struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; struct rcu_head rcu; }; static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); return -EINVAL; } } static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg, unsigned int pidx, u16 vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; /* paired with smp_wmb() in vlan_group_prealloc_vid() */ smp_rmb(); return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; } static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { int pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return NULL; return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; if (!vg || pidx < 0) return; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } /* Must be invoked with rcu_read_lock or with RTNL. */ static inline struct net_device *vlan_find_dev(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); if (vlan_info) return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); return NULL; } static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) { netdev_features_t ret; ret = real_dev->hw_enc_features & (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; return 0; } #define vlan_group_for_each_dev(grp, i, dev) \ for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \ if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \ (i) % VLAN_N_VID))) int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto); /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_priv *vip = vlan_dev_priv(dev); return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP int vlan_gvrp_request_join(const struct net_device *dev); void vlan_gvrp_request_leave(const struct net_device *dev); int vlan_gvrp_init_applicant(struct net_device *dev); void vlan_gvrp_uninit_applicant(struct net_device *dev); int vlan_gvrp_init(void); void vlan_gvrp_uninit(void); #else static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif #ifdef CONFIG_VLAN_8021Q_MVRP int vlan_mvrp_request_join(const struct net_device *dev); void vlan_mvrp_request_leave(const struct net_device *dev); int vlan_mvrp_init_applicant(struct net_device *dev); void vlan_mvrp_uninit_applicant(struct net_device *dev); int vlan_mvrp_init(void); void vlan_mvrp_uninit(void); #else static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_mvrp_init(void) { return 0; } static inline void vlan_mvrp_uninit(void) {} #endif extern const char vlan_fullname[]; extern const char vlan_version[]; int vlan_netlink_init(void); void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; extern unsigned int vlan_net_id; struct proc_dir_entry; struct vlan_net { /* /proc/net/vlan */ struct proc_dir_entry *proc_vlan_dir; /* /proc/net/vlan/config */ struct proc_dir_entry *proc_vlan_conf; /* Determines interface naming scheme. */ unsigned short name_type; }; #endif /* !(__BEN_VLAN_802_1Q_INC__) */ |
| 3134 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H #include <asm/fpu/xstate.h> #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 #define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u32 read_pkru(void) { if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru != rdpkru()) wrpkru(pkru); } static inline void pkru_write_default(void) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; wrpkru(pkru_get_init_value()); } #endif |
| 362 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Network event notifiers * * Authors: * Tom Tucker <tom@opengridcomputing.com> * Steve Wise <swise@opengridcomputing.com> * * Fixes: */ #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/export.h> #include <net/netevent.h> static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); /** * register_netevent_notifier - register a netevent notifier block * @nb: notifier * * Register a notifier to be called when a netevent occurs. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. */ int register_netevent_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&netevent_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_netevent_notifier); /** * unregister_netevent_notifier - unregister a netevent notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_neigh_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. */ int unregister_netevent_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&netevent_notif_chain, nb); } EXPORT_SYMBOL_GPL(unregister_netevent_notifier); /** * call_netevent_notifiers - call all netevent notifier blocks * @val: value passed unmodified to notifier function * @v: pointer passed unmodified to notifier function * * Call all neighbour notifier blocks. Parameters and return value * are as for notifier_call_chain(). */ int call_netevent_notifiers(unsigned long val, void *v) { return atomic_notifier_call_chain(&netevent_notif_chain, val, v); } EXPORT_SYMBOL_GPL(call_netevent_notifiers); |
| 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 | /* 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. * * Authors: Lotsa people, from code originally in tcp */ #ifndef _INET6_HASHTABLES_H #define _INET6_HASHTABLES_H #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/types.h> #include <linux/jhash.h> #include <net/inet_sock.h> #include <net/ipv6.h> #include <net/netns/hash.h> struct inet_hashinfo; static inline unsigned int __inet6_ehashfn(const u32 lhash, const u16 lport, const u32 fhash, const __be16 fport, const u32 initval) { const u32 ports = (((u32)lport) << 16) | (__force u32)fport; return jhash_3words(lhash, fhash, ports, initval); } /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif); typedef u32 (inet6_ehashfn_t)(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport); inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif); static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif, bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif, sdif); } static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif, int sdif, bool *refcounted) { struct sock *sk = skb_steal_sock(skb, refcounted); if (sk) return sk; return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, doff, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), iif, sdif, refcounted); } struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); int inet6_hash(struct sock *sk); static inline bool inet6_match(struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, const int dif, const int sdif) { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || sk->sk_portpair != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; /* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */ return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif); } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ |
| 46 4 7 7 7 7 4 987 988 231 231 229 229 4 4 4 4 4 4 2 10 2 8 4 4 2 2 2 2 2 13 9 4 7 3 3 3 1 2 1 1 2 1 1 2 4 1 3 15 5 3 2 1 4 6 6 4 4 4 1 46 46 46 46 46 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the NetFilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * Changes: */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/capability.h> #include <linux/fs.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/workqueue.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/mutex.h> #include <net/net_namespace.h> #include <linux/nsproxy.h> #include <net/ip.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> #include <net/genetlink.h> #include <linux/uaccess.h> #include <net/ip_vs.h> /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ static DEFINE_MUTEX(__ip_vs_mutex); /* sysctl variables */ #ifdef CONFIG_IP_VS_DEBUG static int sysctl_ip_vs_debug_level = 0; int ip_vs_get_debug_level(void) { return sysctl_ip_vs_debug_level; } #endif /* Protos */ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup); #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static bool __ip_vs_addr_is_local_v6(struct net *net, const struct in6_addr *addr) { struct flowi6 fl6 = { .daddr = *addr, }; struct dst_entry *dst = ip6_route_output(net, NULL, &fl6); bool is_local; is_local = !dst->error && dst->dev && (dst->dev->flags & IFF_LOOPBACK); dst_release(dst); return is_local; } #endif #ifdef CONFIG_SYSCTL /* * update_defense_level is called from keventd and from sysctl, * so it needs to protect itself from softirqs */ static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; int availmem; int nomem; int to_change = -1; /* we only count free and buffered memory (in pages) */ si_meminfo(&i); availmem = i.freeram + i.bufferram; /* however in linux 2.5 the i.bufferram is total page cache size, we need adjust it */ /* si_swapinfo(&i); */ /* availmem = availmem - (i.totalswap - i.freeswap); */ nomem = (availmem < ipvs->sysctl_amemthresh); local_bh_disable(); /* drop_entry */ spin_lock(&ipvs->dropentry_lock); switch (ipvs->sysctl_drop_entry) { case 0: atomic_set(&ipvs->dropentry, 0); break; case 1: if (nomem) { atomic_set(&ipvs->dropentry, 1); ipvs->sysctl_drop_entry = 2; } else { atomic_set(&ipvs->dropentry, 0); } break; case 2: if (nomem) { atomic_set(&ipvs->dropentry, 1); } else { atomic_set(&ipvs->dropentry, 0); ipvs->sysctl_drop_entry = 1; } break; case 3: atomic_set(&ipvs->dropentry, 1); break; } spin_unlock(&ipvs->dropentry_lock); /* drop_packet */ spin_lock(&ipvs->droppacket_lock); switch (ipvs->sysctl_drop_packet) { case 0: ipvs->drop_rate = 0; break; case 1: if (nomem) { ipvs->drop_rate = ipvs->drop_counter = ipvs->sysctl_amemthresh / (ipvs->sysctl_amemthresh-availmem); ipvs->sysctl_drop_packet = 2; } else { ipvs->drop_rate = 0; } break; case 2: if (nomem) { ipvs->drop_rate = ipvs->drop_counter = ipvs->sysctl_amemthresh / (ipvs->sysctl_amemthresh-availmem); } else { ipvs->drop_rate = 0; ipvs->sysctl_drop_packet = 1; } break; case 3: ipvs->drop_rate = ipvs->sysctl_am_droprate; break; } spin_unlock(&ipvs->droppacket_lock); /* secure_tcp */ spin_lock(&ipvs->securetcp_lock); switch (ipvs->sysctl_secure_tcp) { case 0: if (ipvs->old_secure_tcp >= 2) to_change = 0; break; case 1: if (nomem) { if (ipvs->old_secure_tcp < 2) to_change = 1; ipvs->sysctl_secure_tcp = 2; } else { if (ipvs->old_secure_tcp >= 2) to_change = 0; } break; case 2: if (nomem) { if (ipvs->old_secure_tcp < 2) to_change = 1; } else { if (ipvs->old_secure_tcp >= 2) to_change = 0; ipvs->sysctl_secure_tcp = 1; } break; case 3: if (ipvs->old_secure_tcp < 2) to_change = 1; break; } ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) ip_vs_protocol_timeout_change(ipvs, ipvs->sysctl_secure_tcp > 1); spin_unlock(&ipvs->securetcp_lock); local_bh_enable(); } /* Handler for delayed work for expiring no * destination connections */ static void expire_nodest_conn_handler(struct work_struct *work) { struct netns_ipvs *ipvs; ipvs = container_of(work, struct netns_ipvs, expire_nodest_conn_work.work); ip_vs_expire_nodest_conn_flush(ipvs); } /* * Timer for checking the defense */ #define DEFENSE_TIMER_PERIOD 1*HZ static void defense_work_handler(struct work_struct *work) { struct netns_ipvs *ipvs = container_of(work, struct netns_ipvs, defense_work.work); update_defense_level(ipvs); if (atomic_read(&ipvs->dropentry)) ip_vs_random_dropentry(ipvs); queue_delayed_work(system_long_wq, &ipvs->defense_work, DEFENSE_TIMER_PERIOD); } #endif int ip_vs_use_count_inc(void) { return try_module_get(THIS_MODULE); } void ip_vs_use_count_dec(void) { module_put(THIS_MODULE); } /* * Hash table: for virtual service lookups */ #define IP_VS_SVC_TAB_BITS 8 #define IP_VS_SVC_TAB_SIZE (1 << IP_VS_SVC_TAB_BITS) #define IP_VS_SVC_TAB_MASK (IP_VS_SVC_TAB_SIZE - 1) /* the service table hashed by <protocol, addr, port> */ static struct hlist_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE]; /* the service table hashed by fwmark */ static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE]; /* * Returns hash value for virtual service */ static inline unsigned int ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; __u32 ahash; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif ahash = ntohl(addr_fold); ahash ^= ((size_t) ipvs >> 8); return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) & IP_VS_SVC_TAB_MASK; } /* * Returns hash value of fwmark for virtual service lookup */ static inline unsigned int ip_vs_svc_fwm_hashkey(struct netns_ipvs *ipvs, __u32 fwmark) { return (((size_t)ipvs>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; } /* * Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port> * or in the ip_vs_svc_fwm_table by fwmark. * Should be called with locked tables. */ static int ip_vs_svc_hash(struct ip_vs_service *svc) { unsigned int hash; if (svc->flags & IP_VS_SVC_F_HASHED) { pr_err("%s(): request for already hashed, called from %pS\n", __func__, __builtin_return_address(0)); return 0; } if (svc->fwmark == 0) { /* * Hash it by <netns,protocol,addr,port> in ip_vs_svc_table */ hash = ip_vs_svc_hashkey(svc->ipvs, svc->af, svc->protocol, &svc->addr, svc->port); hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* * Hash it by fwmark in svc_fwm_table */ hash = ip_vs_svc_fwm_hashkey(svc->ipvs, svc->fwmark); hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]); } svc->flags |= IP_VS_SVC_F_HASHED; /* increase its refcnt because it is referenced by the svc table */ atomic_inc(&svc->refcnt); return 1; } /* * Unhashes a service from svc_table / svc_fwm_table. * Should be called with locked tables. */ static int ip_vs_svc_unhash(struct ip_vs_service *svc) { if (!(svc->flags & IP_VS_SVC_F_HASHED)) { pr_err("%s(): request for unhash flagged, called from %pS\n", __func__, __builtin_return_address(0)); return 0; } if (svc->fwmark == 0) { /* Remove it from the svc_table table */ hlist_del_rcu(&svc->s_list); } else { /* Remove it from the svc_fwm_table table */ hlist_del_rcu(&svc->f_list); } svc->flags &= ~IP_VS_SVC_F_HASHED; atomic_dec(&svc->refcnt); return 1; } /* * Get service by {netns, proto,addr,port} in the service table. */ static inline struct ip_vs_service * __ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { unsigned int hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ hash = ip_vs_svc_hashkey(ipvs, af, protocol, vaddr, vport); hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) { if ((svc->af == af) && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) && (svc->protocol == protocol) && (svc->ipvs == ipvs)) { /* HIT */ return svc; } } return NULL; } /* * Get service by {fwmark} in the service table. */ static inline struct ip_vs_service * __ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark) { unsigned int hash; struct ip_vs_service *svc; /* Check for fwmark addressed entries */ hash = ip_vs_svc_fwm_hashkey(ipvs, fwmark); hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) { if (svc->fwmark == fwmark && svc->af == af && (svc->ipvs == ipvs)) { /* HIT */ return svc; } } return NULL; } /* Find service, called under RCU lock */ struct ip_vs_service * ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; /* * Check the table hashed by fwmark first */ if (fwmark) { svc = __ip_vs_svc_fwm_find(ipvs, af, fwmark); if (svc) goto out; } /* * Check the table hashed by <protocol,addr,port> * for "full" addressed entries */ svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport); if (!svc && protocol == IPPROTO_TCP && atomic_read(&ipvs->ftpsvc_counter) && (vport == FTPDATA || !inet_port_requires_bind_service(ipvs->net, ntohs(vport)))) { /* * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, FTPPORT); } if (svc == NULL && atomic_read(&ipvs->nullsvc_counter)) { /* * Check if the catch-all port (port zero) exists */ svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, 0); } out: IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n", fwmark, ip_vs_proto_name(protocol), IP_VS_DBG_ADDR(af, vaddr), ntohs(vport), svc ? "hit" : "not hit"); return svc; } static inline void __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) { atomic_inc(&svc->refcnt); rcu_assign_pointer(dest->svc, svc); } static void ip_vs_service_free(struct ip_vs_service *svc) { free_percpu(svc->stats.cpustats); kfree(svc); } static void ip_vs_service_rcu_free(struct rcu_head *head) { struct ip_vs_service *svc; svc = container_of(head, struct ip_vs_service, rcu_head); ip_vs_service_free(svc); } static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) { if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); if (do_delay) call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); else ip_vs_service_free(svc); } } /* * Returns hash value for real service */ static inline unsigned int ip_vs_rs_hashkey(int af, const union nf_inet_addr *addr, __be16 port) { unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif return (ntohl(addr_fold)^(porth>>IP_VS_RTAB_BITS)^porth) & IP_VS_RTAB_MASK; } /* Hash ip_vs_dest in rs_table by <proto,addr,port>. */ static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned int hash; __be16 port; if (dest->in_rs_table) return; switch (IP_VS_DFWD_METHOD(dest)) { case IP_VS_CONN_F_MASQ: port = dest->port; break; case IP_VS_CONN_F_TUNNEL: switch (dest->tun_type) { case IP_VS_CONN_F_TUNNEL_TYPE_GUE: port = dest->tun_port; break; case IP_VS_CONN_F_TUNNEL_TYPE_IPIP: case IP_VS_CONN_F_TUNNEL_TYPE_GRE: port = 0; break; default: return; } break; default: return; } /* * Hash by proto,addr,port, * which are the parameters of the real service. */ hash = ip_vs_rs_hashkey(dest->af, &dest->addr, port); hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]); dest->in_rs_table = 1; } /* Unhash ip_vs_dest from rs_table. */ static void ip_vs_rs_unhash(struct ip_vs_dest *dest) { /* * Remove it from the rs_table table. */ if (dest->in_rs_table) { hlist_del_rcu(&dest->d_list); dest->in_rs_table = 0; } } /* Check if real service by <proto,addr,port> is present */ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { unsigned int hash; struct ip_vs_dest *dest; /* Check for "full" addressed entries */ hash = ip_vs_rs_hashkey(af, daddr, dport); hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && (dest->protocol == protocol || dest->vfwmark) && IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return true; } } return false; } /* Find real service record by <proto,addr,port>. * In case of multiple records with the same <proto,addr,port>, only * the first found record is returned. * * To be called under RCU lock. */ struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { unsigned int hash; struct ip_vs_dest *dest; /* Check for "full" addressed entries */ hash = ip_vs_rs_hashkey(af, daddr, dport); hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && (dest->protocol == protocol || dest->vfwmark) && IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return dest; } } return NULL; } /* Find real service record by <af,addr,tun_port>. * In case of multiple records with the same <af,addr,tun_port>, only * the first found record is returned. * * To be called under RCU lock. */ struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, const union nf_inet_addr *daddr, __be16 tun_port) { struct ip_vs_dest *dest; unsigned int hash; /* Check for "full" addressed entries */ hash = ip_vs_rs_hashkey(af, daddr, tun_port); hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { if (dest->tun_port == tun_port && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_TUNNEL) { /* HIT */ return dest; } } return NULL; } /* Lookup destination by {addr,port} in the given service * Called under RCU lock. */ static struct ip_vs_dest * ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest; /* * Find the destination for the given service */ list_for_each_entry_rcu(dest, &svc->destinations, n_list) { if ((dest->af == dest_af) && ip_vs_addr_equal(dest_af, &dest->addr, daddr) && (dest->port == dport)) { /* HIT */ return dest; } } return NULL; } /* * Find destination by {daddr,dport,vaddr,protocol} * Created to be used in ip_vs_process_message() in * the backup synchronization daemon. It finds the * destination to be bound to the received connection * on the backup. * Called under RCU lock, no refcnt is returned. */ struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags) { struct ip_vs_dest *dest; struct ip_vs_service *svc; __be16 port = dport; svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) port = 0; dest = ip_vs_lookup_dest(svc, dest_af, daddr, port); if (!dest) dest = ip_vs_lookup_dest(svc, dest_af, daddr, port ^ dport); return dest; } void ip_vs_dest_dst_rcu_free(struct rcu_head *head) { struct ip_vs_dest_dst *dest_dst = container_of(head, struct ip_vs_dest_dst, rcu_head); dst_release(dest_dst->dst_cache); kfree(dest_dst); } /* Release dest_dst and dst_cache for dest in user context */ static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest) { struct ip_vs_dest_dst *old; old = rcu_dereference_protected(dest->dest_dst, 1); if (old) { RCU_INIT_POINTER(dest->dest_dst, NULL); call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free); } } /* * Lookup dest by {svc,addr,port} in the destination trash. * The destination trash is used to hold the destinations that are removed * from the service table but are still referenced by some conn entries. * The reason to add the destination trash is when the dest is temporary * down (either by administrator or by monitor program), the dest can be * picked back from the trash, the remaining connections to the dest can * continue, and the counting information of the dest is also useful for * scheduling. */ static struct ip_vs_dest * ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest; struct netns_ipvs *ipvs = svc->ipvs; /* * Find the destination in trash */ spin_lock_bh(&ipvs->dest_trash_lock); list_for_each_entry(dest, &ipvs->dest_trash, t_list) { IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, " "dest->refcnt=%d\n", dest->vfwmark, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), refcount_read(&dest->refcnt)); if (dest->af == dest_af && ip_vs_addr_equal(dest_af, &dest->addr, daddr) && dest->port == dport && dest->vfwmark == svc->fwmark && dest->protocol == svc->protocol && (svc->fwmark || (ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) && dest->vport == svc->port))) { /* HIT */ list_del(&dest->t_list); goto out; } } dest = NULL; out: spin_unlock_bh(&ipvs->dest_trash_lock); return dest; } static void ip_vs_dest_free(struct ip_vs_dest *dest) { struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); __ip_vs_dst_cache_reset(dest); __ip_vs_svc_put(svc, false); free_percpu(dest->stats.cpustats); ip_vs_dest_put_and_free(dest); } /* * Clean up all the destinations in the trash * Called by the ip_vs_control_cleanup() * * When the ip_vs_control_clearup is activated by ipvs module exit, * the service tables must have been flushed and all the connections * are expired, and the refcnt of each destination in the trash must * be 1, so we simply release them here. */ static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs) { struct ip_vs_dest *dest, *nxt; del_timer_sync(&ipvs->dest_trash_timer); /* No need to use dest_trash_lock */ list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, t_list) { list_del(&dest->t_list); ip_vs_dest_free(dest); } } static void ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src) { #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c spin_lock_bh(&src->lock); IP_VS_SHOW_STATS_COUNTER(conns); IP_VS_SHOW_STATS_COUNTER(inpkts); IP_VS_SHOW_STATS_COUNTER(outpkts); IP_VS_SHOW_STATS_COUNTER(inbytes); IP_VS_SHOW_STATS_COUNTER(outbytes); ip_vs_read_estimator(dst, src); spin_unlock_bh(&src->lock); } static void ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src) { dst->conns = (u32)src->conns; dst->inpkts = (u32)src->inpkts; dst->outpkts = (u32)src->outpkts; dst->inbytes = src->inbytes; dst->outbytes = src->outbytes; dst->cps = (u32)src->cps; dst->inpps = (u32)src->inpps; dst->outpps = (u32)src->outpps; dst->inbps = (u32)src->inbps; dst->outbps = (u32)src->outbps; } static void ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); /* get current counters as zero point, rates are zeroed */ #define IP_VS_ZERO_STATS_COUNTER(c) stats->kstats0.c = stats->kstats.c IP_VS_ZERO_STATS_COUNTER(conns); IP_VS_ZERO_STATS_COUNTER(inpkts); IP_VS_ZERO_STATS_COUNTER(outpkts); IP_VS_ZERO_STATS_COUNTER(inbytes); IP_VS_ZERO_STATS_COUNTER(outbytes); ip_vs_zero_estimator(stats); spin_unlock_bh(&stats->lock); } /* * Update a destination in the given service */ static void __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; /* We cannot modify an address and change the address family */ BUG_ON(!add && udest->af != dest->af); if (add && udest->af != svc->af) ipvs->mixed_address_family_dests++; /* keep the last_weight with latest non-0 weight */ if (add || udest->weight != 0) atomic_set(&dest->last_weight, udest->weight); /* set the weight and the flags */ atomic_set(&dest->weight, udest->weight); conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; conn_flags |= IP_VS_CONN_F_INACTIVE; /* Need to rehash? */ if ((udest->conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_DFWD_METHOD(dest) || udest->tun_type != dest->tun_type || udest->tun_port != dest->tun_port) ip_vs_rs_unhash(dest); /* set the tunnel info */ dest->tun_type = udest->tun_type; dest->tun_port = udest->tun_port; dest->tun_flags = udest->tun_flags; /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { /* FTP-NAT requires conntrack for mangling */ if (svc->port == FTPPORT) ip_vs_register_conntrack(svc); } atomic_set(&dest->conn_flags, conn_flags); /* Put the real service in rs_table if not present. */ ip_vs_rs_hash(ipvs, dest); /* bind the service */ old_svc = rcu_dereference_protected(dest->svc, 1); if (!old_svc) { __ip_vs_bind_svc(dest, svc); } else { if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); __ip_vs_svc_put(old_svc, true); } } /* set the dest status flags */ dest->flags |= IP_VS_DEST_F_AVAILABLE; if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold) dest->flags &= ~IP_VS_DEST_F_OVERLOAD; dest->u_threshold = udest->u_threshold; dest->l_threshold = udest->l_threshold; dest->af = udest->af; spin_lock_bh(&dest->dst_lock); __ip_vs_dst_cache_reset(dest); spin_unlock_bh(&dest->dst_lock); if (add) { ip_vs_start_estimator(svc->ipvs, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; sched = rcu_dereference_protected(svc->scheduler, 1); if (sched && sched->add_dest) sched->add_dest(svc, dest); } else { sched = rcu_dereference_protected(svc->scheduler, 1); if (sched && sched->upd_dest) sched->upd_dest(svc, dest); } } /* * Create a destination for the given service */ static int ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, struct ip_vs_dest **dest_p) { struct ip_vs_dest *dest; unsigned int atype, i; EnterFunction(2); #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { int ret; atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; ret = nf_defrag_ipv6_enable(svc->ipvs->net); if (ret) return ret; } else #endif { atype = inet_addr_type(svc->ipvs->net, udest->addr.ip); if (atype != RTN_LOCAL && atype != RTN_UNICAST) return -EINVAL; } dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL); if (dest == NULL) return -ENOMEM; dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); if (!dest->stats.cpustats) goto err_alloc; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *ip_vs_dest_stats; ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i); u64_stats_init(&ip_vs_dest_stats->syncp); } dest->af = udest->af; dest->protocol = svc->protocol; dest->vaddr = svc->addr; dest->vport = svc->port; dest->vfwmark = svc->fwmark; ip_vs_addr_copy(udest->af, &dest->addr, &udest->addr); dest->port = udest->port; atomic_set(&dest->activeconns, 0); atomic_set(&dest->inactconns, 0); atomic_set(&dest->persistconns, 0); refcount_set(&dest->refcnt, 1); INIT_HLIST_NODE(&dest->d_list); spin_lock_init(&dest->dst_lock); spin_lock_init(&dest->stats.lock); __ip_vs_update_dest(svc, dest, udest, 1); *dest_p = dest; LeaveFunction(2); return 0; err_alloc: kfree(dest); return -ENOMEM; } /* * Add a destination into an existing service */ static int ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; union nf_inet_addr daddr; __be16 dport = udest->port; int ret; EnterFunction(2); if (udest->weight < 0) { pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; } if (udest->l_threshold > udest->u_threshold) { pr_err("%s(): lower threshold is higher than upper threshold\n", __func__); return -ERANGE; } if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); return -EINVAL; } } ip_vs_addr_copy(udest->af, &daddr, &udest->addr); /* We use function that requires RCU lock */ rcu_read_lock(); dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport); rcu_read_unlock(); if (dest != NULL) { IP_VS_DBG(1, "%s(): dest already exists\n", __func__); return -EEXIST; } /* * Check if the dest already exists in the trash and * is from the same service */ dest = ip_vs_trash_get_dest(svc, udest->af, &daddr, dport); if (dest != NULL) { IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, " "dest->refcnt=%d, service %u/%s:%u\n", IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport), refcount_read(&dest->refcnt), dest->vfwmark, IP_VS_DBG_ADDR(svc->af, &dest->vaddr), ntohs(dest->vport)); __ip_vs_update_dest(svc, dest, udest, 1); ret = 0; } else { /* * Allocate and initialize the dest structure */ ret = ip_vs_new_dest(svc, udest, &dest); } LeaveFunction(2); return ret; } /* * Edit a destination in the given service */ static int ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; union nf_inet_addr daddr; __be16 dport = udest->port; EnterFunction(2); if (udest->weight < 0) { pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; } if (udest->l_threshold > udest->u_threshold) { pr_err("%s(): lower threshold is higher than upper threshold\n", __func__); return -ERANGE; } if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); return -EINVAL; } } ip_vs_addr_copy(udest->af, &daddr, &udest->addr); /* We use function that requires RCU lock */ rcu_read_lock(); dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport); rcu_read_unlock(); if (dest == NULL) { IP_VS_DBG(1, "%s(): dest doesn't exist\n", __func__); return -ENOENT; } __ip_vs_update_dest(svc, dest, udest, 0); LeaveFunction(2); return 0; } /* * Delete a destination (must be already unlinked from the service) */ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, bool cleanup) { ip_vs_stop_estimator(ipvs, &dest->stats); /* * Remove it from the d-linked list with the real services. */ ip_vs_rs_unhash(dest); spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), refcount_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); /* dest lives in trash with reference */ list_add(&dest->t_list, &ipvs->dest_trash); dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); /* Queue up delayed work to expire all no destination connections. * No-op when CONFIG_SYSCTL is disabled. */ if (!cleanup) ip_vs_enqueue_expire_nodest_conns(ipvs); } /* * Unlink a destination from the given service */ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, int svcupd) { dest->flags &= ~IP_VS_DEST_F_AVAILABLE; /* * Remove it from the d-linked destination list. */ list_del_rcu(&dest->n_list); svc->num_dests--; if (dest->af != svc->af) svc->ipvs->mixed_address_family_dests--; if (svcupd) { struct ip_vs_scheduler *sched; sched = rcu_dereference_protected(svc->scheduler, 1); if (sched && sched->del_dest) sched->del_dest(svc, dest); } } /* * Delete a destination server in the given service */ static int ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; __be16 dport = udest->port; EnterFunction(2); /* We use function that requires RCU lock */ rcu_read_lock(); dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport); rcu_read_unlock(); if (dest == NULL) { IP_VS_DBG(1, "%s(): destination not found!\n", __func__); return -ENOENT; } /* * Unlink dest from the service */ __ip_vs_unlink_dest(svc, dest, 1); /* * Delete the destination */ __ip_vs_del_dest(svc->ipvs, dest, false); LeaveFunction(2); return 0; } static void ip_vs_dest_trash_expire(struct timer_list *t) { struct netns_ipvs *ipvs = from_timer(ipvs, t, dest_trash_timer); struct ip_vs_dest *dest, *next; unsigned long now = jiffies; spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { if (refcount_read(&dest->refcnt) > 1) continue; if (dest->idle_start) { if (time_before(now, dest->idle_start + IP_VS_DEST_TRASH_PERIOD)) continue; } else { dest->idle_start = max(1UL, now); continue; } IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n", dest->vfwmark, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); list_del(&dest->t_list); ip_vs_dest_free(dest); } if (!list_empty(&ipvs->dest_trash)) mod_timer(&ipvs->dest_trash_timer, jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); spin_unlock(&ipvs->dest_trash_lock); } /* * Add a service into the service hash table */ static int ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service **svc_p) { int ret = 0, i; struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; int ret_hooks = -1; /* increase the module use count */ if (!ip_vs_use_count_inc()) return -ENOPROTOOPT; /* Lookup the scheduler by 'u->sched_name' */ if (strcmp(u->sched_name, "none")) { sched = ip_vs_scheduler_get(u->sched_name); if (!sched) { pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); ret = -ENOENT; goto out_err; } } if (u->pe_name && *u->pe_name) { pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); ret = -ENOENT; goto out_err; } } #ifdef CONFIG_IP_VS_IPV6 if (u->af == AF_INET6) { __u32 plen = (__force __u32) u->netmask; if (plen < 1 || plen > 128) { ret = -EINVAL; goto out_err; } ret = nf_defrag_ipv6_enable(ipvs->net); if (ret) goto out_err; } #endif if ((u->af == AF_INET && !ipvs->num_services) || (u->af == AF_INET6 && !ipvs->num_services6)) { ret = ip_vs_register_hooks(ipvs, u->af); if (ret < 0) goto out_err; ret_hooks = ret; } svc = kzalloc(sizeof(struct ip_vs_service), GFP_KERNEL); if (svc == NULL) { IP_VS_DBG(1, "%s(): no memory\n", __func__); ret = -ENOMEM; goto out_err; } svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); if (!svc->stats.cpustats) { ret = -ENOMEM; goto out_err; } for_each_possible_cpu(i) { struct ip_vs_cpu_stats *ip_vs_stats; ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i); u64_stats_init(&ip_vs_stats->syncp); } /* I'm the first user of the service */ atomic_set(&svc->refcnt, 0); svc->af = u->af; svc->protocol = u->protocol; ip_vs_addr_copy(svc->af, &svc->addr, &u->addr); svc->port = u->port; svc->fwmark = u->fwmark; svc->flags = u->flags & ~IP_VS_SVC_F_HASHED; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; svc->ipvs = ipvs; INIT_LIST_HEAD(&svc->destinations); spin_lock_init(&svc->sched_lock); spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ if (sched) { ret = ip_vs_bind_scheduler(svc, sched); if (ret) goto out_err; sched = NULL; } /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); pe = NULL; /* Update the virtual service counters */ if (svc->port == FTPPORT) atomic_inc(&ipvs->ftpsvc_counter); else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); if (svc->pe && svc->pe->conn_out) atomic_inc(&ipvs->conn_out_counter); ip_vs_start_estimator(ipvs, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services++; else if (svc->af == AF_INET6) ipvs->num_services6++; /* Hash the service into the service table */ ip_vs_svc_hash(svc); *svc_p = svc; /* Now there is a service - full throttle */ ipvs->enable = 1; return 0; out_err: if (ret_hooks >= 0) ip_vs_unregister_hooks(ipvs, u->af); if (svc != NULL) { ip_vs_unbind_scheduler(svc, sched); ip_vs_service_free(svc); } ip_vs_scheduler_put(sched); ip_vs_pe_put(pe); /* decrease the module use count */ ip_vs_use_count_dec(); return ret; } /* * Edit a service and bind it with a new scheduler */ static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { struct ip_vs_scheduler *sched = NULL, *old_sched; struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; bool new_pe_conn_out, old_pe_conn_out; /* * Lookup the scheduler, by 'u->sched_name' */ if (strcmp(u->sched_name, "none")) { sched = ip_vs_scheduler_get(u->sched_name); if (!sched) { pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); return -ENOENT; } } old_sched = sched; if (u->pe_name && *u->pe_name) { pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); ret = -ENOENT; goto out; } old_pe = pe; } #ifdef CONFIG_IP_VS_IPV6 if (u->af == AF_INET6) { __u32 plen = (__force __u32) u->netmask; if (plen < 1 || plen > 128) { ret = -EINVAL; goto out; } } #endif old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { if (old_sched) { ip_vs_unbind_scheduler(svc, old_sched); RCU_INIT_POINTER(svc->scheduler, NULL); /* Wait all svc->sched_data users */ synchronize_rcu(); } /* Bind the new scheduler */ if (sched) { ret = ip_vs_bind_scheduler(svc, sched); if (ret) { ip_vs_scheduler_put(sched); goto out; } } } /* * Set the flags and timeout value */ svc->flags = u->flags | IP_VS_SVC_F_HASHED; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; old_pe = rcu_dereference_protected(svc->pe, 1); if (pe != old_pe) { rcu_assign_pointer(svc->pe, pe); /* check for optional methods in new pe */ new_pe_conn_out = (pe && pe->conn_out) ? true : false; old_pe_conn_out = (old_pe && old_pe->conn_out) ? true : false; if (new_pe_conn_out && !old_pe_conn_out) atomic_inc(&svc->ipvs->conn_out_counter); if (old_pe_conn_out && !new_pe_conn_out) atomic_dec(&svc->ipvs->conn_out_counter); } out: ip_vs_scheduler_put(old_sched); ip_vs_pe_put(old_pe); return ret; } /* * Delete a service from the service list * - The service must be unlinked, unlocked and not referenced! * - We are called under _bh lock */ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) { struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; struct ip_vs_pe *old_pe; struct netns_ipvs *ipvs = svc->ipvs; if (svc->af == AF_INET) { ipvs->num_services--; if (!ipvs->num_services) ip_vs_unregister_hooks(ipvs, svc->af); } else if (svc->af == AF_INET6) { ipvs->num_services6--; if (!ipvs->num_services6) ip_vs_unregister_hooks(ipvs, svc->af); } ip_vs_stop_estimator(svc->ipvs, &svc->stats); /* Unbind scheduler */ old_sched = rcu_dereference_protected(svc->scheduler, 1); ip_vs_unbind_scheduler(svc, old_sched); ip_vs_scheduler_put(old_sched); /* Unbind persistence engine, keep svc->pe */ old_pe = rcu_dereference_protected(svc->pe, 1); if (old_pe && old_pe->conn_out) atomic_dec(&ipvs->conn_out_counter); ip_vs_pe_put(old_pe); /* * Unlink the whole destination list */ list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) { __ip_vs_unlink_dest(svc, dest, 0); __ip_vs_del_dest(svc->ipvs, dest, cleanup); } /* * Update the virtual service counters */ if (svc->port == FTPPORT) atomic_dec(&ipvs->ftpsvc_counter); else if (svc->port == 0) atomic_dec(&ipvs->nullsvc_counter); /* * Free the service if nobody refers to it */ __ip_vs_svc_put(svc, true); /* decrease the module use count */ ip_vs_use_count_dec(); } /* * Unlink a service from list and try to delete it if its refcnt reached 0 */ static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup) { ip_vs_unregister_conntrack(svc); /* Hold svc to avoid double release from dest_trash */ atomic_inc(&svc->refcnt); /* * Unhash it from the service table */ ip_vs_svc_unhash(svc); __ip_vs_del_service(svc, cleanup); } /* * Delete a service from the service list */ static int ip_vs_del_service(struct ip_vs_service *svc) { if (svc == NULL) return -EEXIST; ip_vs_unlink_service(svc, false); return 0; } /* * Flush all the virtual services */ static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) { int idx; struct ip_vs_service *svc; struct hlist_node *n; /* * Flush the service table hashed by <netns,protocol,addr,port> */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx], s_list) { if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } /* * Flush the service table hashed by fwmark */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx], f_list) { if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } return 0; } /* * Delete service by {netns} in the service table. * Called by __ip_vs_batch_cleanup() */ void ip_vs_service_nets_cleanup(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; EnterFunction(2); /* Check for "full" addressed entries */ mutex_lock(&__ip_vs_mutex); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_flush(ipvs, true); } mutex_unlock(&__ip_vs_mutex); LeaveFunction(2); } /* Put all references for device (dst_cache) */ static inline void ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) { struct ip_vs_dest_dst *dest_dst; spin_lock_bh(&dest->dst_lock); dest_dst = rcu_dereference_protected(dest->dest_dst, 1); if (dest_dst && dest_dst->dst_cache->dev == dev) { IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", dev->name, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), refcount_read(&dest->refcnt)); __ip_vs_dst_cache_reset(dest); } spin_unlock_bh(&dest->dst_lock); } /* Netdev event receiver * Currently only NETDEV_DOWN is handled to release refs to cached dsts */ static int ip_vs_dst_event(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); struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; struct ip_vs_dest *dest; unsigned int idx; if (event != NETDEV_DOWN || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); EnterFunction(2); mutex_lock(&__ip_vs_mutex); for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); } } } hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); } } } } spin_lock_bh(&ipvs->dest_trash_lock); list_for_each_entry(dest, &ipvs->dest_trash, t_list) { ip_vs_forget_dev(dest, dev); } spin_unlock_bh(&ipvs->dest_trash_lock); mutex_unlock(&__ip_vs_mutex); LeaveFunction(2); return NOTIFY_DONE; } /* * Zero counters in a service or all services */ static int ip_vs_zero_service(struct ip_vs_service *svc) { struct ip_vs_dest *dest; list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_zero_stats(&dest->stats); } ip_vs_zero_stats(&svc->stats); return 0; } static int ip_vs_zero_all(struct netns_ipvs *ipvs) { int idx; struct ip_vs_service *svc; for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } ip_vs_zero_stats(&ipvs->tot_stats); return 0; } #ifdef CONFIG_SYSCTL static int three = 3; static int proc_do_defense_mode(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val = *valp; int rc; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(int), .mode = table->mode, }; rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { if (val < 0 || val > 3) { rc = -EINVAL; } else { *valp = val; update_defense_level(ipvs); } } return rc; } static int proc_do_sync_threshold(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val[2]; int rc; struct ctl_table tmp = { .data = &val, .maxlen = table->maxlen, .mode = table->mode, }; mutex_lock(&ipvs->sync_mutex); memcpy(val, valp, sizeof(val)); rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write) { if (val[0] < 0 || val[1] < 0 || (val[0] >= val[1] && val[1])) rc = -EINVAL; else memcpy(valp, val, sizeof(val)); } mutex_unlock(&ipvs->sync_mutex); return rc; } static int proc_do_sync_ports(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val = *valp; int rc; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(int), .mode = table->mode, }; rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { if (val < 1 || !is_power_of_2(val)) rc = -EINVAL; else *valp = val; } return rc; } /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) * Do not change order or insert new entries without * align with netns init in ip_vs_control_net_init() */ static struct ctl_table vs_vars[] = { { .procname = "amemthresh", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "am_droprate", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "drop_entry", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "drop_packet", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, #ifdef CONFIG_IP_VS_NFCT { .procname = "conntrack", .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, }, #endif { .procname = "secure_tcp", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "snat_reroute", .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, }, { .procname = "sync_version", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "sync_ports", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_sync_ports, }, { .procname = "sync_persist_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sync_qlen_max", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "sync_sock_size", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cache_bypass", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "expire_nodest_conn", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sloppy_tcp", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sloppy_sctp", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "expire_quiescent_template", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sync_threshold", .maxlen = sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold), .mode = 0644, .proc_handler = proc_do_sync_threshold, }, { .procname = "sync_refresh_period", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "sync_retries", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &three, }, { .procname = "nat_icmp_send", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "pmtu_disc", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "backup_only", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "conn_reuse_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "schedule_icmp", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ignore_tunneled", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", .data = &sysctl_ip_vs_debug_level, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif { } }; #endif #ifdef CONFIG_PROC_FS struct ip_vs_iter { struct seq_net_private p; /* Do not move this, netns depends upon it*/ struct hlist_head *table; int bucket; }; /* * Write the contents of the VS rule table to a PROCfs file. * (It is kept just for backward compatibility) */ static inline const char *ip_vs_fwd_name(unsigned int flags) { switch (flags & IP_VS_CONN_F_FWD_MASK) { case IP_VS_CONN_F_LOCALNODE: return "Local"; case IP_VS_CONN_F_TUNNEL: return "Tunnel"; case IP_VS_CONN_F_DROUTE: return "Route"; default: return "Masq"; } } /* Get the Nth entry in the two lists */ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_iter *iter = seq->private; int idx; struct ip_vs_service *svc; /* look in hash by protocol */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) { if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_table; iter->bucket = idx; return svc; } } } /* keep looking in fwmark */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx], f_list) { if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_fwm_table; iter->bucket = idx; return svc; } } } return NULL; } static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ip_vs_info_array(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct hlist_node *e; struct ip_vs_iter *iter; struct ip_vs_service *svc; ++*pos; if (v == SEQ_START_TOKEN) return ip_vs_info_array(seq,0); svc = v; iter = seq->private; if (iter->table == ip_vs_svc_table) { /* next service in table hashed by protocol */ e = rcu_dereference(hlist_next_rcu(&svc->s_list)); if (e) return hlist_entry(e, struct ip_vs_service, s_list); while (++iter->bucket < IP_VS_SVC_TAB_SIZE) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[iter->bucket], s_list) { return svc; } } iter->table = ip_vs_svc_fwm_table; iter->bucket = -1; goto scan_fwmark; } /* next service in hashed by fwmark */ e = rcu_dereference(hlist_next_rcu(&svc->f_list)); if (e) return hlist_entry(e, struct ip_vs_service, f_list); scan_fwmark: while (++iter->bucket < IP_VS_SVC_TAB_SIZE) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[iter->bucket], f_list) return svc; } return NULL; } static void ip_vs_info_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ip_vs_info_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_printf(seq, "IP Virtual Server version %d.%d.%d (size=%d)\n", NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size); seq_puts(seq, "Prot LocalAddress:Port Scheduler Flags\n"); seq_puts(seq, " -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n"); } else { struct net *net = seq_file_net(seq); struct netns_ipvs *ipvs = net_ipvs(net); const struct ip_vs_service *svc = v; const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); char *sched_name = sched ? sched->name : "none"; if (svc->ipvs != ipvs) return 0; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) seq_printf(seq, "%s [%pI6]:%04X %s ", ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), sched_name); else #endif seq_printf(seq, "%s %08X:%04X %s %s ", ip_vs_proto_name(svc->protocol), ntohl(svc->addr.ip), ntohs(svc->port), sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } else { seq_printf(seq, "FWM %08X %s %s", svc->fwmark, sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } if (svc->flags & IP_VS_SVC_F_PERSISTENT) seq_printf(seq, "persistent %d %08X\n", svc->timeout, ntohl(svc->netmask)); else seq_putc(seq, '\n'); list_for_each_entry_rcu(dest, &svc->destinations, n_list) { #ifdef CONFIG_IP_VS_IPV6 if (dest->af == AF_INET6) seq_printf(seq, " -> [%pI6]:%04X" " %-7s %-6d %-10d %-10d\n", &dest->addr.in6, ntohs(dest->port), ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), atomic_read(&dest->inactconns)); else #endif seq_printf(seq, " -> %08X:%04X " "%-7s %-6d %-10d %-10d\n", ntohl(dest->addr.ip), ntohs(dest->port), ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), atomic_read(&dest->inactconns)); } } return 0; } static const struct seq_operations ip_vs_info_seq_ops = { .start = ip_vs_info_seq_start, .next = ip_vs_info_seq_next, .stop = ip_vs_info_seq_stop, .show = ip_vs_info_seq_show, }; static int ip_vs_stats_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); struct ip_vs_kstats show; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Total Incoming Outgoing Incoming Outgoing\n"); seq_puts(seq, " Conns Packets Packets Bytes Bytes\n"); ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats); seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n", (unsigned long long)show.conns, (unsigned long long)show.inpkts, (unsigned long long)show.outpkts, (unsigned long long)show.inbytes, (unsigned long long)show.outbytes); /* 01234567 01234567 01234567 0123456701234567 0123456701234567*/ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n", (unsigned long long)show.cps, (unsigned long long)show.inpps, (unsigned long long)show.outpps, (unsigned long long)show.inbps, (unsigned long long)show.outbps); return 0; } static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats; struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats; struct ip_vs_kstats kstats; int i; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Total Incoming Outgoing Incoming Outgoing\n"); seq_puts(seq, "CPU Conns Packets Packets Bytes Bytes\n"); for_each_possible_cpu(i) { struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i); unsigned int start; u64 conns, inpkts, outpkts, inbytes, outbytes; do { start = u64_stats_fetch_begin_irq(&u->syncp); conns = u->cnt.conns; inpkts = u->cnt.inpkts; outpkts = u->cnt.outpkts; inbytes = u->cnt.inbytes; outbytes = u->cnt.outbytes; } while (u64_stats_fetch_retry_irq(&u->syncp, start)); seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n", i, (u64)conns, (u64)inpkts, (u64)outpkts, (u64)inbytes, (u64)outbytes); } ip_vs_copy_stats(&kstats, tot_stats); seq_printf(seq, " ~ %8LX %8LX %8LX %16LX %16LX\n\n", (unsigned long long)kstats.conns, (unsigned long long)kstats.inpkts, (unsigned long long)kstats.outpkts, (unsigned long long)kstats.inbytes, (unsigned long long)kstats.outbytes); /* ... 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq, " %8LX %8LX %8LX %16LX %16LX\n", kstats.cps, kstats.inpps, kstats.outpps, kstats.inbps, kstats.outbps); return 0; } #endif /* * Set timeout values for tcp tcpfin udp in the timeout_table. */ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) struct ip_vs_proto_data *pd; #endif IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n", u->tcp_timeout, u->tcp_fin_timeout, u->udp_timeout); #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { return -EINVAL; } #endif #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) return -EINVAL; #endif #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] = u->tcp_timeout * HZ; } if (u->tcp_fin_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] = u->tcp_fin_timeout * HZ; } #endif #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); pd->timeout_table[IP_VS_UDP_S_NORMAL] = u->udp_timeout * HZ; } #endif return 0; } #define CMDID(cmd) (cmd - IP_VS_BASE_CTL) struct ip_vs_svcdest_user { struct ip_vs_service_user s; struct ip_vs_dest_user d; }; static const unsigned char set_arglen[CMDID(IP_VS_SO_SET_MAX) + 1] = { [CMDID(IP_VS_SO_SET_ADD)] = sizeof(struct ip_vs_service_user), [CMDID(IP_VS_SO_SET_EDIT)] = sizeof(struct ip_vs_service_user), [CMDID(IP_VS_SO_SET_DEL)] = sizeof(struct ip_vs_service_user), [CMDID(IP_VS_SO_SET_ADDDEST)] = sizeof(struct ip_vs_svcdest_user), [CMDID(IP_VS_SO_SET_DELDEST)] = sizeof(struct ip_vs_svcdest_user), [CMDID(IP_VS_SO_SET_EDITDEST)] = sizeof(struct ip_vs_svcdest_user), [CMDID(IP_VS_SO_SET_TIMEOUT)] = sizeof(struct ip_vs_timeout_user), [CMDID(IP_VS_SO_SET_STARTDAEMON)] = sizeof(struct ip_vs_daemon_user), [CMDID(IP_VS_SO_SET_STOPDAEMON)] = sizeof(struct ip_vs_daemon_user), [CMDID(IP_VS_SO_SET_ZERO)] = sizeof(struct ip_vs_service_user), }; union ip_vs_set_arglen { struct ip_vs_service_user field_IP_VS_SO_SET_ADD; struct ip_vs_service_user field_IP_VS_SO_SET_EDIT; struct ip_vs_service_user field_IP_VS_SO_SET_DEL; struct ip_vs_svcdest_user field_IP_VS_SO_SET_ADDDEST; struct ip_vs_svcdest_user field_IP_VS_SO_SET_DELDEST; struct ip_vs_svcdest_user field_IP_VS_SO_SET_EDITDEST; struct ip_vs_timeout_user field_IP_VS_SO_SET_TIMEOUT; struct ip_vs_daemon_user field_IP_VS_SO_SET_STARTDAEMON; struct ip_vs_daemon_user field_IP_VS_SO_SET_STOPDAEMON; struct ip_vs_service_user field_IP_VS_SO_SET_ZERO; }; #define MAX_SET_ARGLEN sizeof(union ip_vs_set_arglen) static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc, struct ip_vs_service_user *usvc_compat) { memset(usvc, 0, sizeof(*usvc)); usvc->af = AF_INET; usvc->protocol = usvc_compat->protocol; usvc->addr.ip = usvc_compat->addr; usvc->port = usvc_compat->port; usvc->fwmark = usvc_compat->fwmark; /* Deep copy of sched_name is not needed here */ usvc->sched_name = usvc_compat->sched_name; usvc->flags = usvc_compat->flags; usvc->timeout = usvc_compat->timeout; usvc->netmask = usvc_compat->netmask; } static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest, struct ip_vs_dest_user *udest_compat) { memset(udest, 0, sizeof(*udest)); udest->addr.ip = udest_compat->addr; udest->port = udest_compat->port; udest->conn_flags = udest_compat->conn_flags; udest->weight = udest_compat->weight; udest->u_threshold = udest_compat->u_threshold; udest->l_threshold = udest_compat->l_threshold; udest->af = AF_INET; udest->tun_type = IP_VS_CONN_F_TUNNEL_TYPE_IPIP; } static int do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len) { struct net *net = sock_net(sk); int ret; unsigned char arg[MAX_SET_ARGLEN]; struct ip_vs_service_user *usvc_compat; struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; struct ip_vs_dest_user *udest_compat; struct ip_vs_dest_user_kern udest; struct netns_ipvs *ipvs = net_ipvs(net); BUILD_BUG_ON(sizeof(arg) > 255); if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX) return -EINVAL; if (len != set_arglen[CMDID(cmd)]) { IP_VS_DBG(1, "set_ctl: len %u != %u\n", len, set_arglen[CMDID(cmd)]); return -EINVAL; } if (copy_from_sockptr(arg, ptr, len) != 0) return -EFAULT; /* Handle daemons since they have another lock */ if (cmd == IP_VS_SO_SET_STARTDAEMON || cmd == IP_VS_SO_SET_STOPDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; if (cmd == IP_VS_SO_SET_STARTDAEMON) { struct ipvs_sync_daemon_cfg cfg; memset(&cfg, 0, sizeof(cfg)); ret = -EINVAL; if (strscpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)) <= 0) return ret; cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { ret = stop_sync_thread(ipvs, dm->state); } return ret; } mutex_lock(&__ip_vs_mutex); if (cmd == IP_VS_SO_SET_FLUSH) { /* Flush the virtual service */ ret = ip_vs_flush(ipvs, false); goto out_unlock; } else if (cmd == IP_VS_SO_SET_TIMEOUT) { /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; } else if (!len) { /* No more commands with len == 0 below */ ret = -EINVAL; goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; udest_compat = (struct ip_vs_dest_user *)(usvc_compat + 1); /* We only use the new structs internally, so copy userspace compat * structs to extended internal versions */ ip_vs_copy_usvc_compat(&usvc, usvc_compat); ip_vs_copy_udest_compat(&udest, udest_compat); if (cmd == IP_VS_SO_SET_ZERO) { /* if no service address is set, zero counters in all */ if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) { ret = ip_vs_zero_all(ipvs); goto out_unlock; } } if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) && strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) == IP_VS_SCHEDNAME_MAXLEN) { ret = -EINVAL; goto out_unlock; } /* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */ if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP && usvc.protocol != IPPROTO_SCTP) { pr_err("set_ctl: invalid protocol: %d %pI4:%d\n", usvc.protocol, &usvc.addr.ip, ntohs(usvc.port)); ret = -EFAULT; goto out_unlock; } /* Lookup the exact service by <protocol, addr, port> or fwmark */ rcu_read_lock(); if (usvc.fwmark == 0) svc = __ip_vs_service_find(ipvs, usvc.af, usvc.protocol, &usvc.addr, usvc.port); else svc = __ip_vs_svc_fwm_find(ipvs, usvc.af, usvc.fwmark); rcu_read_unlock(); if (cmd != IP_VS_SO_SET_ADD && (svc == NULL || svc->protocol != usvc.protocol)) { ret = -ESRCH; goto out_unlock; } switch (cmd) { case IP_VS_SO_SET_ADD: if (svc != NULL) ret = -EEXIST; else ret = ip_vs_add_service(ipvs, &usvc, &svc); break; case IP_VS_SO_SET_EDIT: ret = ip_vs_edit_service(svc, &usvc); break; case IP_VS_SO_SET_DEL: ret = ip_vs_del_service(svc); if (!ret) goto out_unlock; break; case IP_VS_SO_SET_ZERO: ret = ip_vs_zero_service(svc); break; case IP_VS_SO_SET_ADDDEST: ret = ip_vs_add_dest(svc, &udest); break; case IP_VS_SO_SET_EDITDEST: ret = ip_vs_edit_dest(svc, &udest); break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); } out_unlock: mutex_unlock(&__ip_vs_mutex); return ret; } static void ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; struct ip_vs_kstats kstats; char *sched_name; sched = rcu_dereference_protected(src->scheduler, 1); sched_name = sched ? sched->name : "none"; dst->protocol = src->protocol; dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name)); dst->flags = src->flags; dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; dst->num_dests = src->num_dests; ip_vs_copy_stats(&kstats, &src->stats); ip_vs_export_stats_user(&dst->stats, &kstats); } static inline int __ip_vs_get_service_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_services *get, struct ip_vs_get_services __user *uptr) { int idx, count=0; struct ip_vs_service *svc; struct ip_vs_service_entry entry; int ret = 0; for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { /* Only expose IPv4 entries to old interface */ if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) goto out; memset(&entry, 0, sizeof(entry)); ip_vs_copy_service(&entry, svc); if (copy_to_user(&uptr->entrytable[count], &entry, sizeof(entry))) { ret = -EFAULT; goto out; } count++; } } for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { /* Only expose IPv4 entries to old interface */ if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) goto out; memset(&entry, 0, sizeof(entry)); ip_vs_copy_service(&entry, svc); if (copy_to_user(&uptr->entrytable[count], &entry, sizeof(entry))) { ret = -EFAULT; goto out; } count++; } } out: return ret; } static inline int __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *get, struct ip_vs_get_dests __user *uptr) { struct ip_vs_service *svc; union nf_inet_addr addr = { .ip = get->addr }; int ret = 0; rcu_read_lock(); if (get->fwmark) svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, get->fwmark); else svc = __ip_vs_service_find(ipvs, AF_INET, get->protocol, &addr, get->port); rcu_read_unlock(); if (svc) { int count = 0; struct ip_vs_dest *dest; struct ip_vs_dest_entry entry; struct ip_vs_kstats kstats; memset(&entry, 0, sizeof(entry)); list_for_each_entry(dest, &svc->destinations, n_list) { if (count >= get->num_dests) break; /* Cannot expose heterogeneous members via sockopt * interface */ if (dest->af != svc->af) continue; entry.addr = dest->addr.ip; entry.port = dest->port; entry.conn_flags = atomic_read(&dest->conn_flags); entry.weight = atomic_read(&dest->weight); entry.u_threshold = dest->u_threshold; entry.l_threshold = dest->l_threshold; entry.activeconns = atomic_read(&dest->activeconns); entry.inactconns = atomic_read(&dest->inactconns); entry.persistconns = atomic_read(&dest->persistconns); ip_vs_copy_stats(&kstats, &dest->stats); ip_vs_export_stats_user(&entry.stats, &kstats); if (copy_to_user(&uptr->entrytable[count], &entry, sizeof(entry))) { ret = -EFAULT; break; } count++; } } else ret = -ESRCH; return ret; } static inline void __ip_vs_get_timeouts(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) struct ip_vs_proto_data *pd; #endif memset(u, 0, sizeof (*u)); #ifdef CONFIG_IP_VS_PROTO_TCP pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; #endif #ifdef CONFIG_IP_VS_PROTO_UDP pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); u->udp_timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ; #endif } static const unsigned char get_arglen[CMDID(IP_VS_SO_GET_MAX) + 1] = { [CMDID(IP_VS_SO_GET_VERSION)] = 64, [CMDID(IP_VS_SO_GET_INFO)] = sizeof(struct ip_vs_getinfo), [CMDID(IP_VS_SO_GET_SERVICES)] = sizeof(struct ip_vs_get_services), [CMDID(IP_VS_SO_GET_SERVICE)] = sizeof(struct ip_vs_service_entry), [CMDID(IP_VS_SO_GET_DESTS)] = sizeof(struct ip_vs_get_dests), [CMDID(IP_VS_SO_GET_TIMEOUT)] = sizeof(struct ip_vs_timeout_user), [CMDID(IP_VS_SO_GET_DAEMON)] = 2 * sizeof(struct ip_vs_daemon_user), }; union ip_vs_get_arglen { char field_IP_VS_SO_GET_VERSION[64]; struct ip_vs_getinfo field_IP_VS_SO_GET_INFO; struct ip_vs_get_services field_IP_VS_SO_GET_SERVICES; struct ip_vs_service_entry field_IP_VS_SO_GET_SERVICE; struct ip_vs_get_dests field_IP_VS_SO_GET_DESTS; struct ip_vs_timeout_user field_IP_VS_SO_GET_TIMEOUT; struct ip_vs_daemon_user field_IP_VS_SO_GET_DAEMON[2]; }; #define MAX_GET_ARGLEN sizeof(union ip_vs_get_arglen) static int do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { unsigned char arg[MAX_GET_ARGLEN]; int ret = 0; unsigned int copylen; struct net *net = sock_net(sk); struct netns_ipvs *ipvs = net_ipvs(net); BUG_ON(!net); BUILD_BUG_ON(sizeof(arg) > 255); if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX) return -EINVAL; copylen = get_arglen[CMDID(cmd)]; if (*len < (int) copylen) { IP_VS_DBG(1, "get_ctl: len %d < %u\n", *len, copylen); return -EINVAL; } if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; /* * Handle daemons first since it has its own locking */ if (cmd == IP_VS_SO_GET_DAEMON) { struct ip_vs_daemon_user d[2]; memset(&d, 0, sizeof(d)); mutex_lock(&ipvs->sync_mutex); if (ipvs->sync_state & IP_VS_STATE_MASTER) { d[0].state = IP_VS_STATE_MASTER; strlcpy(d[0].mcast_ifn, ipvs->mcfg.mcast_ifn, sizeof(d[0].mcast_ifn)); d[0].syncid = ipvs->mcfg.syncid; } if (ipvs->sync_state & IP_VS_STATE_BACKUP) { d[1].state = IP_VS_STATE_BACKUP; strlcpy(d[1].mcast_ifn, ipvs->bcfg.mcast_ifn, sizeof(d[1].mcast_ifn)); d[1].syncid = ipvs->bcfg.syncid; } if (copy_to_user(user, &d, sizeof(d)) != 0) ret = -EFAULT; mutex_unlock(&ipvs->sync_mutex); return ret; } mutex_lock(&__ip_vs_mutex); switch (cmd) { case IP_VS_SO_GET_VERSION: { char buf[64]; sprintf(buf, "IP Virtual Server version %d.%d.%d (size=%d)", NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size); if (copy_to_user(user, buf, strlen(buf)+1) != 0) { ret = -EFAULT; goto out; } *len = strlen(buf)+1; } break; case IP_VS_SO_GET_INFO: { struct ip_vs_getinfo info; info.version = IP_VS_VERSION_CODE; info.size = ip_vs_conn_tab_size; info.num_services = ipvs->num_services; if (copy_to_user(user, &info, sizeof(info)) != 0) ret = -EFAULT; } break; case IP_VS_SO_GET_SERVICES: { struct ip_vs_get_services *get; int size; get = (struct ip_vs_get_services *)arg; size = struct_size(get, entrytable, get->num_services); if (*len != size) { pr_err("length: %u != %u\n", *len, size); ret = -EINVAL; goto out; } ret = __ip_vs_get_service_entries(ipvs, get, user); } break; case IP_VS_SO_GET_SERVICE: { struct ip_vs_service_entry *entry; struct ip_vs_service *svc; union nf_inet_addr addr; entry = (struct ip_vs_service_entry *)arg; addr.ip = entry->addr; rcu_read_lock(); if (entry->fwmark) svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, entry->fwmark); else svc = __ip_vs_service_find(ipvs, AF_INET, entry->protocol, &addr, entry->port); rcu_read_unlock(); if (svc) { ip_vs_copy_service(entry, svc); if (copy_to_user(user, entry, sizeof(*entry)) != 0) ret = -EFAULT; } else ret = -ESRCH; } break; case IP_VS_SO_GET_DESTS: { struct ip_vs_get_dests *get; int size; get = (struct ip_vs_get_dests *)arg; size = struct_size(get, entrytable, get->num_dests); if (*len != size) { pr_err("length: %u != %u\n", *len, size); ret = -EINVAL; goto out; } ret = __ip_vs_get_dest_entries(ipvs, get, user); } break; case IP_VS_SO_GET_TIMEOUT: { struct ip_vs_timeout_user t; __ip_vs_get_timeouts(ipvs, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; } break; default: ret = -EINVAL; } out: mutex_unlock(&__ip_vs_mutex); return ret; } static struct nf_sockopt_ops ip_vs_sockopts = { .pf = PF_INET, .set_optmin = IP_VS_BASE_CTL, .set_optmax = IP_VS_SO_SET_MAX+1, .set = do_ip_vs_set_ctl, .get_optmin = IP_VS_BASE_CTL, .get_optmax = IP_VS_SO_GET_MAX+1, .get = do_ip_vs_get_ctl, .owner = THIS_MODULE, }; /* * Generic Netlink interface */ /* IPVS genetlink family */ static struct genl_family ip_vs_genl_family; /* Policy used for first-level command attributes */ static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = { [IPVS_CMD_ATTR_SERVICE] = { .type = NLA_NESTED }, [IPVS_CMD_ATTR_DEST] = { .type = NLA_NESTED }, [IPVS_CMD_ATTR_DAEMON] = { .type = NLA_NESTED }, [IPVS_CMD_ATTR_TIMEOUT_TCP] = { .type = NLA_U32 }, [IPVS_CMD_ATTR_TIMEOUT_TCP_FIN] = { .type = NLA_U32 }, [IPVS_CMD_ATTR_TIMEOUT_UDP] = { .type = NLA_U32 }, }; /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DAEMON */ static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = { [IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 }, [IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING, .len = IP_VS_IFNAME_MAXLEN - 1 }, [IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 }, [IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 }, [IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 }, [IPVS_DAEMON_ATTR_MCAST_GROUP6] = { .len = sizeof(struct in6_addr) }, [IPVS_DAEMON_ATTR_MCAST_PORT] = { .type = NLA_U16 }, [IPVS_DAEMON_ATTR_MCAST_TTL] = { .type = NLA_U8 }, }; /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_SERVICE */ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = { [IPVS_SVC_ATTR_AF] = { .type = NLA_U16 }, [IPVS_SVC_ATTR_PROTOCOL] = { .type = NLA_U16 }, [IPVS_SVC_ATTR_ADDR] = { .type = NLA_BINARY, .len = sizeof(union nf_inet_addr) }, [IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 }, [IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 }, [IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING, .len = IP_VS_SCHEDNAME_MAXLEN - 1 }, [IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING, .len = IP_VS_PENAME_MAXLEN }, [IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY, .len = sizeof(struct ip_vs_flags) }, [IPVS_SVC_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPVS_SVC_ATTR_NETMASK] = { .type = NLA_U32 }, [IPVS_SVC_ATTR_STATS] = { .type = NLA_NESTED }, }; /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DEST */ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { [IPVS_DEST_ATTR_ADDR] = { .type = NLA_BINARY, .len = sizeof(union nf_inet_addr) }, [IPVS_DEST_ATTR_PORT] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_FWD_METHOD] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_WEIGHT] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_U_THRESH] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_L_THRESH] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_ACTIVE_CONNS] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_INACT_CONNS] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_PERSIST_CONNS] = { .type = NLA_U32 }, [IPVS_DEST_ATTR_STATS] = { .type = NLA_NESTED }, [IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 }, [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_TUN_FLAGS] = { .type = NLA_U16 }, }; static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, struct ip_vs_kstats *kstats) { struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type); if (!nl_stats) return -EMSGSIZE; if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, (u32)kstats->conns) || nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, (u32)kstats->inpkts) || nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, (u32)kstats->outpkts) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes, IPVS_STATS_ATTR_PAD) || nla_put_u32(skb, IPVS_STATS_ATTR_CPS, (u32)kstats->cps) || nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, (u32)kstats->inpps) || nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, (u32)kstats->outpps) || nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, (u32)kstats->inbps) || nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, (u32)kstats->outbps)) goto nla_put_failure; nla_nest_end(skb, nl_stats); return 0; nla_put_failure: nla_nest_cancel(skb, nl_stats); return -EMSGSIZE; } static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type, struct ip_vs_kstats *kstats) { struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type); if (!nl_stats) return -EMSGSIZE; if (nla_put_u64_64bit(skb, IPVS_STATS_ATTR_CONNS, kstats->conns, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_INPKTS, kstats->inpkts, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_OUTPKTS, kstats->outpkts, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_CPS, kstats->cps, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_INPPS, kstats->inpps, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_OUTPPS, kstats->outpps, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_INBPS, kstats->inbps, IPVS_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, IPVS_STATS_ATTR_OUTBPS, kstats->outbps, IPVS_STATS_ATTR_PAD)) goto nla_put_failure; nla_nest_end(skb, nl_stats); return 0; nla_put_failure: nla_nest_cancel(skb, nl_stats); return -EMSGSIZE; } static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_service *svc) { struct ip_vs_scheduler *sched; struct ip_vs_pe *pe; struct nlattr *nl_service; struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; struct ip_vs_kstats kstats; char *sched_name; nl_service = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) return -EMSGSIZE; if (nla_put_u16(skb, IPVS_SVC_ATTR_AF, svc->af)) goto nla_put_failure; if (svc->fwmark) { if (nla_put_u32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark)) goto nla_put_failure; } else { if (nla_put_u16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol) || nla_put(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr) || nla_put_be16(skb, IPVS_SVC_ATTR_PORT, svc->port)) goto nla_put_failure; } sched = rcu_dereference_protected(svc->scheduler, 1); sched_name = sched ? sched->name : "none"; pe = rcu_dereference_protected(svc->pe, 1); if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) || (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) || nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || nla_put_be32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask)) goto nla_put_failure; ip_vs_copy_stats(&kstats, &svc->stats); if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &kstats)) goto nla_put_failure; if (ip_vs_genl_fill_stats64(skb, IPVS_SVC_ATTR_STATS64, &kstats)) goto nla_put_failure; nla_nest_end(skb, nl_service); return 0; nla_put_failure: nla_nest_cancel(skb, nl_service); return -EMSGSIZE; } static int ip_vs_genl_dump_service(struct sk_buff *skb, struct ip_vs_service *svc, struct netlink_callback *cb) { void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_SERVICE); if (!hdr) return -EMSGSIZE; if (ip_vs_genl_fill_service(skb, svc) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ip_vs_genl_dump_services(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; goto nla_put_failure; } } } for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; goto nla_put_failure; } } } nla_put_failure: mutex_unlock(&__ip_vs_mutex); cb->args[0] = idx; return skb->len; } static bool ip_vs_is_af_valid(int af) { if (af == AF_INET) return true; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6 && ipv6_mod_enabled()) return true; #endif return false; } static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *usvc, struct nlattr *nla, bool full_entry, struct ip_vs_service **ret_svc) { struct nlattr *attrs[IPVS_SVC_ATTR_MAX + 1]; struct nlattr *nla_af, *nla_port, *nla_fwmark, *nla_protocol, *nla_addr; struct ip_vs_service *svc; /* Parse mandatory identifying service fields first */ if (nla == NULL || nla_parse_nested_deprecated(attrs, IPVS_SVC_ATTR_MAX, nla, ip_vs_svc_policy, NULL)) return -EINVAL; nla_af = attrs[IPVS_SVC_ATTR_AF]; nla_protocol = attrs[IPVS_SVC_ATTR_PROTOCOL]; nla_addr = attrs[IPVS_SVC_ATTR_ADDR]; nla_port = attrs[IPVS_SVC_ATTR_PORT]; nla_fwmark = attrs[IPVS_SVC_ATTR_FWMARK]; if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr)))) return -EINVAL; memset(usvc, 0, sizeof(*usvc)); usvc->af = nla_get_u16(nla_af); if (!ip_vs_is_af_valid(usvc->af)) return -EAFNOSUPPORT; if (nla_fwmark) { usvc->protocol = IPPROTO_TCP; usvc->fwmark = nla_get_u32(nla_fwmark); } else { usvc->protocol = nla_get_u16(nla_protocol); nla_memcpy(&usvc->addr, nla_addr, sizeof(usvc->addr)); usvc->port = nla_get_be16(nla_port); usvc->fwmark = 0; } rcu_read_lock(); if (usvc->fwmark) svc = __ip_vs_svc_fwm_find(ipvs, usvc->af, usvc->fwmark); else svc = __ip_vs_service_find(ipvs, usvc->af, usvc->protocol, &usvc->addr, usvc->port); rcu_read_unlock(); *ret_svc = svc; /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_sched, *nla_flags, *nla_pe, *nla_timeout, *nla_netmask; struct ip_vs_flags flags; nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME]; nla_pe = attrs[IPVS_SVC_ATTR_PE_NAME]; nla_flags = attrs[IPVS_SVC_ATTR_FLAGS]; nla_timeout = attrs[IPVS_SVC_ATTR_TIMEOUT]; nla_netmask = attrs[IPVS_SVC_ATTR_NETMASK]; if (!(nla_sched && nla_flags && nla_timeout && nla_netmask)) return -EINVAL; nla_memcpy(&flags, nla_flags, sizeof(flags)); /* prefill flags from service if it already exists */ if (svc) usvc->flags = svc->flags; /* set new flags from userland */ usvc->flags = (usvc->flags & ~flags.mask) | (flags.flags & flags.mask); usvc->sched_name = nla_data(nla_sched); usvc->pe_name = nla_pe ? nla_data(nla_pe) : NULL; usvc->timeout = nla_get_u32(nla_timeout); usvc->netmask = nla_get_be32(nla_netmask); } return 0; } static struct ip_vs_service *ip_vs_genl_find_service(struct netns_ipvs *ipvs, struct nlattr *nla) { struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; int ret; ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, false, &svc); return ret ? ERR_PTR(ret) : svc; } static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) { struct nlattr *nl_dest; struct ip_vs_kstats kstats; nl_dest = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DEST); if (!nl_dest) return -EMSGSIZE; if (nla_put(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr) || nla_put_be16(skb, IPVS_DEST_ATTR_PORT, dest->port) || nla_put_u32(skb, IPVS_DEST_ATTR_FWD_METHOD, (atomic_read(&dest->conn_flags) & IP_VS_CONN_F_FWD_MASK)) || nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT, atomic_read(&dest->weight)) || nla_put_u8(skb, IPVS_DEST_ATTR_TUN_TYPE, dest->tun_type) || nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT, dest->tun_port) || nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, dest->tun_flags) || nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, atomic_read(&dest->activeconns)) || nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS, atomic_read(&dest->inactconns)) || nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, atomic_read(&dest->persistconns)) || nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af)) goto nla_put_failure; ip_vs_copy_stats(&kstats, &dest->stats); if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &kstats)) goto nla_put_failure; if (ip_vs_genl_fill_stats64(skb, IPVS_DEST_ATTR_STATS64, &kstats)) goto nla_put_failure; nla_nest_end(skb, nl_dest); return 0; nla_put_failure: nla_nest_cancel(skb, nl_dest); return -EMSGSIZE; } static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, struct netlink_callback *cb) { void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DEST); if (!hdr) return -EMSGSIZE; if (ip_vs_genl_fill_dest(skb, dest) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ip_vs_genl_dump_dests(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0; int start = cb->args[0]; struct ip_vs_service *svc; struct ip_vs_dest *dest; struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); /* Try to find the service for which to dump destinations */ if (nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN, attrs, IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy, cb->extack)) goto out_err; svc = ip_vs_genl_find_service(ipvs, attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR_OR_NULL(svc)) goto out_err; /* Dump the destinations */ list_for_each_entry(dest, &svc->destinations, n_list) { if (++idx <= start) continue; if (ip_vs_genl_dump_dest(skb, dest, cb) < 0) { idx--; goto nla_put_failure; } } nla_put_failure: cb->args[0] = idx; out_err: mutex_unlock(&__ip_vs_mutex); return skb->len; } static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, struct nlattr *nla, bool full_entry) { struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1]; struct nlattr *nla_addr, *nla_port; struct nlattr *nla_addr_family; /* Parse mandatory identifying destination fields first */ if (nla == NULL || nla_parse_nested_deprecated(attrs, IPVS_DEST_ATTR_MAX, nla, ip_vs_dest_policy, NULL)) return -EINVAL; nla_addr = attrs[IPVS_DEST_ATTR_ADDR]; nla_port = attrs[IPVS_DEST_ATTR_PORT]; nla_addr_family = attrs[IPVS_DEST_ATTR_ADDR_FAMILY]; if (!(nla_addr && nla_port)) return -EINVAL; memset(udest, 0, sizeof(*udest)); nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr)); udest->port = nla_get_be16(nla_port); if (nla_addr_family) udest->af = nla_get_u16(nla_addr_family); else udest->af = 0; /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh, *nla_l_thresh, *nla_tun_type, *nla_tun_port, *nla_tun_flags; nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD]; nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT]; nla_u_thresh = attrs[IPVS_DEST_ATTR_U_THRESH]; nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH]; nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE]; nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT]; nla_tun_flags = attrs[IPVS_DEST_ATTR_TUN_FLAGS]; if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh)) return -EINVAL; udest->conn_flags = nla_get_u32(nla_fwd) & IP_VS_CONN_F_FWD_MASK; udest->weight = nla_get_u32(nla_weight); udest->u_threshold = nla_get_u32(nla_u_thresh); udest->l_threshold = nla_get_u32(nla_l_thresh); if (nla_tun_type) udest->tun_type = nla_get_u8(nla_tun_type); if (nla_tun_port) udest->tun_port = nla_get_be16(nla_tun_port); if (nla_tun_flags) udest->tun_flags = nla_get_u16(nla_tun_flags); } return 0; } static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state, struct ipvs_sync_daemon_cfg *c) { struct nlattr *nl_daemon; nl_daemon = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DAEMON); if (!nl_daemon) return -EMSGSIZE; if (nla_put_u32(skb, IPVS_DAEMON_ATTR_STATE, state) || nla_put_string(skb, IPVS_DAEMON_ATTR_MCAST_IFN, c->mcast_ifn) || nla_put_u32(skb, IPVS_DAEMON_ATTR_SYNC_ID, c->syncid) || nla_put_u16(skb, IPVS_DAEMON_ATTR_SYNC_MAXLEN, c->sync_maxlen) || nla_put_u16(skb, IPVS_DAEMON_ATTR_MCAST_PORT, c->mcast_port) || nla_put_u8(skb, IPVS_DAEMON_ATTR_MCAST_TTL, c->mcast_ttl)) goto nla_put_failure; #ifdef CONFIG_IP_VS_IPV6 if (c->mcast_af == AF_INET6) { if (nla_put_in6_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP6, &c->mcast_group.in6)) goto nla_put_failure; } else #endif if (c->mcast_af == AF_INET && nla_put_in_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP, c->mcast_group.ip)) goto nla_put_failure; nla_nest_end(skb, nl_daemon); return 0; nla_put_failure: nla_nest_cancel(skb, nl_daemon); return -EMSGSIZE; } static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state, struct ipvs_sync_daemon_cfg *c, struct netlink_callback *cb) { void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DAEMON); if (!hdr) return -EMSGSIZE; if (ip_vs_genl_fill_daemon(skb, state, c)) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, &ipvs->mcfg, cb) < 0) goto nla_put_failure; cb->args[0] = 1; } if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP, &ipvs->bcfg, cb) < 0) goto nla_put_failure; cb->args[1] = 1; } nla_put_failure: mutex_unlock(&ipvs->sync_mutex); return skb->len; } static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) { struct ipvs_sync_daemon_cfg c; struct nlattr *a; int ret; memset(&c, 0, sizeof(c)); if (!(attrs[IPVS_DAEMON_ATTR_STATE] && attrs[IPVS_DAEMON_ATTR_MCAST_IFN] && attrs[IPVS_DAEMON_ATTR_SYNC_ID])) return -EINVAL; strlcpy(c.mcast_ifn, nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), sizeof(c.mcast_ifn)); c.syncid = nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID]); a = attrs[IPVS_DAEMON_ATTR_SYNC_MAXLEN]; if (a) c.sync_maxlen = nla_get_u16(a); a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP]; if (a) { c.mcast_af = AF_INET; c.mcast_group.ip = nla_get_in_addr(a); if (!ipv4_is_multicast(c.mcast_group.ip)) return -EINVAL; } else { a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP6]; if (a) { #ifdef CONFIG_IP_VS_IPV6 int addr_type; c.mcast_af = AF_INET6; c.mcast_group.in6 = nla_get_in6_addr(a); addr_type = ipv6_addr_type(&c.mcast_group.in6); if (!(addr_type & IPV6_ADDR_MULTICAST)) return -EINVAL; #else return -EAFNOSUPPORT; #endif } } a = attrs[IPVS_DAEMON_ATTR_MCAST_PORT]; if (a) c.mcast_port = nla_get_u16(a); a = attrs[IPVS_DAEMON_ATTR_MCAST_TTL]; if (a) c.mcast_ttl = nla_get_u8(a); /* The synchronization protocol is incompatible with mixed family * services */ if (ipvs->mixed_address_family_dests > 0) return -EINVAL; ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); return ret; } static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) { int ret; if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL; ret = stop_sync_thread(ipvs, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); return ret; } static int ip_vs_genl_set_config(struct netns_ipvs *ipvs, struct nlattr **attrs) { struct ip_vs_timeout_user t; __ip_vs_get_timeouts(ipvs, &t); if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]) t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]); if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN]) t.tcp_fin_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN]); if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]) t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]); return ip_vs_set_timeout(ipvs, &t); } static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { int ret = -EINVAL, cmd; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || nla_parse_nested_deprecated(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], ip_vs_daemon_policy, info->extack)) goto out; if (cmd == IPVS_CMD_NEW_DAEMON) ret = ip_vs_genl_new_daemon(ipvs, daemon_attrs); else ret = ip_vs_genl_del_daemon(ipvs, daemon_attrs); } out: return ret; } static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) { bool need_full_svc = false, need_full_dest = false; struct ip_vs_service *svc = NULL; struct ip_vs_service_user_kern usvc; struct ip_vs_dest_user_kern udest; int ret = 0, cmd; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; mutex_lock(&__ip_vs_mutex); if (cmd == IPVS_CMD_FLUSH) { ret = ip_vs_flush(ipvs, false); goto out; } else if (cmd == IPVS_CMD_SET_CONFIG) { ret = ip_vs_genl_set_config(ipvs, info->attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { ret = ip_vs_zero_all(ipvs); goto out; } /* All following commands require a service argument, so check if we * received a valid one. We need a full service specification when * adding / editing a service. Only identifying members otherwise. */ if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) need_full_svc = true; ret = ip_vs_genl_parse_service(ipvs, &usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], need_full_svc, &svc); if (ret) goto out; /* Unless we're adding a new service, the service must already exist */ if ((cmd != IPVS_CMD_NEW_SERVICE) && (svc == NULL)) { ret = -ESRCH; goto out; } /* Destination commands require a valid destination argument. For * adding / editing a destination, we need a full destination * specification. */ if (cmd == IPVS_CMD_NEW_DEST || cmd == IPVS_CMD_SET_DEST || cmd == IPVS_CMD_DEL_DEST) { if (cmd != IPVS_CMD_DEL_DEST) need_full_dest = true; ret = ip_vs_genl_parse_dest(&udest, info->attrs[IPVS_CMD_ATTR_DEST], need_full_dest); if (ret) goto out; /* Old protocols did not allow the user to specify address * family, so we set it to zero instead. We also didn't * allow heterogeneous pools in the old code, so it's safe * to assume that this will have the same address family as * the service. */ if (udest.af == 0) udest.af = svc->af; if (!ip_vs_is_af_valid(udest.af)) { ret = -EAFNOSUPPORT; goto out; } if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) { /* The synchronization protocol is incompatible * with mixed family services */ if (ipvs->sync_state) { ret = -EINVAL; goto out; } /* Which connection types do we support? */ switch (udest.conn_flags) { case IP_VS_CONN_F_TUNNEL: /* We are able to forward this */ break; default: ret = -EINVAL; goto out; } } } switch (cmd) { case IPVS_CMD_NEW_SERVICE: if (svc == NULL) ret = ip_vs_add_service(ipvs, &usvc, &svc); else ret = -EEXIST; break; case IPVS_CMD_SET_SERVICE: ret = ip_vs_edit_service(svc, &usvc); break; case IPVS_CMD_DEL_SERVICE: ret = ip_vs_del_service(svc); /* do not use svc, it can be freed */ break; case IPVS_CMD_NEW_DEST: ret = ip_vs_add_dest(svc, &udest); break; case IPVS_CMD_SET_DEST: ret = ip_vs_edit_dest(svc, &udest); break; case IPVS_CMD_DEL_DEST: ret = ip_vs_del_dest(svc, &udest); break; case IPVS_CMD_ZERO: ret = ip_vs_zero_service(svc); break; default: ret = -EINVAL; } out: mutex_unlock(&__ip_vs_mutex); return ret; } static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; void *reply; int ret, cmd, reply_cmd; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) reply_cmd = IPVS_CMD_NEW_SERVICE; else if (cmd == IPVS_CMD_GET_INFO) reply_cmd = IPVS_CMD_SET_INFO; else if (cmd == IPVS_CMD_GET_CONFIG) reply_cmd = IPVS_CMD_SET_CONFIG; else { pr_err("unknown Generic Netlink command\n"); return -EINVAL; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; mutex_lock(&__ip_vs_mutex); reply = genlmsg_put_reply(msg, info, &ip_vs_genl_family, 0, reply_cmd); if (reply == NULL) goto nla_put_failure; switch (cmd) { case IPVS_CMD_GET_SERVICE: { struct ip_vs_service *svc; svc = ip_vs_genl_find_service(ipvs, info->attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc)) { ret = PTR_ERR(svc); goto out_err; } else if (svc) { ret = ip_vs_genl_fill_service(msg, svc); if (ret) goto nla_put_failure; } else { ret = -ESRCH; goto out_err; } break; } case IPVS_CMD_GET_CONFIG: { struct ip_vs_timeout_user t; __ip_vs_get_timeouts(ipvs, &t); #ifdef CONFIG_IP_VS_PROTO_TCP if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout) || nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, t.tcp_fin_timeout)) goto nla_put_failure; #endif #ifdef CONFIG_IP_VS_PROTO_UDP if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_UDP, t.udp_timeout)) goto nla_put_failure; #endif break; } case IPVS_CMD_GET_INFO: if (nla_put_u32(msg, IPVS_INFO_ATTR_VERSION, IP_VS_VERSION_CODE) || nla_put_u32(msg, IPVS_INFO_ATTR_CONN_TAB_SIZE, ip_vs_conn_tab_size)) goto nla_put_failure; break; } genlmsg_end(msg, reply); ret = genlmsg_reply(msg, info); goto out; nla_put_failure: pr_err("not enough space in Netlink message\n"); ret = -EMSGSIZE; out_err: nlmsg_free(msg); out: mutex_unlock(&__ip_vs_mutex); return ret; } static const struct genl_small_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_NEW_SERVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_SET_SERVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_DEL_SERVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_GET_SERVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_get_cmd, .dumpit = ip_vs_genl_dump_services, }, { .cmd = IPVS_CMD_NEW_DEST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_SET_DEST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_DEL_DEST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_GET_DEST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .dumpit = ip_vs_genl_dump_dests, }, { .cmd = IPVS_CMD_NEW_DAEMON, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_DEL_DAEMON, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_GET_DAEMON, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .dumpit = ip_vs_genl_dump_daemons, }, { .cmd = IPVS_CMD_SET_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_GET_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_get_cmd, }, { .cmd = IPVS_CMD_GET_INFO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_get_cmd, }, { .cmd = IPVS_CMD_ZERO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_set_cmd, }, }; static struct genl_family ip_vs_genl_family __ro_after_init = { .hdrsize = 0, .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, .maxattr = IPVS_CMD_ATTR_MAX, .policy = ip_vs_cmd_policy, .netnsok = true, /* Make ipvsadm to work on netns */ .module = THIS_MODULE, .small_ops = ip_vs_genl_ops, .n_small_ops = ARRAY_SIZE(ip_vs_genl_ops), }; static int __init ip_vs_genl_register(void) { return genl_register_family(&ip_vs_genl_family); } static void ip_vs_genl_unregister(void) { genl_unregister_family(&ip_vs_genl_family); } /* End of Generic Netlink interface definitions */ /* * per netns intit/exit func. */ #ifdef CONFIG_SYSCTL static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { struct net *net = ipvs->net; int idx; struct ctl_table *tbl; atomic_set(&ipvs->dropentry, 0); spin_lock_init(&ipvs->dropentry_lock); spin_lock_init(&ipvs->droppacket_lock); spin_lock_init(&ipvs->securetcp_lock); if (!net_eq(net, &init_net)) { tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) tbl[0].procname = NULL; } else tbl = vs_vars; /* Initialize sysctl defaults */ for (idx = 0; idx < ARRAY_SIZE(vs_vars); idx++) { if (tbl[idx].proc_handler == proc_do_defense_mode) tbl[idx].extra2 = ipvs; } idx = 0; ipvs->sysctl_amemthresh = 1024; tbl[idx++].data = &ipvs->sysctl_amemthresh; ipvs->sysctl_am_droprate = 10; tbl[idx++].data = &ipvs->sysctl_am_droprate; tbl[idx++].data = &ipvs->sysctl_drop_entry; tbl[idx++].data = &ipvs->sysctl_drop_packet; #ifdef CONFIG_IP_VS_NFCT tbl[idx++].data = &ipvs->sysctl_conntrack; #endif tbl[idx++].data = &ipvs->sysctl_secure_tcp; ipvs->sysctl_snat_reroute = 1; tbl[idx++].data = &ipvs->sysctl_snat_reroute; ipvs->sysctl_sync_ver = 1; tbl[idx++].data = &ipvs->sysctl_sync_ver; ipvs->sysctl_sync_ports = 1; tbl[idx++].data = &ipvs->sysctl_sync_ports; tbl[idx++].data = &ipvs->sysctl_sync_persist_mode; ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32; tbl[idx++].data = &ipvs->sysctl_sync_qlen_max; ipvs->sysctl_sync_sock_size = 0; tbl[idx++].data = &ipvs->sysctl_sync_sock_size; tbl[idx++].data = &ipvs->sysctl_cache_bypass; tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; tbl[idx++].data = &ipvs->sysctl_sloppy_tcp; tbl[idx++].data = &ipvs->sysctl_sloppy_sctp; tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; tbl[idx].extra2 = ipvs; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3); tbl[idx++].data = &ipvs->sysctl_sync_retries; tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; ipvs->sysctl_pmtu_disc = 1; tbl[idx++].data = &ipvs->sysctl_pmtu_disc; tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_conn_reuse_mode = 1; tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; #ifdef CONFIG_IP_VS_DEBUG /* Global sysctls must be ro in non-init netns */ if (!net_eq(net, &init_net)) tbl[idx++].mode = 0444; #endif ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { if (!net_eq(net, &init_net)) kfree(tbl); return -ENOMEM; } ip_vs_start_estimator(ipvs, &ipvs->tot_stats); ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); queue_delayed_work(system_long_wq, &ipvs->defense_work, DEFENSE_TIMER_PERIOD); /* Init delayed work for expiring no dest conn */ INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, expire_nodest_conn_handler); return 0; } static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { struct net *net = ipvs->net; cancel_delayed_work_sync(&ipvs->expire_nodest_conn_work); cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); ip_vs_stop_estimator(ipvs, &ipvs->tot_stats); if (!net_eq(net, &init_net)) kfree(ipvs->sysctl_tbl); } #else static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { return 0; } static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { } #endif static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, #ifdef CONFIG_IP_VS_IPV6 .priority = ADDRCONF_NOTIFY_PRIORITY + 5, #endif }; int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { int i, idx; /* Initialize rs_table */ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) INIT_HLIST_HEAD(&ipvs->rs_table[idx]); INIT_LIST_HEAD(&ipvs->dest_trash); spin_lock_init(&ipvs->dest_trash_lock); timer_setup(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire, 0); atomic_set(&ipvs->ftpsvc_counter, 0); atomic_set(&ipvs->nullsvc_counter, 0); atomic_set(&ipvs->conn_out_counter, 0); /* procfs stats */ ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); if (!ipvs->tot_stats.cpustats) return -ENOMEM; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *ipvs_tot_stats; ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats.cpustats, i); u64_stats_init(&ipvs_tot_stats->syncp); } spin_lock_init(&ipvs->tot_stats.lock); #ifdef CONFIG_PROC_FS if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter))) goto err_vs; if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, ip_vs_stats_show, NULL)) goto err_stats; if (!proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net, ip_vs_stats_percpu_show, NULL)) goto err_percpu; #endif if (ip_vs_control_net_init_sysctl(ipvs)) goto err; return 0; err: #ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); err_percpu: remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); err_stats: remove_proc_entry("ip_vs", ipvs->net->proc_net); err_vs: #endif free_percpu(ipvs->tot_stats.cpustats); return -ENOMEM; } void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); #ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); remove_proc_entry("ip_vs", ipvs->net->proc_net); #endif free_percpu(ipvs->tot_stats.cpustats); } int __init ip_vs_register_nl_ioctl(void) { int ret; ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); goto err_genl; } return 0; err_genl: nf_unregister_sockopt(&ip_vs_sockopts); err_sock: return ret; } void ip_vs_unregister_nl_ioctl(void) { ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); } int __init ip_vs_control_init(void) { int idx; int ret; EnterFunction(2); /* Initialize svc_table, ip_vs_svc_fwm_table */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { INIT_HLIST_HEAD(&ip_vs_svc_table[idx]); INIT_HLIST_HEAD(&ip_vs_svc_fwm_table[idx]); } smp_wmb(); /* Do we really need it now ? */ ret = register_netdevice_notifier(&ip_vs_dst_notifier); if (ret < 0) return ret; LeaveFunction(2); return 0; } void ip_vs_control_cleanup(void) { EnterFunction(2); unregister_netdevice_notifier(&ip_vs_dst_notifier); LeaveFunction(2); } |
| 337 338 336 4 334 5 7 5 5 2 25 5 53 53 53 53 53 53 51 53 51 53 14 51 45 168 168 168 164 6 168 492 13 324 322 324 408 408 408 407 407 284 282 285 281 284 408 152 321 324 322 323 10 316 18 124 381 53 458 28 28 28 28 28 28 28 28 28 28 129 128 129 7 128 457 460 461 460 458 5 458 457 458 460 28 458 460 325 324 12 13 436 430 16 448 5 8 13 432 8 4 7 8 8 8 6 2 4 4 2 323 324 5 324 3 2 5 350 351 347 349 350 351 350 351 1 1 1 3 152 155 223 155 118 3 38 3 185 183 122 155 223 6 4 7 29 29 29 5 3 1 3 3 1 1 6 14 1 2 8 12 6 1 16 1 20 6 15 13 2 4 9 2 6 17 10 7 6 11 1 6 1 1 1 1 1 4 19 19 11 6 25 29 218 362 363 39 218 254 254 279 278 244 31 419 418 419 418 419 154 153 155 37 14 14 1 1 3 9 10 2 4 1 2 48 48 1 3 1 4 2 38 42 31 8 2 4 2 1 31 1 10 19 28 5 7 24 5 24 5 13 1 13 13 1 1 8 1 1 1 1 1 13 11 1 13 13 13 13 3 4 12 13 12 8 1 2 5 5 4 14 14 9 3 14 13 13 13 11 13 365 3 1 18 1 365 3 367 3 1 1 1 6 2 10 8 8 8 8 8 8 8 8 6 6 7 8 8 8 8 2 2 2 1 18 4 11 4 10 18 3 15 18 7 18 15 16 9 10 8 8 16 1 4 4 1 2 4 1 3 12 12 2 1 2 359 361 439 440 434 440 439 435 440 174 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resolution entity * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Fixes: * Vitaly E. Lavrov releasing NULL neighbor in neigh_add. * Harald Welte Add neighbour cache statistics like rtstat */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/kmemleak.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/times.h> #include <net/net_namespace.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/dst.h> #include <net/sock.h> #include <net/netevent.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> #include <linux/log2.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #include <trace/events/neigh.h> #define NEIGH_DEBUG 1 #define neigh_dbg(level, fmt, ...) \ do { \ if (level <= NEIGH_DEBUG) \ pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #define PNEIGH_HASHMASK 0xF static void neigh_timer_handler(struct timer_list *t); static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid); static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, struct net_device *dev); #ifdef CONFIG_PROC_FS static const struct seq_operations neigh_stat_seq_ops; #endif /* Neighbour hash table buckets are protected with rwlock tbl->lock. - All the scans/updates to hash buckets MUST be made under this lock. - NOTHING clever should be made under this lock: no callbacks to protocol backends, no attempts to send something to network. It will result in deadlocks, if backend/driver wants to use neighbour cache. - If the entry requires some non-trivial actions, increase its reference count and release table lock. Neighbour entries are protected: - with reference count. - with rwlock neigh->lock Reference count prevents destruction. neigh->lock mainly serializes ll address data and its validity state. However, the same lock is used to protect another entry fields: - timer - resolution queue Again, nothing clever shall be made under neigh->lock, the most complicated procedure, which we allow is dev->hard_header. It is supposed, that dev->hard_header is simplistic and does not make callbacks to neighbour tables. */ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); return -ENETDOWN; } static void neigh_cleanup_and_release(struct neighbour *neigh) { trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); neigh_release(neigh); } /* * It is random distribution in the interval (1/2)*base...(3/2)*base. * It corresponds to default IPv6 settings and is not overridable, * because it is really reasonable choice. */ unsigned long neigh_rand_reach_time(unsigned long base) { return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); static void neigh_mark_dead(struct neighbour *n) { n->dead = 1; if (!list_empty(&n->gc_list)) { list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } } static void neigh_update_gc_list(struct neighbour *n) { bool on_gc_list, exempt_from_gc; write_lock_bh(&n->tbl->lock); write_lock(&n->lock); if (n->dead) goto out; /* remove from the gc list if new state is permanent or if neighbor * is externally learned; otherwise entry should be on the gc list */ exempt_from_gc = n->nud_state & NUD_PERMANENT || n->flags & NTF_EXT_LEARNED; on_gc_list = !list_empty(&n->gc_list); if (exempt_from_gc && on_gc_list) { list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } else if (!exempt_from_gc && !on_gc_list) { /* add entries to the tail; cleaning removes from the front */ list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, int *notify) { bool rc = false; u8 ndm_flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) return rc; ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; rc = true; *notify = 1; } return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, struct neigh_table *tbl) { bool retval = false; write_lock(&n->lock); if (refcount_read(&n->refcnt) == 1) { struct neighbour *neigh; neigh = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); rcu_assign_pointer(*np, neigh); neigh_mark_dead(n); retval = true; } write_unlock(&n->lock); if (retval) neigh_cleanup_and_release(n); return retval; } bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) { struct neigh_hash_table *nht; void *pkey = ndel->primary_key; u32 hash_val; struct neighbour *n; struct neighbour __rcu **np; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); hash_val = hash_val >> (32 - nht->hash_shift); np = &nht->hash_buckets[hash_val]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock)))) { if (n == ndel) return neigh_del(n, np, tbl); np = &n->next; } return false; } static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); write_lock_bh(&tbl->lock); list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) { if (refcount_read(&n->refcnt) == 1) { bool remove = false; write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); if (remove && neigh_remove_one(n, tbl)) shrunk++; if (shrunk >= max_clean) break; if (++loop == 16) { if (ktime_get_ns() > tmax) goto unlock; loop = 0; } } } WRITE_ONCE(tbl->last_flush, jiffies); unlock: write_unlock_bh(&tbl->lock); return shrunk; } static void neigh_add_timer(struct neighbour *n, unsigned long when) { /* Use safe distance from the jiffies - LONG_MAX point while timer * is running in DELAY/PROBE state but still show to user space * large times in the past. */ unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); neigh_hold(n); if (!time_in_range(n->confirmed, mint, jiffies)) n->confirmed = mint; if (time_before(n->used, n->confirmed)) n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); dump_stack(); } } static int neigh_del_timer(struct neighbour *n) { if ((n->nud_state & NUD_IN_TIMER) && del_timer(&n->timer)) { neigh_release(n); return 1; } return 0; } static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { struct sk_buff_head tmp; unsigned long flags; struct sk_buff *skb; skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb = skb_peek(list); while (skb != NULL) { struct sk_buff *skb_next = skb_peek_next(skb, list); if (net == NULL || net_eq(dev_net(skb->dev), net)) { __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } skb = skb_next; } spin_unlock_irqrestore(&list->lock, flags); while ((skb = __skb_dequeue(&tmp))) { dev_put(skb->dev); kfree_skb(skb); } } static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { int i; struct neigh_hash_table *nht; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { if (dev && n->dev != dev) { np = &n->next; continue; } if (skip_perm && n->nud_state & NUD_PERMANENT) { np = &n->next; continue; } rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); write_lock(&n->lock); neigh_del_timer(n); neigh_mark_dead(n); if (refcount_read(&n->refcnt) != 1) { /* The most unpleasant situation. We must destroy neighbour entry, but someone still uses it. The destroy will be delayed until the last user releases us, but we must kill timers etc. and move it to safe state. */ __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else n->nud_state = NUD_NONE; neigh_dbg(2, "neigh %p is stray\n", n); } write_unlock(&n->lock); neigh_cleanup_and_release(n); } } } void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, false); write_unlock_bh(&tbl->lock); } EXPORT_SYMBOL(neigh_changeaddr); static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; } int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev) { __neigh_ifdown(tbl, dev, true); return 0; } EXPORT_SYMBOL(neigh_carrier_down); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { __neigh_ifdown(tbl, dev, false); return 0; } EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, u8 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; int entries, gc_thresh3; if (exempt_from_gc) goto do_alloc; entries = atomic_inc_return(&tbl->gc_entries) - 1; gc_thresh3 = READ_ONCE(tbl->gc_thresh3); if (entries >= gc_thresh3 || (entries >= READ_ONCE(tbl->gc_thresh2) && time_after(now, READ_ONCE(tbl->last_flush) + 5 * HZ))) { if (!neigh_forced_gc(tbl) && entries >= gc_thresh3) { net_info_ratelimited("%s: neighbor table overflow!\n", tbl->id); NEIGH_CACHE_STAT_INC(tbl, table_fulls); goto out_entries; } } do_alloc: n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; n->flags = flags; seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); timer_setup(&n->timer, neigh_timer_handler, 0); NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); atomic_inc(&tbl->entries); out: return n; out_entries: if (!exempt_from_gc) atomic_dec(&tbl->gc_entries); goto out; } static void neigh_get_hash_rnd(u32 *x) { *x = get_random_u32() | 1; } static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) { size_t size = (1 << shift) * sizeof(struct neighbour *); struct neigh_hash_table *ret; struct neighbour __rcu **buckets; int i; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) return NULL; if (size <= PAGE_SIZE) { buckets = kzalloc(size, GFP_ATOMIC); } else { buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); kmemleak_alloc(buckets, size, 1, GFP_ATOMIC); } if (!buckets) { kfree(ret); return NULL; } ret->hash_buckets = buckets; ret->hash_shift = shift; for (i = 0; i < NEIGH_NUM_HASH_RND; i++) neigh_get_hash_rnd(&ret->hash_rnd[i]); return ret; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct neigh_hash_table *nht = container_of(head, struct neigh_hash_table, rcu); size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) { kfree(buckets); } else { kmemleak_free(buckets); free_pages((unsigned long)buckets, get_order(size)); } kfree(nht); } static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, unsigned long new_shift) { unsigned int i, hash; struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); old_nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); new_nht = neigh_hash_alloc(new_shift); if (!new_nht) return old_nht; for (i = 0; i < (1 << old_nht->hash_shift); i++) { struct neighbour *n, *next; for (n = rcu_dereference_protected(old_nht->hash_buckets[i], lockdep_is_held(&tbl->lock)); n != NULL; n = next) { hash = tbl->hash(n->primary_key, n->dev, new_nht->hash_rnd); hash >>= (32 - new_nht->hash_shift); next = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); rcu_assign_pointer(n->next, rcu_dereference_protected( new_nht->hash_buckets[hash], lockdep_is_held(&tbl->lock))); rcu_assign_pointer(new_nht->hash_buckets[hash], n); } } rcu_assign_pointer(tbl->nht, new_nht); call_rcu(&old_nht->rcu, neigh_hash_free_rcu); return new_nht; } struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n; NEIGH_CACHE_STAT_INC(tbl, lookups); rcu_read_lock_bh(); n = __neigh_lookup_noref(tbl, pkey, dev); if (n) { if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); } rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup); static struct neighbour * ___neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, u8 flags, bool exempt_from_gc, bool want_ref) { u32 hash_val, key_len = tbl->key_len; struct neighbour *n1, *rc, *n; struct neigh_hash_table *nht; int error; n = neigh_alloc(tbl, dev, flags, exempt_from_gc); trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; } memcpy(n->primary_key, pkey, key_len); n->dev = dev; dev_hold(dev); /* Protocol specific setup. */ if (tbl->constructor && (error = tbl->constructor(n)) < 0) { rc = ERR_PTR(error); goto out_neigh_release; } if (dev->netdev_ops->ndo_neigh_construct) { error = dev->netdev_ops->ndo_neigh_construct(dev, n); if (error < 0) { rc = ERR_PTR(error); goto out_neigh_release; } } /* Device specific setup. */ if (n->parms->neigh_setup && (error = n->parms->neigh_setup(n)) < 0) { rc = ERR_PTR(error); goto out_neigh_release; } n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) nht = neigh_hash_grow(tbl, nht->hash_shift + 1); hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); goto out_tbl_unlock; } for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock)); n1 != NULL; n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); rc = n1; goto out_tbl_unlock; } } n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock))); rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); neigh_dbg(2, "neigh %p is created\n", n); rc = n; out: return rc; out_tbl_unlock: write_unlock_bh(&tbl->lock); out_neigh_release: if (!exempt_from_gc) atomic_dec(&tbl->gc_entries); neigh_release(n); goto out; } struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); } EXPORT_SYMBOL(__neigh_create); static u32 pneigh_hash(const void *pkey, unsigned int key_len) { u32 hash_val = *(u32 *)(pkey + key_len - 4); hash_val ^= (hash_val >> 16); hash_val ^= hash_val >> 8; hash_val ^= hash_val >> 4; hash_val &= PNEIGH_HASHMASK; return hash_val; } static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, struct net *net, const void *pkey, unsigned int key_len, struct net_device *dev) { while (n) { if (!memcmp(n->key, pkey, key_len) && net_eq(pneigh_net(n), net) && (n->dev == dev || !n->dev)) return n; n = n->next; } return NULL; } struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); return __pneigh_lookup_1(tbl->phash_buckets[hash_val], net, pkey, key_len, dev); } EXPORT_SYMBOL_GPL(__pneigh_lookup); struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev, int creat) { struct pneigh_entry *n; unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); read_lock_bh(&tbl->lock); n = __pneigh_lookup_1(tbl->phash_buckets[hash_val], net, pkey, key_len, dev); read_unlock_bh(&tbl->lock); if (n || !creat) goto out; ASSERT_RTNL(); n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; dev_hold(dev); if (tbl->pconstructor && tbl->pconstructor(n)) { dev_put(dev); kfree(n); n = NULL; goto out; } write_lock_bh(&tbl->lock); n->next = tbl->phash_buckets[hash_val]; tbl->phash_buckets[hash_val] = n; write_unlock_bh(&tbl->lock); out: return n; } EXPORT_SYMBOL(pneigh_lookup); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { struct pneigh_entry *n, **np; unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); write_lock_bh(&tbl->lock); for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL; np = &n->next) { if (!memcmp(n->key, pkey, key_len) && n->dev == dev && net_eq(pneigh_net(n), net)) { *np = n->next; write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); dev_put(n->dev); kfree(n); return 0; } } write_unlock_bh(&tbl->lock); return -ENOENT; } static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, struct net_device *dev) { struct pneigh_entry *n, **np, *freelist = NULL; u32 h; for (h = 0; h <= PNEIGH_HASHMASK; h++) { np = &tbl->phash_buckets[h]; while ((n = *np) != NULL) { if (!dev || n->dev == dev) { *np = n->next; n->next = freelist; freelist = n; continue; } np = &n->next; } } write_unlock_bh(&tbl->lock); while ((n = freelist)) { freelist = n->next; n->next = NULL; if (tbl->pdestructor) tbl->pdestructor(n); dev_put(n->dev); kfree(n); } return -ENOENT; } static void neigh_parms_destroy(struct neigh_parms *parms); static inline void neigh_parms_put(struct neigh_parms *parms) { if (refcount_dec_and_test(&parms->refcnt)) neigh_parms_destroy(parms); } /* * neighbour must already be out of the table; * */ void neigh_destroy(struct neighbour *neigh) { struct net_device *dev = neigh->dev; NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { pr_warn("Destroying alive neighbour %p\n", neigh); dump_stack(); return; } if (neigh_del_timer(neigh)) pr_warn("Impossible event\n"); write_lock_bh(&neigh->lock); __skb_queue_purge(&neigh->arp_queue); write_unlock_bh(&neigh->lock); neigh->arp_queue_len_bytes = 0; if (dev->netdev_ops->ndo_neigh_destroy) dev->netdev_ops->ndo_neigh_destroy(dev, neigh); dev_put(dev); neigh_parms_put(neigh->parms); neigh_dbg(2, "neigh %p is destroyed\n", neigh); atomic_dec(&neigh->tbl->entries); kfree_rcu(neigh, rcu); } EXPORT_SYMBOL(neigh_destroy); /* Neighbour state is suspicious; disable fast path. Called with write_locked neigh. */ static void neigh_suspect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->output = neigh->ops->output; } /* Neighbour state is OK; enable fast path. Called with write_locked neigh. */ static void neigh_connect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is connected\n", neigh); neigh->output = neigh->ops->connected_output; } static void neigh_periodic_work(struct work_struct *work) { struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); struct neighbour *n; struct neighbour __rcu **np; unsigned int i; struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); /* * periodically recompute ReachableTime from random function */ if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { unsigned int state; write_lock(&n->lock); state = n->nud_state; if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); goto next_elt; } if (time_before(n->used, n->confirmed) && time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); next_elt: np = &n->next; } /* * It's fine to release lock here, even if hash table * grows while we are preempted. */ write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); } out: /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 * BASE_REACHABLE_TIME. */ queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) : NEIGH_VAR(p, MCAST_PROBES)); } static void neigh_invalidate(struct neighbour *neigh) __releases(neigh->lock) __acquires(neigh->lock) { struct sk_buff *skb; NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); neigh_dbg(2, "neigh %p is failed\n", neigh); neigh->updated = jiffies; /* It is very thin place. report_unreachable is very complicated routine. Particularly, it can hit the same neighbour entry! So that, we try to be accurate and avoid dead loop. --ANK */ while (neigh->nud_state == NUD_FAILED && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { write_unlock(&neigh->lock); neigh->ops->error_report(neigh, skb); write_lock(&neigh->lock); } __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } static void neigh_probe(struct neighbour *neigh) __releases(neigh->lock) { struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); if (neigh->ops->solicit) neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); consume_skb(skb); } /* Called when a timer expires for a neighbour entry. */ static void neigh_timer_handler(struct timer_list *t) { unsigned long now, next; struct neighbour *neigh = from_timer(neigh, t, timer); unsigned int state; int notify = 0; write_lock(&neigh->lock); state = neigh->nud_state; now = jiffies; next = now + HZ; if (!(state & NUD_IN_TIMER)) goto out; if (state & NUD_REACHABLE) { if (time_before_eq(now, neigh->confirmed + neigh->parms->reachable_time)) { neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, neigh->used + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; neigh->updated = jiffies; neigh_suspect(neigh); notify = 1; } } else if (state & NUD_DELAY) { if (time_before_eq(now, neigh->confirmed + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; neigh_connect(neigh); notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { neigh_dbg(2, "neigh %p is probed\n", neigh); neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); notify = 1; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); goto out; } if (neigh->nud_state & NUD_IN_TIMER) { if (time_before(next, jiffies + HZ/100)) next = jiffies + HZ/100; if (!mod_timer(&neigh->timer, next)) neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { neigh_probe(neigh); } else { out: write_unlock(&neigh->lock); } if (notify) neigh_update_notify(neigh, 0); trace_neigh_timer_handler(neigh, 0); neigh_release(neigh); } int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { int rc; bool immediate_probe = false; write_lock_bh(&neigh->lock); rc = 0; if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; if (neigh->dead) goto out_dead; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + NEIGH_VAR(neigh->parms, APP_PROBES)) { unsigned long next, now = jiffies; atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh_del_timer(neigh); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); neigh_add_timer(neigh, next); immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; write_unlock_bh(&neigh->lock); kfree_skb(skb); return 1; } } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh_del_timer(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { while (neigh->arp_queue_len_bytes + skb->truesize > NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; buff = __skb_dequeue(&neigh->arp_queue); if (!buff) break; neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } out_unlock_bh: if (immediate_probe) neigh_probe(neigh); else write_unlock(&neigh->lock); local_bh_enable(); trace_neigh_event_send_done(neigh, rc); return rc; out_dead: if (neigh->nud_state & NUD_STALE) goto out_unlock_bh; write_unlock_bh(&neigh->lock); kfree_skb(skb); trace_neigh_event_send_dead(neigh, 1); return 1; } EXPORT_SYMBOL(__neigh_event_send); static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) = NULL; if (neigh->dev->header_ops) update = neigh->dev->header_ops->cache_update; if (update) { hh = &neigh->hh; if (READ_ONCE(hh->hh_len)) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); } } } /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. -- flags NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr, if it is different. NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected" lladdr instead of overriding it if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. NEIGH_UPDATE_F_USE means that the entry is user triggered. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as a router. Caller MUST hold reference count on the entry. */ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { bool ext_learn_change = false; u8 old; int err; int notify = 0; struct net_device *dev; int update_isrouter = 0; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); write_lock_bh(&neigh->lock); dev = neigh->dev; old = neigh->nud_state; err = -EPERM; if (neigh->dead) { NL_SET_ERR_MSG(extack, "Neighbor entry is now dead"); new = old; goto out; } if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); if (flags & NEIGH_UPDATE_F_USE) { new = old & ~NUD_PERMANENT; neigh->nud_state = new; err = 0; goto out; } if (!(new & NUD_VALID)) { neigh_del_timer(neigh); if (old & NUD_CONNECTED) neigh_suspect(neigh); neigh->nud_state = new; err = 0; notify = old & NUD_VALID; if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && (new & NUD_FAILED)) { neigh_invalidate(neigh); notify = 1; } goto out; } /* Compare new lladdr with cached one */ if (!dev->addr_len) { /* First case: device needs no address. */ lladdr = neigh->ha; } else if (lladdr) { /* The second case: if something is already cached and a new address is proposed: - compare new & old - if they are different, check override flag */ if ((old & NUD_VALID) && !memcmp(lladdr, neigh->ha, dev->addr_len)) lladdr = neigh->ha; } else { /* No address is supplied; if we know something, use it, otherwise discard the request. */ err = -EINVAL; if (!(old & NUD_VALID)) { NL_SET_ERR_MSG(extack, "No link layer address given"); goto out; } lladdr = neigh->ha; } /* Update confirmed timestamp for neighbour entry after we * received ARP packet even if it doesn't change IP to MAC binding. */ if (new & NUD_CONNECTED) neigh->confirmed = jiffies; /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ err = 0; update_isrouter = flags & NEIGH_UPDATE_F_OVERRIDE_ISROUTER; if (old & NUD_VALID) { if (lladdr != neigh->ha && !(flags & NEIGH_UPDATE_F_OVERRIDE)) { update_isrouter = 0; if ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) && (old & NUD_CONNECTED)) { lladdr = neigh->ha; new = NUD_STALE; } else goto out; } else { if (lladdr == neigh->ha && new == NUD_STALE && !(flags & NEIGH_UPDATE_F_ADMIN)) new = old; } } /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; if (new != old) { neigh_del_timer(neigh); if (new & NUD_PROBE) atomic_set(&neigh->probes, 0); if (new & NUD_IN_TIMER) neigh_add_timer(neigh, (jiffies + ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); neigh->nud_state = new; notify = 1; } if (lladdr != neigh->ha) { write_seqlock(&neigh->ha_lock); memcpy(&neigh->ha, lladdr, dev->addr_len); write_sequnlock(&neigh->ha_lock); neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) goto out; if (new & NUD_CONNECTED) neigh_connect(neigh); else neigh_suspect(neigh); if (!(old & NUD_VALID)) { struct sk_buff *skb; /* Again: avoid dead loop if something went wrong */ while (neigh->nud_state & NUD_VALID && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { struct dst_entry *dst = skb_dst(skb); struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); rcu_read_lock(); /* Why not just use 'neigh' as-is? The problem is that * things such as shaper, eql, and sch_teql can end up * using alternative, different, neigh objects to output * the packet in the output path. So what we need to do * here is re-lookup the top-level neigh in the path so * we can reinject the packet there. */ n2 = NULL; if (dst && dst->obsolete != DST_OBSOLETE_DEAD) { n2 = dst_neigh_lookup_skb(dst, skb); if (n2) n1 = n2; } n1->output(n1, skb); if (n2) neigh_release(n2); rcu_read_unlock(); write_lock_bh(&neigh->lock); } __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) neigh_update_gc_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); trace_neigh_update_done(neigh, err); return err; } int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid) { return __neigh_update(neigh, lladdr, new, flags, nlmsg_pid, NULL); } EXPORT_SYMBOL(neigh_update); /* Update the neigh to listen temporarily for probe responses, even if it is * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. */ void __neigh_set_probe_once(struct neighbour *neigh) { if (neigh->dead) return; neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; neigh->nud_state = NUD_INCOMPLETE; atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100)); } EXPORT_SYMBOL(__neigh_set_probe_once); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) { struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev, lladdr || !dev->addr_len); if (neigh) neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_OVERRIDE, 0); return neigh; } EXPORT_SYMBOL(neigh_event_ns); /* called with read_lock_bh(&n->lock); */ static void neigh_hh_init(struct neighbour *n) { struct net_device *dev = n->dev; __be16 prot = n->tbl->protocol; struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); /* Only one thread can come in here and initialize the * hh_cache entry. */ if (!hh->hh_len) dev->header_ops->cache(n, hh, prot); write_unlock_bh(&n->lock); } /* Slow and careful. */ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { int rc = 0; if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; unsigned int seq; if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len)) neigh_hh_init(neigh); do { __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) rc = dev_queue_xmit(skb); else goto out_kfree_skb; } out: return rc; out_kfree_skb: rc = -EINVAL; kfree_skb(skb); goto out; } EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) { struct net_device *dev = neigh->dev; unsigned int seq; int err; do { __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) err = dev_queue_xmit(skb); else { err = -EINVAL; kfree_skb(skb); } return err; } EXPORT_SYMBOL(neigh_connected_output); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) { return dev_queue_xmit(skb); } EXPORT_SYMBOL(neigh_direct_output); static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); long sched_next = 0; unsigned long now = jiffies; struct sk_buff *skb, *n; spin_lock(&tbl->proxy_queue.lock); skb_queue_walk_safe(&tbl->proxy_queue, skb, n) { long tdif = NEIGH_CB(skb)->sched_next - now; if (tdif <= 0) { struct net_device *dev = skb->dev; __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) { rcu_read_lock(); tbl->proxy_redo(skb); rcu_read_unlock(); } else { kfree_skb(skb); } dev_put(dev); } else if (!sched_next || tdif < sched_next) sched_next = tdif; } del_timer(&tbl->proxy_timer); if (sched_next) mod_timer(&tbl->proxy_timer, jiffies + sched_next); spin_unlock(&tbl->proxy_queue.lock); } void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long sched_next = jiffies + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY)); if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } NEIGH_CB(skb)->sched_next = sched_next; NEIGH_CB(skb)->flags |= LOCALLY_ENQUEUED; spin_lock(&tbl->proxy_queue.lock); if (del_timer(&tbl->proxy_timer)) { if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } EXPORT_SYMBOL(pneigh_enqueue); static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, struct net *net, int ifindex) { struct neigh_parms *p; list_for_each_entry(p, &tbl->parms_list, list) { if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || (!p->dev && !ifindex && net_eq(net, &init_net))) return p; } return NULL; } struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { struct neigh_parms *p; struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { dev_put(dev); kfree(p); return NULL; } write_lock_bh(&tbl->lock); list_add(&p->list, &tbl->parms.list); write_unlock_bh(&tbl->lock); neigh_parms_data_state_cleanall(p); } return p; } EXPORT_SYMBOL(neigh_parms_alloc); static void neigh_rcu_free_parms(struct rcu_head *head) { struct neigh_parms *parms = container_of(head, struct neigh_parms, rcu_head); neigh_parms_put(parms); } void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) { if (!parms || parms == &tbl->parms) return; write_lock_bh(&tbl->lock); list_del(&parms->list); parms->dead = 1; write_unlock_bh(&tbl->lock); dev_put(parms->dev); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } EXPORT_SYMBOL(neigh_parms_release); static void neigh_parms_destroy(struct neigh_parms *parms) { kfree(parms); } static struct lock_class_key neigh_table_proxy_queue_class; static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly; void neigh_table_init(int index, struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); #ifdef CONFIG_PROC_FS if (!proc_create_seq_data(tbl->id, 0, init_net.proc_net_stat, &neigh_stat_seq_ops, tbl)) panic("cannot create neighbour proc dir entry"); #endif RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); if (!tbl->entry_size) tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + tbl->key_len, NEIGH_PRIV_ALIGN); else WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; neigh_tables[index] = tbl; } EXPORT_SYMBOL(neigh_table_init); int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, neigh_hash_free_rcu); tbl->nht = NULL; kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; remove_proc_entry(tbl->id, init_net.proc_net_stat); free_percpu(tbl->stats); tbl->stats = NULL; return 0; } EXPORT_SYMBOL(neigh_table_clear); static struct neigh_table *neigh_find_table(int family) { struct neigh_table *tbl = NULL; switch (family) { case AF_INET: tbl = neigh_tables[NEIGH_ARP_TABLE]; break; case AF_INET6: tbl = neigh_tables[NEIGH_ND_TABLE]; break; } return tbl; } const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_UNSPEC] = { .strict_start_type = NDA_NH_ID }, [NDA_DST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_CACHEINFO] = { .len = sizeof(struct nda_cacheinfo) }, [NDA_PROBES] = { .type = NLA_U32 }, [NDA_VLAN] = { .type = NLA_U16 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_IFINDEX] = { .type = NLA_U32 }, [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *dst_attr; struct neigh_table *tbl; struct neighbour *neigh; struct net_device *dev = NULL; int err = -EINVAL; ASSERT_RTNL(); if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); if (!dst_attr) { NL_SET_ERR_MSG(extack, "Network address not specified"); goto out; } ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } } tbl = neigh_find_table(ndm->ndm_family); if (tbl == NULL) return -EAFNOSUPPORT; if (nla_len(dst_attr) < (int)tbl->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address"); goto out; } if (ndm->ndm_flags & NTF_PROXY) { err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); goto out; } if (dev == NULL) goto out; neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); if (neigh == NULL) { err = -ENOENT; goto out; } err = __neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid, extack); write_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh, tbl); write_unlock_bh(&tbl->lock); out: return err; } static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; int err; ASSERT_RTNL(); err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, nda_policy, extack); if (err < 0) goto out; err = -EINVAL; if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Network address not specified"); goto out; } ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) { NL_SET_ERR_MSG(extack, "Invalid link address"); goto out; } } tbl = neigh_find_table(ndm->ndm_family); if (tbl == NULL) return -EAFNOSUPPORT; if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address"); goto out; } dst = nla_data(tb[NDA_DST]); lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); if (ndm->ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { pn->flags = ndm->ndm_flags; if (protocol) pn->protocol = protocol; err = 0; } goto out; } if (!dev) { NL_SET_ERR_MSG(extack, "Device not specified"); goto out; } if (tbl->allow_add && !tbl->allow_add(dev, extack)) { err = -EINVAL; goto out; } neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { bool exempt_from_gc; if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; goto out; } exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || ndm->ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, ndm->ndm_flags & NTF_EXT_LEARNED, exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); goto out; } } else { if (nlh->nlmsg_flags & NLM_F_EXCL) { err = -EEXIST; neigh_release(neigh); goto out; } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) flags &= ~(NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } if (protocol) neigh->protocol = protocol; if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; if (ndm->ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; if (ndm->ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); if (!err && ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; } neigh_release(neigh); out: return err; } static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, NDTA_PARMS); if (nest == NULL) return -ENOBUFS; if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) || nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || nla_put_u32(skb, NDTPA_UCAST_PROBES, NEIGH_VAR(parms, UCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_PROBES, NEIGH_VAR(parms, MCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_REPROBES, NEIGH_VAR(parms, MCAST_REPROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time, NDTPA_PAD) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, NEIGH_VAR(parms, BASE_REACHABLE_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_GC_STALETIME, NEIGH_VAR(parms, GC_STALETIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, NEIGH_VAR(parms, DELAY_PROBE_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_RETRANS_TIME, NEIGH_VAR(parms, RETRANS_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, NEIGH_VAR(parms, ANYCAST_DELAY), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_PROXY_DELAY, NEIGH_VAR(parms, PROXY_DELAY), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_LOCKTIME, NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); if (nlh == NULL) return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) || nla_put_msecs(skb, NDTA_GC_INTERVAL, READ_ONCE(tbl->gc_interval), NDTA_PAD) || nla_put_u32(skb, NDTA_THRESH1, READ_ONCE(tbl->gc_thresh1)) || nla_put_u32(skb, NDTA_THRESH2, READ_ONCE(tbl->gc_thresh2)) || nla_put_u32(skb, NDTA_THRESH3, READ_ONCE(tbl->gc_thresh3))) goto nla_put_failure; { unsigned long now = jiffies; long flush_delta = now - READ_ONCE(tbl->last_flush); long rand_delta = now - READ_ONCE(tbl->last_rand); struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, .ndtc_entry_size = tbl->entry_size, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); ndc.ndtc_hash_rnd = nht->hash_rnd[0]; ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) goto nla_put_failure; } { int cpu; struct ndt_stats ndst; memset(&ndst, 0, sizeof(ndst)); for_each_possible_cpu(cpu) { struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); ndst.ndts_allocs += READ_ONCE(st->allocs); ndst.ndts_destroys += READ_ONCE(st->destroys); ndst.ndts_hash_grows += READ_ONCE(st->hash_grows); ndst.ndts_res_failed += READ_ONCE(st->res_failed); ndst.ndts_lookups += READ_ONCE(st->lookups); ndst.ndts_hits += READ_ONCE(st->hits); ndst.ndts_rcv_probes_mcast += READ_ONCE(st->rcv_probes_mcast); ndst.ndts_rcv_probes_ucast += READ_ONCE(st->rcv_probes_ucast); ndst.ndts_periodic_gc_runs += READ_ONCE(st->periodic_gc_runs); ndst.ndts_forced_gc_runs += READ_ONCE(st->forced_gc_runs); ndst.ndts_table_fulls += READ_ONCE(st->table_fulls); } if (nla_put_64bit(skb, NDTA_STATS, sizeof(ndst), &ndst, NDTA_PAD)) goto nla_put_failure; } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) goto nla_put_failure; read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; nla_put_failure: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int neightbl_fill_param_info(struct sk_buff *skb, struct neigh_table *tbl, struct neigh_parms *parms, u32 pid, u32 seq, int type, unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); if (nlh == NULL) return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || neightbl_fill_parms(skb, parms) < 0) goto errout; read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; errout: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { [NDTA_NAME] = { .type = NLA_STRING }, [NDTA_THRESH1] = { .type = NLA_U32 }, [NDTA_THRESH2] = { .type = NLA_U32 }, [NDTA_THRESH3] = { .type = NLA_U32 }, [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, [NDTA_PARMS] = { .type = NLA_NESTED }, }; static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 }, [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, [NDTPA_LOCKTIME] = { .type = NLA_U64 }, }; static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct neigh_table *tbl; struct ndtmsg *ndtmsg; struct nlattr *tb[NDTA_MAX+1]; bool found = false; int err, tidx; err = nlmsg_parse_deprecated(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, nl_neightbl_policy, extack); if (err < 0) goto errout; if (tb[NDTA_NAME] == NULL) { err = -EINVAL; goto errout; } ndtmsg = nlmsg_data(nlh); for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { tbl = neigh_tables[tidx]; if (!tbl) continue; if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) { found = true; break; } } if (!found) return -ENOENT; /* * We acquire tbl->lock to be nice to the periodic timers and * make sure they always see a consistent set of values. */ write_lock_bh(&tbl->lock); if (tb[NDTA_PARMS]) { struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; int i, ifindex = 0; err = nla_parse_nested_deprecated(tbp, NDTPA_MAX, tb[NDTA_PARMS], nl_ntbl_parm_policy, extack); if (err < 0) goto errout_tbl_lock; if (tbp[NDTPA_IFINDEX]) ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); p = lookup_neigh_parms(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; goto errout_tbl_lock; } for (i = 1; i <= NDTPA_MAX; i++) { if (tbp[i] == NULL) continue; switch (i) { case NDTPA_QUEUE_LEN: NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, nla_get_u32(tbp[i]) * SKB_TRUESIZE(ETH_FRAME_LEN)); break; case NDTPA_QUEUE_LENBYTES: NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: NEIGH_VAR_SET(p, PROXY_QLEN, nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: NEIGH_VAR_SET(p, APP_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: NEIGH_VAR_SET(p, UCAST_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: NEIGH_VAR_SET(p, MCAST_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_MCAST_REPROBES: NEIGH_VAR_SET(p, MCAST_REPROBES, nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, nla_get_msecs(tbp[i])); /* update reachable_time as well, otherwise, the change will * only be effective after the next time neigh_periodic_work * decides to recompute it (can be multiple minutes) */ p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); break; case NDTPA_GC_STALETIME: NEIGH_VAR_SET(p, GC_STALETIME, nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: NEIGH_VAR_SET(p, DELAY_PROBE_TIME, nla_get_msecs(tbp[i])); call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); break; case NDTPA_RETRANS_TIME: NEIGH_VAR_SET(p, RETRANS_TIME, nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: NEIGH_VAR_SET(p, ANYCAST_DELAY, nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: NEIGH_VAR_SET(p, PROXY_DELAY, nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: NEIGH_VAR_SET(p, LOCKTIME, nla_get_msecs(tbp[i])); break; } } } err = -ENOENT; if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) && !net_eq(net, &init_net)) goto errout_tbl_lock; if (tb[NDTA_THRESH1]) WRITE_ONCE(tbl->gc_thresh1, nla_get_u32(tb[NDTA_THRESH1])); if (tb[NDTA_THRESH2]) WRITE_ONCE(tbl->gc_thresh2, nla_get_u32(tb[NDTA_THRESH2])); if (tb[NDTA_THRESH3]) WRITE_ONCE(tbl->gc_thresh3, nla_get_u32(tb[NDTA_THRESH3])); if (tb[NDTA_GC_INTERVAL]) WRITE_ONCE(tbl->gc_interval, nla_get_msecs(tb[NDTA_GC_INTERVAL])); err = 0; errout_tbl_lock: write_unlock_bh(&tbl->lock); errout: return err; } static int neightbl_valid_dump_info(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ndtmsg *ndtm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndtm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor table dump request"); return -EINVAL; } ndtm = nlmsg_data(nlh); if (ndtm->ndtm_pad1 || ndtm->ndtm_pad2) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor table dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ndtm))) { NL_SET_ERR_MSG(extack, "Invalid data after header in neighbor table dump request"); return -EINVAL; } return 0; } static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; int neigh_skip = cb->args[1]; struct neigh_table *tbl; if (cb->strict_check) { int err = neightbl_valid_dump_info(nlh, cb->extack); if (err < 0) return err; } family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { struct neigh_parms *p; tbl = neigh_tables[tidx]; if (!tbl) continue; if (tidx < tbl_skip || (family && tbl->family != family)) continue; if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) < 0) break; nidx = 0; p = list_next_entry(&tbl->parms, list); list_for_each_entry_from(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) continue; if (nidx < neigh_skip) goto next; if (neightbl_fill_param_info(skb, tbl, p, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) < 0) goto out; next: nidx++; } neigh_skip = 0; } out: cb->args[0] = tidx; cb->args[1] = nidx; return skb->len; } static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = neigh->flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key)) goto nla_put_failure; read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; if (neigh->nud_state & NUD_VALID) { char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, neigh, neigh->dev); if (nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, haddr) < 0) { read_unlock_bh(&neigh->lock); goto nla_put_failure; } } ci.ndm_used = jiffies_to_clock_t(now - neigh->used); ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); ci.ndm_refcnt = refcount_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { struct nlmsghdr *nlh; struct ndmsg *ndm; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = pn->flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid) { call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); __neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid); } static bool neigh_master_filtered(struct net_device *dev, int master_idx) { struct net_device *master; if (!master_idx) return false; master = dev ? netdev_master_upper_dev_get(dev) : NULL; /* 0 is already used to denote NDA_MASTER wasn't passed, therefore need another * invalid value for ifindex to denote "no master". */ if (master_idx == -1) return !!master; if (!master || master->ifindex != master_idx) return true; return false; } static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) { if (filter_idx && (!dev || dev->ifindex != filter_idx)) return true; return false; } struct neigh_dump_filter { int master_idx; int dev_idx; }; static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb, struct neigh_dump_filter *filter) { struct net *net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; unsigned int flags = NLM_F_MULTI; if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; n != NULL; n = rcu_dereference_bh(n->next)) { if (idx < s_idx || !net_eq(dev_net(n->dev), net)) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, flags) < 0) { rc = -1; goto out; } next: idx++; } } rc = skb->len; out: rcu_read_unlock_bh(); cb->args[1] = h; cb->args[2] = idx; return rc; } static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb, struct neigh_dump_filter *filter) { struct pneigh_entry *n; struct net *net = sock_net(skb->sk); int rc, h, s_h = cb->args[3]; int idx, s_idx = idx = cb->args[4]; unsigned int flags = NLM_F_MULTI; if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; read_lock_bh(&tbl->lock); for (h = s_h; h <= PNEIGH_HASHMASK; h++) { if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { if (idx < s_idx || pneigh_net(n) != net) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, flags, tbl) < 0) { read_unlock_bh(&tbl->lock); rc = -1; goto out; } next: idx++; } } read_unlock_bh(&tbl->lock); rc = skb->len; out: cb->args[3] = h; cb->args[4] = idx; return rc; } static int neigh_valid_dump_req(const struct nlmsghdr *nlh, bool strict_check, struct neigh_dump_filter *filter, struct netlink_ext_ack *extack) { struct nlattr *tb[NDA_MAX + 1]; int err, i; if (strict_check) { struct ndmsg *ndm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor dump request"); return -EINVAL; } ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex || ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request"); return -EINVAL; } if (ndm->ndm_flags & ~NTF_PROXY) { NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor dump request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); } else { err = nlmsg_parse_deprecated(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); } if (err < 0) return err; for (i = 0; i <= NDA_MAX; ++i) { if (!tb[i]) continue; /* all new attributes should require strict_check */ switch (i) { case NDA_IFINDEX: filter->dev_idx = nla_get_u32(tb[i]); break; case NDA_MASTER: filter->master_idx = nla_get_u32(tb[i]); break; default: if (strict_check) { NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor dump request"); return -EINVAL; } } } return 0; } static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct neigh_dump_filter filter = {}; struct neigh_table *tbl; int t, family, s_t; int proxy = 0; int err; family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; /* check for full ndmsg structure presence, family member is * the same for both structures */ if (nlmsg_len(nlh) >= sizeof(struct ndmsg) && ((struct ndmsg *)nlmsg_data(nlh))->ndm_flags == NTF_PROXY) proxy = 1; err = neigh_valid_dump_req(nlh, cb->strict_check, &filter, cb->extack); if (err < 0 && cb->strict_check) return err; s_t = cb->args[0]; for (t = 0; t < NEIGH_NR_TABLES; t++) { tbl = neigh_tables[t]; if (!tbl) continue; if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (proxy) err = pneigh_dump_table(tbl, skb, cb, &filter); else err = neigh_dump_table(tbl, skb, cb, &filter); if (err < 0) break; } cb->args[0] = t; return skb->len; } static int neigh_valid_get_req(const struct nlmsghdr *nlh, struct neigh_table **tbl, void **dst, int *dev_idx, u8 *ndm_flags, struct netlink_ext_ack *extack) { struct nlattr *tb[NDA_MAX + 1]; struct ndmsg *ndm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request"); return -EINVAL; } ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request"); return -EINVAL; } if (ndm->ndm_flags & ~NTF_PROXY) { NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); if (err < 0) return err; *ndm_flags = ndm->ndm_flags; *dev_idx = ndm->ndm_ifindex; *tbl = neigh_find_table(ndm->ndm_family); if (*tbl == NULL) { NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request"); return -EAFNOSUPPORT; } for (i = 0; i <= NDA_MAX; ++i) { if (!tb[i]) continue; switch (i) { case NDA_DST: if (nla_len(tb[i]) != (int)(*tbl)->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request"); return -EINVAL; } *dst = nla_data(tb[i]); break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor get request"); return -EINVAL; } } return 0; } static inline size_t neigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + nla_total_size(1); /* NDA_PROTOCOL */ } static int neigh_get_reply(struct net *net, struct neighbour *neigh, u32 pid, u32 seq) { struct sk_buff *skb; int err = 0; skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0); if (err) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, pid); errout: return err; } static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + nla_total_size(1); /* NDA_PROTOCOL */ } static int pneigh_get_reply(struct net *net, struct pneigh_entry *neigh, u32 pid, u32 seq, struct neigh_table *tbl) { struct sk_buff *skb; int err = 0; skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = pneigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0, tbl); if (err) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, pid); errout: return err; } static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct net_device *dev = NULL; struct neigh_table *tbl = NULL; struct neighbour *neigh; void *dst = NULL; u8 ndm_flags = 0; int dev_idx = 0; int err; err = neigh_valid_get_req(nlh, &tbl, &dst, &dev_idx, &ndm_flags, extack); if (err < 0) return err; if (dev_idx) { dev = __dev_get_by_index(net, dev_idx); if (!dev) { NL_SET_ERR_MSG(extack, "Unknown device ifindex"); return -ENODEV; } } if (!dst) { NL_SET_ERR_MSG(extack, "Network address not specified"); return -EINVAL; } if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; pn = pneigh_lookup(tbl, net, dst, dev, 0); if (!pn) { NL_SET_ERR_MSG(extack, "Proxy neighbour entry not found"); return -ENOENT; } return pneigh_get_reply(net, pn, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, tbl); } if (!dev) { NL_SET_ERR_MSG(extack, "No device specified"); return -EINVAL; } neigh = neigh_lookup(tbl, dst, dev); if (!neigh) { NL_SET_ERR_MSG(extack, "Neighbour entry not found"); return -ENOENT; } err = neigh_get_reply(net, neigh, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); neigh_release(neigh); return err; } void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie) { int chain; struct neigh_hash_table *nht; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); /* avoid resizes */ for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; for (n = rcu_dereference_bh(nht->hash_buckets[chain]); n != NULL; n = rcu_dereference_bh(n->next)) cb(n, cookie); } read_unlock(&tbl->lock); rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_for_each); /* The tbl->lock must be held as a writer and BH disabled. */ void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { int chain; struct neigh_hash_table *nht; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; struct neighbour __rcu **np; np = &nht->hash_buckets[chain]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { int release; write_lock(&n->lock); release = cb(n); if (release) { rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); } else np = &n->next; write_unlock(&n->lock); if (release) neigh_cleanup_and_release(n); } } } EXPORT_SYMBOL(__neigh_for_each_release); int neigh_xmit(int index, struct net_device *dev, const void *addr, struct sk_buff *skb) { int err = -EAFNOSUPPORT; if (likely(index < NEIGH_NR_TABLES)) { struct neigh_table *tbl; struct neighbour *neigh; tbl = neigh_tables[index]; if (!tbl) goto out; rcu_read_lock_bh(); if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); neigh = __ipv4_neigh_lookup_noref(dev, key); } else { neigh = __neigh_lookup_noref(tbl, addr, dev); } if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); if (IS_ERR(neigh)) { rcu_read_unlock_bh(); goto out_kfree_skb; } err = neigh->output(neigh, skb); rcu_read_unlock_bh(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), addr, NULL, skb->len); if (err < 0) goto out_kfree_skb; err = dev_queue_xmit(skb); } out: return err; out_kfree_skb: kfree_skb(skb); goto out; } EXPORT_SYMBOL(neigh_xmit); #ifdef CONFIG_PROC_FS static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; int bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { if (!net_eq(dev_net(n->dev), net)) goto next; if (state->neigh_sub_iter) { loff_t fakep = 0; void *v; v = state->neigh_sub_iter(state, n, &fakep); if (!v) goto next; } if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; if (n->nud_state & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); } if (n) break; } state->bucket = bucket; return n; } static struct neighbour *neigh_get_next(struct seq_file *seq, struct neighbour *n, loff_t *pos) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; } n = rcu_dereference_bh(n->next); while (1) { while (n) { if (!net_eq(dev_net(n->dev), net)) goto next; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; goto next; } if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; if (n->nud_state & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); } if (n) break; if (++state->bucket >= (1 << nht->hash_shift)) break; n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); } if (n && pos) --(*pos); return n; } static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) { struct neighbour *n = neigh_get_first(seq); if (n) { --(*pos); while (*pos) { n = neigh_get_next(seq, n, pos); if (!n) break; } } return *pos ? NULL : n; } static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; int bucket; state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { pn = tbl->phash_buckets[bucket]; while (pn && !net_eq(pneigh_net(pn), net)) pn = pn->next; if (pn) break; } state->bucket = bucket; return pn; } static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct pneigh_entry *pn, loff_t *pos) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; do { pn = pn->next; } while (pn && !net_eq(pneigh_net(pn), net)); while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; pn = tbl->phash_buckets[state->bucket]; while (pn && !net_eq(pneigh_net(pn), net)) pn = pn->next; if (pn) break; } if (pn && pos) --(*pos); return pn; } static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos) { struct pneigh_entry *pn = pneigh_get_first(seq); if (pn) { --(*pos); while (*pos) { pn = pneigh_get_next(seq, pn, pos); if (!pn) break; } } return *pos ? NULL : pn; } static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; void *rc; loff_t idxpos = *pos; rc = neigh_get_idx(seq, &idxpos); if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY)) rc = pneigh_get_idx(seq, &idxpos); return rc; } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) __acquires(tbl->lock) __acquires(rcu_bh) { struct neigh_seq_state *state = seq->private; state->tbl = tbl; state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); rcu_read_lock_bh(); state->nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } EXPORT_SYMBOL(neigh_seq_start); void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct neigh_seq_state *state; void *rc; if (v == SEQ_START_TOKEN) { rc = neigh_get_first(seq); goto out; } state = seq->private; if (!(state->flags & NEIGH_SEQ_IS_PNEIGH)) { rc = neigh_get_next(seq, v, NULL); if (rc) goto out; if (!(state->flags & NEIGH_SEQ_NEIGH_ONLY)) rc = pneigh_get_first(seq); } else { BUG_ON(state->flags & NEIGH_SEQ_NEIGH_ONLY); rc = pneigh_get_next(seq, v, NULL); } out: ++(*pos); return rc; } EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) __releases(tbl->lock) __releases(rcu_bh) { struct neigh_seq_state *state = seq->private; struct neigh_table *tbl = state->tbl; read_unlock(&tbl->lock); rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_seq_stop); /* statistics via seq_file */ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } return NULL; } static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } (*pos)++; return NULL; } static void neigh_stat_seq_stop(struct seq_file *seq, void *v) { } static int neigh_stat_seq_show(struct seq_file *seq, void *v) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " "%08lx %08lx %08lx " "%08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, st->destroys, st->hash_grows, st->lookups, st->hits, st->res_failed, st->rcv_probes_mcast, st->rcv_probes_ucast, st->periodic_gc_runs, st->forced_gc_runs, st->unres_discards, st->table_fulls ); return 0; } static const struct seq_operations neigh_stat_seq_ops = { .start = neigh_stat_seq_start, .next = neigh_stat_seq_next, .stop = neigh_stat_seq_stop, .show = neigh_stat_seq_show, }; #endif /* CONFIG_PROC_FS */ static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid) { struct net *net = dev_net(n->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = neigh_fill_info(skb, n, pid, 0, type, flags); if (err < 0) { /* -EMSGSIZE implies BUG in neigh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } void neigh_app_ns(struct neighbour *n) { __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0); } EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); static int proc_unres_qlen(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int size, ret; struct ctl_table tmp = *ctl; tmp.extra1 = SYSCTL_ZERO; tmp.extra2 = &unres_qlen_max; tmp.data = &size; size = *(int *)ctl->data / SKB_TRUESIZE(ETH_FRAME_LEN); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); return ret; } static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, int family) { switch (family) { case AF_INET: return __in_dev_arp_parms_get_rcu(dev); case AF_INET6: return __in6_dev_nd_parms_get_rcu(dev); } return NULL; } static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) { struct net_device *dev; int family = neigh_parms_family(p); rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct neigh_parms *dst_p = neigh_get_dev_parms_rcu(dev, family); if (dst_p && !test_bit(index, dst_p->data_state)) dst_p->data[index] = p->data[index]; } rcu_read_unlock(); } static void neigh_proc_update(struct ctl_table *ctl, int write) { struct net_device *dev = ctl->extra1; struct neigh_parms *p = ctl->extra2; struct net *net = neigh_parms_net(p); int index = (int *) ctl->data - p->data; if (!write) return; set_bit(index, p->data_state); if (index == NEIGH_VAR_DELAY_PROBE_TIME) call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); if (!dev) /* NULL dev means this is default value */ neigh_copy_dflt_parms(net, p, index); } static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp = *ctl; int ret; tmp.extra1 = SYSCTL_ZERO; tmp.extra2 = SYSCTL_INT_MAX; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec); int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct neigh_parms *p = ctl->extra2; int ret; if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0) { /* update reachable_time as well, otherwise, the change will * only be effective after the next time neigh_periodic_work * decides to recompute it */ p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } return ret; } #define NEIGH_PARMS_DATA_OFFSET(index) \ (&((struct neigh_parms *) 0)->data[index]) #define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ [NEIGH_VAR_ ## attr] = { \ .procname = name, \ .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ } #define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) #define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) #define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) #define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) #define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *handler) { int i; struct neigh_sysctl_table *t; const char *dev_name_source; char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; t->neigh_vars[i].extra2 = p; } if (dev) { dev_name_source = dev->name; /* Terminate the table early */ memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { struct neigh_table *tbl = p->tbl; dev_name_source = "default"; t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval; t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1; t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2; t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3; } if (handler) { /* RetransTime */ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; /* RetransTime (in milliseconds)*/ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; } else { /* Those handlers will update p->reachable_time after * base_reachable_time(_ms) is set to ensure the new timer starts being * applied after the next neighbour update instead of waiting for * neigh_periodic_work to update its value (can be multiple minutes) * So any handler that replaces them should do this as well */ /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = neigh_proc_base_reachable_time; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = neigh_proc_base_reachable_time; } /* Don't export sysctls to unprivileged users */ if (neigh_parms_net(p)->user_ns != &init_user_ns) t->neigh_vars[0].procname = NULL; switch (neigh_parms_family(p)) { case AF_INET: p_name = "ipv4"; break; case AF_INET6: p_name = "ipv6"; break; default: BUG(); } snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars); if (!t->sysctl_header) goto free; p->sysctl_table = t; return 0; free: kfree(t); err: return -ENOBUFS; } EXPORT_SYMBOL(neigh_sysctl_register); void neigh_sysctl_unregister(struct neigh_parms *p) { if (p->sysctl_table) { struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } EXPORT_SYMBOL(neigh_sysctl_unregister); #endif /* CONFIG_SYSCTL */ static int __init neigh_init(void) { rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, 0); rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, 0); rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, 0); return 0; } subsys_initcall(neigh_init); |
| 1 1 5 5 9 9 5 5 5 5 5 2 5 5 2 5 1 2 1 4 1 4 1 5 5 5 5 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 ethtool hooks for cfg80211 * * Copied from cfg.c - originally * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2014 Intel Corporation (Author: Johannes Berg) * Copyright (C) 2018 Intel Corporation */ #include <linux/types.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "sta_info.h" #include "driver-ops.h" static int ieee80211_set_ringparam(struct net_device *dev, struct ethtool_ringparam *rp) { struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0) return -EINVAL; return drv_set_ringparam(local, rp->tx_pending, rp->rx_pending); } static void ieee80211_get_ringparam(struct net_device *dev, struct ethtool_ringparam *rp) { struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); memset(rp, 0, sizeof(*rp)); drv_get_ringparam(local, &rp->tx_pending, &rp->tx_max_pending, &rp->rx_pending, &rp->rx_max_pending); } static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { "rx_packets", "rx_bytes", "rx_duplicates", "rx_fragments", "rx_dropped", "tx_packets", "tx_bytes", "tx_filtered", "tx_retry_failed", "tx_retries", "sta_state", "txrate", "rxrate", "signal", "channel", "noise", "ch_time", "ch_time_busy", "ch_time_ext_busy", "ch_time_rx", "ch_time_tx" }; #define STA_STATS_LEN ARRAY_SIZE(ieee80211_gstrings_sta_stats) static int ieee80211_get_sset_count(struct net_device *dev, int sset) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); int rv = 0; if (sset == ETH_SS_STATS) rv += STA_STATS_LEN; rv += drv_get_et_sset_count(sdata, sset); if (rv == 0) return -EOPNOTSUPP; return rv; } static void ieee80211_get_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *channel; struct sta_info *sta; struct ieee80211_local *local = sdata->local; struct station_info sinfo; struct survey_info survey; int i, q; #define STA_STATS_SURVEY_LEN 7 memset(data, 0, sizeof(u64) * STA_STATS_LEN); #define ADD_STA_STATS(sta) \ do { \ data[i++] += sta->rx_stats.packets; \ data[i++] += sta->rx_stats.bytes; \ data[i++] += sta->rx_stats.num_duplicates; \ data[i++] += sta->rx_stats.fragments; \ data[i++] += sta->rx_stats.dropped; \ \ data[i++] += sinfo.tx_packets; \ data[i++] += sinfo.tx_bytes; \ data[i++] += sta->status_stats.filtered; \ data[i++] += sta->status_stats.retry_failed; \ data[i++] += sta->status_stats.retry_count; \ } while (0) /* For Managed stations, find the single station based on BSSID * and use that. For interface types, iterate through all available * stations and add stats for any station that is assigned to this * network device. */ mutex_lock(&local->sta_mtx); if (sdata->vif.type == NL80211_IFTYPE_STATION) { sta = sta_info_get_bss(sdata, sdata->u.mgd.bssid); if (!(sta && !WARN_ON(sta->sdata->dev != dev))) goto do_survey; memset(&sinfo, 0, sizeof(sinfo)); sta_set_sinfo(sta, &sinfo, false); i = 0; ADD_STA_STATS(sta); data[i++] = sta->sta_state; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.txrate); i++; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG)) data[i] = (u8)sinfo.signal_avg; i++; } else { list_for_each_entry(sta, &local->sta_list, list) { /* Make sure this station belongs to the proper dev */ if (sta->sdata->dev != dev) continue; memset(&sinfo, 0, sizeof(sinfo)); sta_set_sinfo(sta, &sinfo, false); i = 0; ADD_STA_STATS(sta); } } do_survey: i = STA_STATS_LEN - STA_STATS_SURVEY_LEN; /* Get survey stats for current channel */ survey.filled = 0; rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (chanctx_conf) channel = chanctx_conf->def.chan; else channel = NULL; rcu_read_unlock(); if (channel) { q = 0; do { survey.filled = 0; if (drv_get_survey(local, q, &survey) != 0) { survey.filled = 0; break; } q++; } while (channel != survey.channel); } if (survey.filled) data[i++] = survey.channel->center_freq; else data[i++] = 0; if (survey.filled & SURVEY_INFO_NOISE_DBM) data[i++] = (u8)survey.noise; else data[i++] = -1LL; if (survey.filled & SURVEY_INFO_TIME) data[i++] = survey.time; else data[i++] = -1LL; if (survey.filled & SURVEY_INFO_TIME_BUSY) data[i++] = survey.time_busy; else data[i++] = -1LL; if (survey.filled & SURVEY_INFO_TIME_EXT_BUSY) data[i++] = survey.time_ext_busy; else data[i++] = -1LL; if (survey.filled & SURVEY_INFO_TIME_RX) data[i++] = survey.time_rx; else data[i++] = -1LL; if (survey.filled & SURVEY_INFO_TIME_TX) data[i++] = survey.time_tx; else data[i++] = -1LL; mutex_unlock(&local->sta_mtx); if (WARN_ON(i != STA_STATS_LEN)) return; drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN])); } static void ieee80211_get_strings(struct net_device *dev, u32 sset, u8 *data) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); int sz_sta_stats = 0; if (sset == ETH_SS_STATS) { sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats); memcpy(data, ieee80211_gstrings_sta_stats, sz_sta_stats); } drv_get_et_strings(sdata, sset, &(data[sz_sta_stats])); } static int ieee80211_get_regs_len(struct net_device *dev) { return 0; } static void ieee80211_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *data) { struct wireless_dev *wdev = dev->ieee80211_ptr; regs->version = wdev->wiphy->hw_version; regs->len = 0; } const struct ethtool_ops ieee80211_ethtool_ops = { .get_drvinfo = cfg80211_get_drvinfo, .get_regs_len = ieee80211_get_regs_len, .get_regs = ieee80211_get_regs, .get_link = ethtool_op_get_link, .get_ringparam = ieee80211_get_ringparam, .set_ringparam = ieee80211_set_ringparam, .get_strings = ieee80211_get_strings, .get_ethtool_stats = ieee80211_get_stats, .get_sset_count = ieee80211_get_sset_count, }; |
| 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS: Locality-Based Least-Connection with Replication scheduler * * Authors: Wensong Zhang <wensong@gnuchina.org> * * Changes: * Julian Anastasov : Added the missing (dest->weight>0) * condition in the ip_vs_dest_set_max. */ /* * The lblc/r algorithm is as follows (pseudo code): * * if serverSet[dest_ip] is null then * n, serverSet[dest_ip] <- {weighted least-conn node}; * else * n <- {least-conn (alive) node in serverSet[dest_ip]}; * if (n is null) OR * (n.conns>n.weight AND * there is a node m with m.conns<m.weight/2) then * n <- {weighted least-conn node}; * add n to serverSet[dest_ip]; * if |serverSet[dest_ip]| > 1 AND * now - serverSet[dest_ip].lastMod > T then * m <- {most conn node in serverSet[dest_ip]}; * remove m from serverSet[dest_ip]; * if serverSet[dest_ip] changed then * serverSet[dest_ip].lastMod <- now; * * return n; * */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/jiffies.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> #include <linux/sysctl.h> #include <net/net_namespace.h> #include <net/ip_vs.h> /* * It is for garbage collection of stale IPVS lblcr entries, * when the table is full. */ #define CHECK_EXPIRE_INTERVAL (60*HZ) #define ENTRY_TIMEOUT (6*60*HZ) #define DEFAULT_EXPIRATION (24*60*60*HZ) /* * It is for full expiration check. * When there is no partial expiration check (garbage collection) * in a half hour, do a full expiration check to collect stale * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 /* * for IPVS lblcr entry hash table */ #ifndef CONFIG_IP_VS_LBLCR_TAB_BITS #define CONFIG_IP_VS_LBLCR_TAB_BITS 10 #endif #define IP_VS_LBLCR_TAB_BITS CONFIG_IP_VS_LBLCR_TAB_BITS #define IP_VS_LBLCR_TAB_SIZE (1 << IP_VS_LBLCR_TAB_BITS) #define IP_VS_LBLCR_TAB_MASK (IP_VS_LBLCR_TAB_SIZE - 1) /* * IPVS destination set structure and operations */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; struct ip_vs_dest_set { atomic_t size; /* set size */ unsigned long lastmod; /* last modified time */ struct list_head list; /* destination list */ }; static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest, bool check) { struct ip_vs_dest_set_elem *e; if (check) { list_for_each_entry(e, &set->list, list) { if (e->dest == dest) return; } } e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e == NULL) return; ip_vs_dest_hold(dest); e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); set->lastmod = jiffies; } static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) { struct ip_vs_dest_set_elem *e; e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); ip_vs_dest_put_and_free(e->dest); kfree(e); } static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; list_del_rcu(&e->list); call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } } static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { list_del_rcu(&e->list); call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } /* get weighted least-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *least; int loh, doh; /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; if ((atomic_read(&least->weight) > 0) && (least->flags & IP_VS_DEST_F_AVAILABLE)) { loh = ip_vs_dest_conn_overhead(least); goto nextstage; } } return NULL; /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); if (((__s64)loh * atomic_read(&dest->weight) > (__s64)doh * atomic_read(&least->weight)) && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { least = dest; loh = doh; } } IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", __func__, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } /* get weighted most-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *most; int moh, doh; if (set == NULL) return NULL; /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; } } return NULL; /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ if (((__s64)moh * atomic_read(&dest->weight) < (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; } } IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", __func__, IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port), atomic_read(&most->activeconns), refcount_read(&most->refcnt), atomic_read(&most->weight), moh); return most; } /* * IPVS lblcr entry represents an association between destination * IP address and its destination server set */ struct ip_vs_lblcr_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ struct ip_vs_dest_set set; /* destination server set */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; /* * IPVS lblcr hash table */ struct ip_vs_lblcr_table { struct rcu_head rcu_head; struct hlist_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */ atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ struct timer_list periodic_timer; /* collect stale entries */ struct ip_vs_service *svc; /* pointer back to service */ int rover; /* rover for expire check */ int counter; /* counter for no expire */ bool dead; }; #ifdef CONFIG_SYSCTL /* * IPVS LBLCR sysctl table */ static struct ctl_table vs_vars_table[] = { { .procname = "lblcr_expiration", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; #endif static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { hlist_del_rcu(&en->list); ip_vs_dest_set_eraseall(&en->set); kfree_rcu(en, rcu_head); } /* * Returns hash value for IPVS LBLCR entry */ static inline unsigned int ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS); } /* * Hash an entry in the ip_vs_lblcr_table. * returns bool success. */ static void ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en) { unsigned int hash = ip_vs_lblcr_hashkey(en->af, &en->addr); hlist_add_head_rcu(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); } /* Get ip_vs_lblcr_entry associated with supplied parameters. */ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *addr) { unsigned int hash = ip_vs_lblcr_hashkey(af, addr); struct ip_vs_lblcr_entry *en; hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list) if (ip_vs_addr_equal(af, &en->addr, addr)) return en; return NULL; } /* * Create or update an ip_vs_lblcr_entry, which is a mapping of a destination * IP address to a server. Called under spin lock. */ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr, u16 af, struct ip_vs_dest *dest) { struct ip_vs_lblcr_entry *en; en = ip_vs_lblcr_get(af, tbl, daddr); if (!en) { en = kmalloc(sizeof(*en), GFP_ATOMIC); if (!en) return NULL; en->af = af; ip_vs_addr_copy(af, &en->addr, daddr); en->lastuse = jiffies; /* initialize its dest set */ atomic_set(&(en->set.size), 0); INIT_LIST_HEAD(&en->set.list); ip_vs_dest_set_insert(&en->set, dest, false); ip_vs_lblcr_hash(tbl, en); return en; } ip_vs_dest_set_insert(&en->set, dest, true); return en; } /* * Flush all the entries of the specified table. */ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; int i; struct ip_vs_lblcr_entry *en; struct hlist_node *next; spin_lock_bh(&svc->sched_lock); tbl->dead = true; for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { ip_vs_lblcr_free(en); } } spin_unlock_bh(&svc->sched_lock); } static int sysctl_lblcr_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL return svc->ipvs->sysctl_lblcr_expiration; #else return DEFAULT_EXPIRATION; #endif } static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en; struct hlist_node *next; for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) { if (time_after(en->lastuse + sysctl_lblcr_expiration(svc), now)) continue; ip_vs_lblcr_free(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); } tbl->rover = j; } /* * Periodical timer handler for IPVS lblcr table * It is used to collect stale entries when the number of entries * exceeds the maximum size of the table. * * Fixme: we probably need more complicated algorithm to collect * entries that have not been used for a long time even * if the number of entries doesn't exceed the maximum size * of the table. * The full expiration check is for this purpose now. */ static void ip_vs_lblcr_check_expire(struct timer_list *t) { struct ip_vs_lblcr_table *tbl = from_timer(tbl, t, periodic_timer); struct ip_vs_service *svc = tbl->svc; unsigned long now = jiffies; int goal; int i, j; struct ip_vs_lblcr_entry *en; struct hlist_node *next; if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) { /* do full expiration check */ ip_vs_lblcr_full_check(svc); tbl->counter = 1; goto out; } if (atomic_read(&tbl->entries) <= tbl->max_size) { tbl->counter++; goto out; } goal = (atomic_read(&tbl->entries) - tbl->max_size)*4/3; if (goal > tbl->max_size/2) goal = tbl->max_size/2; for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) { if (time_before(now, en->lastuse+ENTRY_TIMEOUT)) continue; ip_vs_lblcr_free(en); atomic_dec(&tbl->entries); goal--; } spin_unlock(&svc->sched_lock); if (goal <= 0) break; } tbl->rover = j; out: mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL); } static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) { int i; struct ip_vs_lblcr_table *tbl; /* * Allocate the ip_vs_lblcr_table for this service */ tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; svc->sched_data = tbl; IP_VS_DBG(6, "LBLCR hash table (memory=%zdbytes) allocated for " "current service\n", sizeof(*tbl)); /* * Initialize the hash buckets */ for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { INIT_HLIST_HEAD(&tbl->bucket[i]); } tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16; tbl->rover = 0; tbl->counter = 1; tbl->dead = false; tbl->svc = svc; atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection */ timer_setup(&tbl->periodic_timer, ip_vs_lblcr_check_expire, 0); mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; } static void ip_vs_lblcr_done_svc(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; /* remove periodic timer */ del_timer_sync(&tbl->periodic_timer); /* got to clean up table entries here */ ip_vs_lblcr_flush(svc); /* release the table itself */ kfree_rcu(tbl, rcu_head); IP_VS_DBG(6, "LBLCR hash table (memory=%zdbytes) released\n", sizeof(*tbl)); } static inline struct ip_vs_dest * __ip_vs_lblcr_schedule(struct ip_vs_service *svc) { struct ip_vs_dest *dest, *least; int loh, doh; /* * We use the following formula to estimate the load: * (dest overhead) / dest->weight * * Remember -- no floats in kernel mode!!! * The comparison of h1*w2 > h2*w1 is equivalent to that of * h1/w1 > h2/w2 * if every weight is larger than zero. * * The server with weight=0 is quiesced and will not receive any * new connection. */ list_for_each_entry_rcu(dest, &svc->destinations, n_list) { if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; if (atomic_read(&dest->weight) > 0) { least = dest; loh = ip_vs_dest_conn_overhead(least); goto nextstage; } } return NULL; /* * Find the destination with the least load. */ nextstage: list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) { if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); if ((__s64)loh * atomic_read(&dest->weight) > (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } } IP_VS_DBG_BUF(6, "LBLCR: server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } /* * If this destination server is overloaded and there is a less loaded * server, then return true. */ static inline int is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) { if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) { struct ip_vs_dest *d; list_for_each_entry_rcu(d, &svc->destinations, n_list) { if (atomic_read(&d->activeconns)*2 < atomic_read(&d->weight)) { return 1; } } } return 0; } /* * Locality-Based (weighted) Least-Connection scheduling */ static struct ip_vs_dest * ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_lblcr_table *tbl = svc->sched_data; struct ip_vs_dest *dest; struct ip_vs_lblcr_entry *en; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ en = ip_vs_lblcr_get(svc->af, tbl, &iph->daddr); if (en) { en->lastuse = jiffies; /* Get the least loaded destination */ dest = ip_vs_dest_set_min(&en->set); /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && time_after(jiffies, en->set.lastmod + sysctl_lblcr_expiration(svc))) { spin_lock_bh(&svc->sched_lock); if (atomic_read(&en->set.size) > 1) { struct ip_vs_dest *m; m = ip_vs_dest_set_max(&en->set); if (m) ip_vs_dest_set_erase(&en->set, m); } spin_unlock_bh(&svc->sched_lock); } /* If the destination is not overloaded, use it */ if (dest && !is_overloaded(dest, svc)) goto out; /* The cache entry is invalid, time to schedule */ dest = __ip_vs_lblcr_schedule(svc); if (!dest) { ip_vs_scheduler_err(svc, "no destination available"); return NULL; } /* Update our cache entry */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) ip_vs_dest_set_insert(&en->set, dest, true); spin_unlock_bh(&svc->sched_lock); goto out; } /* No cache entry, time to schedule */ dest = __ip_vs_lblcr_schedule(svc); if (!dest) { IP_VS_DBG(1, "no destination available\n"); return NULL; } /* If we fail to create a cache entry, we'll just use the valid dest */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) ip_vs_lblcr_new(tbl, &iph->daddr, svc->af, dest); spin_unlock_bh(&svc->sched_lock); out: IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n", IP_VS_DBG_ADDR(svc->af, &iph->daddr), IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); return dest; } /* * IPVS LBLCR Scheduler structure */ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = { .name = "lblcr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), .init_service = ip_vs_lblcr_init_svc, .done_service = ip_vs_lblcr_done_svc, .schedule = ip_vs_lblcr_schedule, }; /* * per netns init. */ #ifdef CONFIG_SYSCTL static int __net_init __ip_vs_lblcr_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); if (!ipvs) return -ENOENT; if (!net_eq(net, &init_net)) { ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), GFP_KERNEL); if (ipvs->lblcr_ctl_table == NULL) return -ENOMEM; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) ipvs->lblcr_ctl_table[0].procname = NULL; } else ipvs->lblcr_ctl_table = vs_vars_table; ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION; ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; ipvs->lblcr_ctl_header = register_net_sysctl(net, "net/ipv4/vs", ipvs->lblcr_ctl_table); if (!ipvs->lblcr_ctl_header) { if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); return -ENOMEM; } return 0; } static void __net_exit __ip_vs_lblcr_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); unregister_net_sysctl_table(ipvs->lblcr_ctl_header); if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); } #else static int __net_init __ip_vs_lblcr_init(struct net *net) { return 0; } static void __net_exit __ip_vs_lblcr_exit(struct net *net) { } #endif static struct pernet_operations ip_vs_lblcr_ops = { .init = __ip_vs_lblcr_init, .exit = __ip_vs_lblcr_exit, }; static int __init ip_vs_lblcr_init(void) { int ret; ret = register_pernet_subsys(&ip_vs_lblcr_ops); if (ret) return ret; ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) unregister_pernet_subsys(&ip_vs_lblcr_ops); return ret; } static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); rcu_barrier(); } module_init(ip_vs_lblcr_init); module_exit(ip_vs_lblcr_cleanup); MODULE_LICENSE("GPL"); |
| 33 8 8 6 2 32 32 32 2 26 26 26 26 26 26 4 4 2 4 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_mq.c Classful multiqueue dummy scheduler * * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> struct mq_sched { struct Qdisc **qdiscs; }; static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) { struct net_device *dev = qdisc_dev(sch); struct tc_mq_qopt_offload opt = { .command = cmd, .handle = sch->handle, }; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); } static int mq_offload_stats(struct Qdisc *sch) { struct tc_mq_qopt_offload opt = { .command = TC_MQ_STATS, .handle = sch->handle, .stats = { .bstats = &sch->bstats, .qstats = &sch->qstats, }, }; return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt); } static void mq_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); unsigned int ntx; mq_offload(sch, TC_MQ_DESTROY); if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } static int mq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct netdev_queue *dev_queue; struct Qdisc *qdisc; unsigned int ntx; if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; /* pre-allocate qdiscs, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); if (!priv->qdiscs) return -ENOMEM; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1)), extack); if (!qdisc) return -ENOMEM; priv->qdiscs[ntx] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; mq_offload(sch, TC_MQ_CREATE); return 0; } static void mq_attach(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct Qdisc *qdisc, *old; unsigned int ntx; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); #endif } kfree(priv->qdiscs); priv->qdiscs = NULL; } static void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) { #ifdef CONFIG_NET_SCHED struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } #endif } static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; __u32 qlen = 0; sch->q.qlen = 0; memset(&sch->bstats, 0, sizeof(sch->bstats)); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs * to account for all, none, or a mix of locked and unlocked child * qdiscs. Percpu stats are added to counters in-band and locking * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); if (qdisc_is_percpu_stats(qdisc)) { qlen = qdisc_qlen_sum(qdisc); __gnet_stats_copy_basic(NULL, &sch->bstats, qdisc->cpu_bstats, &qdisc->bstats); __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; sch->bstats.packets += qdisc->bstats.packets; sch->qstats.qlen += qdisc->qstats.qlen; sch->qstats.backlog += qdisc->qstats.backlog; sch->qstats.drops += qdisc->qstats.drops; sch->qstats.requeues += qdisc->qstats.requeues; sch->qstats.overlimits += qdisc->qstats.overlimits; } spin_unlock_bh(qdisc_lock(qdisc)); } return mq_offload_stats(sch); } static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return netdev_get_tx_queue(dev, ntx); } static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); struct tc_mq_qopt_offload graft_offload; struct net_device *dev = qdisc_dev(sch); if (dev->flags & IFF_UP) dev_deactivate(dev); *old = dev_graft_qdisc(dev_queue, new); if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); graft_offload.handle = sch->handle; graft_offload.graft_params.queue = cl - 1; graft_offload.graft_params.child_handle = new ? new->handle : 0; graft_offload.command = TC_MQ_GRAFT; qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, TC_SETUP_QDISC_MQ, &graft_offload, extack); return 0; } static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); return dev_queue->qdisc_sleeping; } static unsigned long mq_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); if (!mq_queue_get(sch, ntx)) return 0; return ntx; } static int mq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = dev_queue->qdisc_sleeping->handle; return 0; } static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct net_device *dev = qdisc_dev(sch); unsigned int ntx; if (arg->stop) return; arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; break; } arg->count++; } } static const struct Qdisc_class_ops mq_class_ops = { .select_queue = mq_select_queue, .graft = mq_graft, .leaf = mq_leaf, .find = mq_find, .walk = mq_walk, .dump = mq_dump_class, .dump_stats = mq_dump_class_stats, }; struct Qdisc_ops mq_qdisc_ops __read_mostly = { .cl_ops = &mq_class_ops, .id = "mq", .priv_size = sizeof(struct mq_sched), .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; |
| 51 51 51 51 81 430 485 484 426 80 426 486 488 430 81 429 66 66 66 66 465 219 293 227 229 274 126 185 10 273 125 186 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/export.h> #include <linux/init.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/checksum.h> #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> #include <linux/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/nfnetlink_conntrack.h> static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) { __be16 *portptr, newport; if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } if (do_csum) { nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } *portptr = newport; } static bool udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); return true; } static bool udplite_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, true); #endif return true; } static bool sctp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such * cases we cannot update the checksum field since it is outside * of the 8 bytes of transport layer headers we are guaranteed. */ if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ hdr->source = tuple->src.u.sctp.port; } else { /* Get rid of dst port */ hdr->dest = tuple->dst.u.sctp.port; } if (hdrsize < sizeof(*hdr)) return true; if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; } #endif return true; } static bool tcp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct tcphdr *hdr; __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such cases we cannot update the checksum field since it is outside of the 8 bytes of transport layer headers we are guaranteed */ if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.tcp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.tcp.port; portptr = &hdr->dest; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool dccp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_DCCP struct dccp_hdr *hdr; __be16 *portptr, oldport, newport; int hdrsize = 8; /* DCCP connection tracking guarantees this much */ if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct dccp_hdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { newport = tuple->src.u.dccp.port; portptr = &hdr->dccph_sport; } else { newport = tuple->dst.u.dccp.port; portptr = &hdr->dccph_dport; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype); inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, false); #endif return true; } static bool icmp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); switch (hdr->type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMP_INFO_REQUEST: case ICMP_INFO_REPLY: case ICMP_ADDRESS: case ICMP_ADDRESSREPLY: break; default: return true; } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } static bool icmpv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmp6hdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; } /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) const struct gre_base_hdr *greh; struct pptp_gre_header *pgreh; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; pgreh = (struct pptp_gre_header *)greh; /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->flags & GRE_VERSION) { case GRE_VERSION_0: /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_1: pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: pr_debug("can't nat unknown GRE version\n"); return false; } #endif return true; } static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDPLITE: return udplite_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_DCCP: return dccp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { struct iphdr *iph; unsigned int hdroff; if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; hdroff = iphdroff + iph->ihl * 4; if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; iph = (void *)skb->data + iphdroff; if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); iph->daddr = target->dst.u3.ip; } return true; } static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ipv6h; __be16 frag_off; int hdroff; u8 nexthdr; if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; nexthdr = ipv6h->nexthdr; hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), &nexthdr, &frag_off); if (hdroff < 0) goto manip_addr; if ((frag_off & htons(~0x7)) == 0 && !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; /* must reload, offset might have changed */ ipv6h = (void *)skb->data + iphdroff; manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; else ipv6h->daddr = target->dst.u3.in6; #endif return true; } unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir) { struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (target.src.l3num) { case NFPROTO_IPV6: if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; case NFPROTO_IPV4: if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; default: WARN_ON_ONCE(1); break; } return NF_DROP; } static void nf_nat_ipv4_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); __be32 oldip, newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = t->src.u3.ip; } else { oldip = iph->daddr; newip = t->dst.u3.ip; } inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv6_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); const struct in6_addr *oldip, *newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = &ipv6h->saddr; newip = &t->src.u3.in6; } else { oldip = &ipv6h->daddr; newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, newip->s6_addr32, true); #endif } static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { switch (t->src.l3num) { case NFPROTO_IPV4: nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); return; case NFPROTO_IPV6: nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); return; } } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct iphdr *iph = ip_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + ip_hdrlen(skb); skb->csum_offset = (void *)check - data; *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #if IS_ENABLED(CONFIG_IPV6) static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + (data - (void *)skb->data); skb->csum_offset = (void *)check - data; *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #endif void nf_nat_csum_recalc(struct sk_buff *skb, u8 nfproto, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { switch (nfproto) { case NFPROTO_IPV4: nf_nat_ipv4_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: nf_nat_ipv6_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #endif } WARN_ON_ONCE(1); } int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum) { struct { struct icmphdr icmp; struct iphdr ip; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); unsigned int hdrlen = ip_hdrlen(skb); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp.type == ICMP_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { /* Reloading "inside" here since manip_pkt may reallocate */ inside = (void *)skb->data + hdrlen; inside->icmp.checksum = 0; inside->icmp.checksum = csum_fold(skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } #ifdef CONFIG_XFRM static int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct sock *sk = skb->sk; struct dst_entry *dst; unsigned int hh_len; struct flowi fl; int err; err = xfrm_decode_session(skb, &fl, family); if (err < 0) return err; dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; if (!dst_hold_safe(dst)) return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_drop(skb); skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -ENOMEM; return 0; } #endif static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { __be32 saddr = ip_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr && !inet_sk_transparent(sk)) skb_orphan(skb); /* TCP edemux obtained wrong socket */ return ret; } static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_out, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_local_fn, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); #if IS_ENABLED(CONFIG_IPV6) int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen) { struct { struct icmp6hdr icmp6; struct ipv6hdr ip6; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); inside = (void *)skb->data + hdrlen; inside->icmp6.icmp6_cksum = 0; inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be16 frag_off; int hdrlen; u8 nexthdr; ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, state->hook, hdrlen)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_out, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_local_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); #endif /* CONFIG_IPV6 */ #if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT) int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) { int ret; if (WARN_ON_ONCE(ops->pf != NFPROTO_INET)) return -EINVAL; ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); if (ret) return ret; ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn); #endif /* NFT INET NAT */ |
| 65 66 66 2 65 1975 1974 1975 1047 1026 19 5646 5387 5386 5334 66 5386 5198 9 9 66 66 16 16 18 5721 5996 6013 5715 5730 224 5725 55 5723 5991 5806 322 135 6000 6000 5112 3739 6002 5994 849 5991 102 6002 2896 2949 2702 160 209 206 6 6 4241 4259 4098 3536 3535 3539 3533 3465 3455 6 6 41 41 3462 3465 3348 179 3355 45 1449 1102 400 51 52 86 86 74 16 1464 1468 1172 349 350 350 31 350 1174 1473 1468 15 15 15 9 9 4 4 4 5209 5210 1047 1049 2766 2767 1208 27 1189 51 51 16 23 34 34 51 51 34 17 51 14 283 277 279 121 121 71 110 12 12 12 12 49 108 37 89 90 12 90 89 38 855 272 184 574 53 53 156 157 11 157 22 37 11 38 17 33 1 31 1 2 2 2 226 4 207 32 27 30 30 30 8 9 2 135 170 7 145 27 32 33 33 33 5 5 5 145 27 121 146 1225 1468 342 345 19 74 74 3 2654 22 25 25 25 9 25 25 25 25 55 75 22 23 23 12 11 23 23 23 23 23 23 23 6 6 17 13 13 13 13 13 13 11 6 6 23 23 12 12 2 10 2 2 2 12 2 10 18 17 17 17 17 30 9 9 15 9 9 17 17 17 17 17 17 17 17 17 17 16 74 1 1 72 2 2 2 2 2 2 2 4 4 20 20 20 20 4 15 16 16 199 199 197 200 199 4 2 14 9 23 24 24 24 17 5 12 17 20 20 20 17 17 17 17 481 479 467 6 2 5 5 5 14 2 14 6 5 1 2 2 2 2 2 1236 1 2 1230 142 52 138 50 170 168 12 1 1 23 23 1 3 23 3 3 1 23 23 23 21 19 19 19 1 23 23 3 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <net/page_pool.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include "datagram.h" #include "sock_destructor.h" struct kmem_cache *skbuff_head_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n", msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } #define NAPI_SKB_CACHE_SIZE 64 #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) struct napi_alloc_cache { struct page_frag_cache page; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); static void *__alloc_frag_align(unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align_mask); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { fragsz = SKB_DATA_ALIGN(fragsz); return __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { local_bh_disable(); data = __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); local_bh_enable(); } return data; } EXPORT_SYMBOL(__netdev_alloc_frag_align); static struct sk_buff *napi_skb_cache_get(void) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; if (unlikely(!nc->skb_count)) nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); if (unlikely(!nc->skb_count)) return NULL; skb = nc->skb_cache[--nc->skb_count]; kasan_unpoison_object_data(skbuff_head_cache, skb); return skb; } /* Caller must provide SKB that is memset cleared */ static void __build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; unsigned int size = frag_size ? : ksize(data); size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Assumes caller memset cleared SKB */ skb->truesize = SKB_TRUESIZE(size); refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if * @frag_size is 0, otherwise data should come from the page allocator * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, frag_size); return skb; } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc * This means that if @frag_size is not zero, then @data must be backed * by a page fragment, not kmalloc() or vmalloc() */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; } EXPORT_SYMBOL(build_skb); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; __build_skb_around(skb, data, frag_size); if (frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; } EXPORT_SYMBOL(build_skb_around); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = napi_skb_cache_get(); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, frag_size); return skb; } /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __napi_build_skb(data, frag_size); if (likely(skb) && frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(napi_build_skb); /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ static void *kmalloc_reserve(size_t size, gfp_t flags, int node, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; obj = kmalloc_node_track_caller(size, flags, node); out: if (pfmemalloc) *pfmemalloc = ret_pfmemalloc; return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { struct kmem_cache *cache; struct sk_buff *skb; u8 *data; bool pfmemalloc; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && likely(node == NUMA_NO_NODE || node == numa_mem_id())) skb = napi_skb_cache_get(); else skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); if (unlikely(!skb)) return NULL; prefetchw(skb); /* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc(size) might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + size); /* * Only clear those fields we need to clear, not those that we will * actually initialise below. Hence, don't put any more fields after * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, 0); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); skb->fclone = SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); fclones->skb2.fclone = SKB_FCLONE_CLONE; } return skb; nodata: kmem_cache_free(cache, skb); return NULL; } EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; len += NET_SKB_PAD; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; local_bh_enable(); } if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); /** * __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { struct napi_alloc_cache *nc; struct sk_buff *skb; void *data; len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } nc = this_cpu_ptr(&napi_alloc_cache); len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; data = page_frag_alloc(&nc->page, len, gfp_mask); if (unlikely(!data)) return NULL; skb = __napi_build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); skb->dev = napi->dev; skb_fail: return skb; } EXPORT_SYMBOL(__napi_alloc_skb); void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_fill_page_desc(skb, i, page, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_add_rx_frag); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; skb_frag_size_add(frag, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { kfree_skb_list(*listp); *listp = NULL; } static inline void skb_drop_fraglist(struct sk_buff *skb) { skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; skb_walk_frags(skb, list) skb_get(list); } static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) { if (skb_pp_recycle(skb, head)) return; skb_free_frag(head); } else { kfree(head); } } static void skb_release_data(struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; if (skb->cloned && atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, &shinfo->dataref)) goto exit; skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have * additional references to to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling */ skb->pp_recycle = 0; } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff_fclones *fclones; switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(skbuff_head_cache, skb); return; case SKB_FCLONE_ORIG: fclones = container_of(skb, struct sk_buff_fclones, skb1); /* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; default: /* SKB_FCLONE_CLONE */ fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { WARN_ON(in_hardirq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb_nfct(skb)); #endif skb_ext_put(skb); } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb) { skb_release_head_state(skb); if (likely(skb->head)) skb_release_data(skb); } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { skb_release_all(skb); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); /** * kfree_skb_reason - free an sk_buff with special reason * @skb: buffer to free * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has * hit zero. Meanwhile, pass the drop reason to 'kfree_skb' * tracepoint. */ void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (!skb_unref(skb)) return; trace_kfree_skb(skb, __builtin_return_address(0), reason); __kfree_skb(skb); } EXPORT_SYMBOL(kfree_skb_reason); void kfree_skb_list(struct sk_buff *segs) { while (segs) { struct sk_buff *next = segs->next; kfree_skb(segs); segs = next; } } EXPORT_SYMBOL(kfree_skb_list); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; struct sk_buff *list_skb; bool has_mac, has_trans; int headroom, tailroom; int i, len, seg_len; if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); headroom = skb_headroom(skb); tailroom = skb_tailroom(skb); has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" "mac=(%d,%d) net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n", level, skb->len, headroom, skb_headlen(skb), tailroom, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, skb->csum, skb->ip_summed, skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); if (dev) printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb->head, headroom, false); seg_len = min_t(int, skb_headlen(skb), len); if (seg_len) print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, seg_len, false); len -= seg_len; if (full_pkt && tailroom) print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb_tail_pointer(skb), tailroom, false); for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); vaddr = kmap_atomic(p); print_hex_dump(level, "skb frag: ", DUMP_PREFIX_OFFSET, 16, 1, vaddr + p_off, seg_len, false); kunmap_atomic(vaddr); len -= seg_len; if (!len) break; } } if (full_pkt && skb_has_frag_list(skb)) { printk("skb fraglist:\n"); skb_walk_frags(skb, list_skb) skb_dump(level, list_skb, true); } } EXPORT_SYMBOL(skb_dump); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { skb_zcopy_clear(skb, true); } EXPORT_SYMBOL(skb_tx_error); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_consume_skb(skb); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); #endif /** * __consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb); skb_release_data(skb); kfree_skbmem(skb); } static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; kasan_poison_object_data(skbuff_head_cache, skb); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_unpoison_object_data(skbuff_head_cache, nc->skb_cache[i]); kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } } void __kfree_skb_defer(struct sk_buff *skb) { skb_release_all(skb); napi_skb_cache_put(skb); } void napi_skb_free_stolen_head(struct sk_buff *skb) { if (unlikely(skb->slow_gro)) { nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); skb_orphan(skb); skb->slow_gro = 0; } napi_skb_cache_put(skb); } void napi_consume_skb(struct sk_buff *skb, int budget) { /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { dev_consume_skb_any(skb); return; } lockdep_assert_in_softirq(); if (!skb_unref(skb)) return; /* if reaching here SKB is ready to free */ trace_consume_skb(skb); /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } skb_release_all(skb); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); /* Make sure a field is enclosed inside headers_start/headers_end section */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) < \ offsetof(struct sk_buff, headers_start)); \ BUILD_BUG_ON(offsetof(struct sk_buff, field) > \ offsetof(struct sk_buff, headers_end)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; /* We do not copy old->sk */ new->dev = old->dev; memcpy(new->cb, old->cb, sizeof(old->cb)); skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false); /* Note : this field could be in headers_start/headers_end section * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; memcpy(&new->headers_start, &old->headers_start, offsetof(struct sk_buff, headers_end) - offsetof(struct sk_buff, headers_start)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); CHECK_SKB_FIELD(priority); CHECK_SKB_FIELD(skb_iif); CHECK_SKB_FIELD(vlan_proto); CHECK_SKB_FIELD(vlan_tci); CHECK_SKB_FIELD(transport_header); CHECK_SKB_FIELD(network_header); CHECK_SKB_FIELD(mac_header); CHECK_SKB_FIELD(inner_protocol); CHECK_SKB_FIELD(inner_transport_header); CHECK_SKB_FIELD(inner_network_header); CHECK_SKB_FIELD(inner_mac_header); CHECK_SKB_FIELD(mark); #ifdef CONFIG_NETWORK_SECMARK CHECK_SKB_FIELD(secmark); #endif #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x n->next = n->prev = NULL; n->sk = NULL; __copy_skb_header(n, skb); C(len); C(data_len); C(mac_len); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; n->peeked = 0; C(pfmemalloc); C(pp_recycle); n->destructor = NULL; C(tail); C(end); C(head); C(head_frag); C(data); C(truesize); refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; return n; #undef C } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { struct sk_buff *n; n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL; n->len = first->len; n->data_len = first->len; n->truesize = first->truesize; skb_shinfo(n)->frag_list = first; __copy_skb_header(n, first); n->destructor = NULL; return n; } EXPORT_SYMBOL_GPL(alloc_skb_for_msg); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { skb_release_all(dst); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg; struct user_struct *user; if (capable(CAP_IPC_LOCK) || !size) return 0; num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; user = mmp->user ? : current_user(); do { old_pg = atomic_long_read(&user->locked_vm); new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; } while (atomic_long_cmpxchg(&user->locked_vm, old_pg, new_pg) != old_pg); if (!mmp->user) { mmp->user = get_uid(user); mmp->num_pg = num_pg; } else { mmp->num_pg += num_pg; } return 0; } EXPORT_SYMBOL_GPL(mm_account_pinned_pages); void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; struct sk_buff *skb; WARN_ON_ONCE(!in_task()); skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; uarg->mmp.user = NULL; if (mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } uarg->callback = msg_zerocopy_callback; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; uarg->flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&uarg->refcnt, 1); sock_hold(sk); return uarg; } EXPORT_SYMBOL_GPL(msg_zerocopy_alloc); static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg) { if (uarg) { const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ if (!sock_owned_by_user(sk)) { WARN_ON_ONCE(1); return NULL; } bytelen = uarg->bytelen + size; if (uarg->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL; } next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg->id + uarg->len) == next) { if (mm_account_pinned_pages(&uarg->mmp, size)) return NULL; uarg->len++; uarg->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) net_zcopy_get(uarg); return uarg; } } new_alloc: return msg_zerocopy_alloc(sk, size); } EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 old_lo, old_hi; u64 sum_len; old_lo = serr->ee.ee_info; old_hi = serr->ee.ee_data; sum_len = old_hi - old_lo + 1ULL + len; if (sum_len >= (1ULL << 32)) return false; if (lo != old_hi + 1) return false; serr->ee.ee_data += len; return true; } static void __msg_zerocopy_callback(struct ubuf_info *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; bool is_zerocopy; u32 lo, hi; u16 len; mm_unaccount_pinned_pages(&uarg->mmp); /* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification */ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release; len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = 0; serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; spin_lock_irqsave(&q->lock, flags); tail = skb_peek_tail(q); if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || !skb_zerocopy_notify_extend(tail, lo, len)) { __skb_queue_tail(q, skb); skb = NULL; } spin_unlock_irqrestore(&q->lock, flags); sk_error_report(sk); release: consume_skb(skb); sock_put(sk); } void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { uarg->zerocopy = uarg->zerocopy & success; if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg); } EXPORT_SYMBOL_GPL(msg_zerocopy_callback); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { struct sock *sk = skb_from_uarg(uarg)->sk; atomic_dec(&sk->sk_zckey); uarg->len--; if (have_uref) msg_zerocopy_callback(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) { struct ubuf_info *orig_uarg = skb_zcopy(skb); struct iov_iter orig_iter = msg->msg_iter; int err, orig_len = skb->len; /* An skb can only point to one uarg. This edge case happens when * TCP appends to an skb, but zerocopy_realloc triggered a new alloc. */ if (orig_uarg && uarg != orig_uarg) return -EEXIST; err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; /* Streams do not free skb on error. Reset to prev state. */ msg->msg_iter = orig_iter; skb->sk = sk; ___pskb_trim(skb, orig_len); skb->sk = save_sk; return err; } skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) { WARN_ON_ONCE(1); return -ENOMEM; } if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO; } skb_zcopy_set(nskb, skb_uarg(orig), NULL); } return 0; } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; if (!num_frags) goto release; new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < new_frags; i++) { page = alloc_page(gfp_mask); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); put_page(head); head = next; } return -ENOMEM; } set_page_private(page, (unsigned long)head); head = page; } page = head; d_off = 0; for (i = 0; i < num_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); while (done < p_len) { if (d_off == PAGE_SIZE) { d_off = 0; page = (struct page *)page_private(page); } copy = min_t(u32, PAGE_SIZE - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; d_off += copy; } kunmap_atomic(vaddr); } } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_page_desc(skb, i, head, 0, PAGE_SIZE); head = (struct page *)page_private(head); } __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; release: skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff_fclones *fclones = container_of(skb, struct sk_buff_fclones, skb1); struct sk_buff *n; if (skb_orphan_frags(skb, gfp_mask)) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; refcount_set(&fclones->fclone_ref, 2); } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; n->fclone = SKB_FCLONE_UNAVAILABLE; } return __skb_clone(n, skb); } EXPORT_SYMBOL(skb_clone); void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */ skb->transport_header += off; skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; skb->inner_transport_header += off; skb->inner_network_header += off; skb->inner_mac_header += off; } EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { if (skb_pfmemalloc(skb)) return SKB_ALLOC_RX; return 0; } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; unsigned int size; int headerlen; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; headerlen = skb_headroom(skb); size = skb_end_offset(skb) + skb->data_len; n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; /* Set the data pointer */ skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { unsigned int size = skb_headlen(skb) + headroom; int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ skb_copy_from_linear_data(skb, n->data, n->len); n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; if (skb_orphan_frags(skb, gfp_mask) || skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } skb_copy_header(n, skb); out: return n; } EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { int i, osize = skb_end_offset(skb); int size = osize + nhead + ntail; long off; u8 *data; BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); /* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values */ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb); } else { skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; skb->head_frag = 0; skb->data += off; skb_set_end_offset(skb, size); #ifdef NET_SKBUFF_DATA_USES_OFFSET off = nhead; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); skb_metadata_clear(skb); /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). */ if (!skb->sk || skb->destructor == sock_edemux) skb->truesize += size - osize; return 0; nofrags: kfree(data); nodata: return -ENOMEM; } EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { struct sk_buff *skb2; int delta = headroom - skb_headroom(skb); if (delta <= 0) skb2 = pskb_copy(skb, GFP_ATOMIC); else { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { kfree_skb(skb2); skb2 = NULL; } } return skb2; } EXPORT_SYMBOL(skb_realloc_headroom); int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { unsigned int saved_end_offset, saved_truesize; struct skb_shared_info *shinfo; int res; saved_end_offset = skb_end_offset(skb); saved_truesize = skb->truesize; res = pskb_expand_head(skb, 0, 0, pri); if (res) return res; skb->truesize = saved_truesize; if (likely(skb_end_offset(skb) == saved_end_offset)) return 0; shinfo = skb_shinfo(skb); /* We are about to change back skb->end, * we need to move skb_shinfo() to its new location. */ memmove(skb->head + saved_end_offset, shinfo, offsetof(struct skb_shared_info, frags[shinfo->nr_frags])); skb_set_end_offset(skb, saved_end_offset); return 0; } /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); int osize = skb_end_offset(skb); struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; delta = SKB_DATA_ALIGN(delta); /* pskb_expand_head() might crash, if skb is shared. */ if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) goto fail; if (sk) skb_set_owner_w(nskb, sk); consume_skb(skb); skb = nskb; } if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) goto fail; if (sk && is_skb_wmem(skb)) { delta = skb_end_offset(skb) - osize; refcount_add(delta, &sk->sk_wmem_alloc); skb->truesize += delta; } return skb; fail: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_expand_head); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { /* * Allocate the copy buffer */ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; oldheadroom = skb_headroom(skb); n = __alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; skb_reserve(n, newheadroom); /* Set the tail pointer and length */ skb_put(n, skb->len); head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; else head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } EXPORT_SYMBOL(skb_copy_expand); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; /* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); return 0; } ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) { err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb; } /* FIXME: The use of this function with non-linear skb's really needs * to be audited. */ err = skb_linearize(skb); if (unlikely(err)) goto free_skb; memset(skb->data + skb->len, 0, pad); return 0; free_skb: if (free_on_error) kfree_skb(skb); return err; } EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; skb->len += len; } return skb_put(tail, len); } EXPORT_SYMBOL_GPL(pskb_put); /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ void *skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(skb->tail > skb->end)) skb_over_panic(skb, len, __builtin_return_address(0)); return tmp; } EXPORT_SYMBOL(skb_put); /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } EXPORT_SYMBOL(skb_push); /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); /** * skb_pull_data - remove data from the start of a buffer returning its * original position. * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the original data in the buffer * is returned after checking if there is enough data to pull. Once the * data has been pulled future pushes will overwrite the old data. */ void *skb_pull_data(struct sk_buff *skb, size_t len) { void *data = skb->data; if (skb->len < len) return NULL; skb_pull(skb, len); return data; } EXPORT_SYMBOL(skb_pull_data); /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. * The skb must be linear. */ void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } EXPORT_SYMBOL(skb_trim); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err; if (skb_cloned(skb) && unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; i = 0; if (offset >= len) goto drop_pages; for (; i < nfrags; i++) { int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); fragp = &frag->next) { int end = offset + frag->len; if (skb_shared(frag)) { struct sk_buff *nfrag; nfrag = skb_clone(frag, GFP_ATOMIC); if (unlikely(!nfrag)) return -ENOMEM; nfrag->next = frag->next; consume_skb(frag); frag = nfrag; *fragp = frag; } if (end < len) { offset = end; continue; } if (end > len && unlikely((err = pskb_trim(frag, len - offset)))) return err; if (frag->next) skb_drop_list(&frag->next); break; } done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { skb->len = len; skb->data_len = 0; skb_set_tail_pointer(skb, len); } if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len; skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; int offset = skb_checksum_start_offset(skb) + skb->csum_offset; if (offset + sizeof(__sum16) > hdlen) return -EINVAL; } return __pskb_trim(skb, len); } EXPORT_SYMBOL(pskb_trim_rcsum_slow); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned. */ int i, k, eat = (skb->tail + delta) - skb->end; if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) return NULL; } BUG_ON(skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size >= eat) goto pull_pages; eat -= size; } /* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8) */ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag && skb_headlen(list)) skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL; insp = list->next; list = clone; } else { /* This may be pulled without * problems. */ insp = list; } if (!pskb_pull(list, eat)) { kfree_skb(clone); return NULL; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; skb_shinfo(skb)->frag_list = clone; } } /* Success! Now we may commit changes to skb data. */ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; *frag = skb_shinfo(skb)->frags[i]; if (eat) { skb_frag_off_add(frag, eat); skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; } k++; } } skb_shinfo(skb)->nr_frags = k; end: skb->tail += delta; skb->data_len -= delta; if (!skb->data_len) skb_zcopy_clear(skb, false); return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; /* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; to += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(f, skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_copy_bits(frag_iter, offset - start, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_copy_bits); /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { put_page(spd->pages[i]); } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) return NULL; *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); memcpy(page_address(pfrag->page) + pfrag->offset, page_address(page) + *offset, *len); *offset = pfrag->offset; pfrag->offset += *len; return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { return spd->nr_pages && spd->pages[spd->nr_pages - 1] == page && (spd->partial[spd->nr_pages - 1].offset + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { page = linear_to_page(page, len, &offset, sk); if (!page) return true; } if (spd_can_coalesce(spd, page, offset)) { spd->partial[spd->nr_pages - 1].len += *len; return false; } get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; return false; } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) { if (!*len) return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; return false; } /* ignore any bits we already processed */ poff += *off; plen -= *off; *off = 0; do { unsigned int flen = min(*len, plen); if (spd_fill_page(spd, pipe, page, &flen, poff, linear, sk)) return true; poff += flen; plen -= flen; *len -= flen; } while (*len && plen); return false; } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { int seg; struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; /* * then map the fragments */ for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) return true; } skb_walk_frags(skb, iter) { if (*offset >= iter->len) { *offset -= iter->len; continue; } /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case. */ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) return true; } return false; } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; int ret = 0; __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) ret = splice_to_pipe(pipe, &spd); return ret; } EXPORT_SYMBOL_GPL(skb_splice_bits); static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { struct socket *sock = sk->sk_socket; if (!sock) return -EINVAL; return kernel_sendmsg(sock, msg, vec, num, size); } static int sendpage_unlocked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct socket *sock = sk->sk_socket; if (!sock) return -EINVAL; return kernel_sendpage(sock, page, offset, size, flags); } typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size); typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset, size_t size, int flags); static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len, sendmsg_func sendmsg, sendpage_func sendpage) { unsigned int orig_len = len; struct sk_buff *head = skb; unsigned short fragidx; int slen, ret; do_frag_list: /* Deal with head data */ while (offset < skb_headlen(skb) && len) { struct kvec kv; struct msghdr msg; slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT; ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked, sendmsg_unlocked, sk, &msg, &kv, 1, slen); if (ret <= 0) goto error; offset += ret; len -= ret; } /* All the data was skb head? */ if (!len) goto out; /* Make offset relative to start of frags */ offset -= skb_headlen(skb); /* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; if (offset < skb_frag_size(frag)) break; offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked, sendpage_unlocked, sk, skb_frag_page(frag), skb_frag_off(frag) + offset, slen, MSG_DONTWAIT); if (ret <= 0) goto error; len -= ret; offset += ret; slen -= ret; } offset = 0; } if (len) { /* Process any frag lists */ if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } } out: return orig_len - len; error: return orig_len == len ? ret : orig_len - len; } /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked, kernel_sendpage_locked); } EXPORT_SYMBOL_GPL(skb_send_sock_locked); /* Send skb data on a socket. Socket must be unlocked. */ int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, sendpage_unlocked); } /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; from += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_store_bits(frag_iter, offset - start, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; csum = INDIRECT_CALL_1(ops->update, csum_partial_ext, skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = INDIRECT_CALL_1(ops->update, csum_partial_ext, vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, p_len); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; csum2 = __skb_checksum(frag_iter, offset - start, copy, 0, ops); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, copy); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(__skb_checksum); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { const struct skb_checksum_ops ops = { .update = csum_partial_ext, .combine = csum_block_add_ext, }; return __skb_checksum(skb, offset, len, csum, &ops); } EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, copy); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { __wsum csum2; int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_copy_and_csum_bits); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { __wsum csum; __sum16 sum; csum = skb_checksum(skb, 0, skb->len, 0); sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around. */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) { /* Save full packet checksum */ skb->csum = csum; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum_complete_sw = 1; skb->csum_valid = !sum; } return sum; } EXPORT_SYMBOL(__skb_checksum_complete); static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, int offset, int len) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static const struct skb_checksum_ops default_crc32c_ops = { .update = warn_crc32c_csum_update, .combine = warn_crc32c_csum_combine, }; const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = &default_crc32c_ops; EXPORT_SYMBOL(crc32c_csum_stub); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { unsigned int hlen = 0; if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); if (!hlen) hlen = from->len; } if (skb_has_frag_list(from)) hlen = from->len; return hlen; } EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); __skb_fill_page_desc(to, 0, page, offset, plen); get_page(page); j = 1; len -= plen; } } to->truesize += len + plen; to->len += len + plen; to->data_len += len + plen; if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { skb_tx_error(from); return -ENOMEM; } skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { int size; if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), len); skb_frag_size_set(&skb_shinfo(to)->frags[j], size); len -= size; skb_frag_ref(to, j); j++; } skb_shinfo(to)->nr_frags = j; return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge - empty a list * @list: list to empty * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ void skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = skb_dequeue(list)) != NULL) kfree_skb(skb); } EXPORT_SYMBOL(skb_queue_purge); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); sum += skb->truesize; kfree_skb(skb); } return sum; } /** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_append); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; skb->len = len; skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; } else skb_shinfo(skb)->nr_frags++; pos += size; } skb_shinfo(skb1)->nr_frags = k; } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; fragfrom = &skb_shinfo(skb)->frags[from]; /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ if (!to || !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; /* All previous frag pointers might be stale! */ fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } from++; } /* Skip full, not-fitting skb to avoid expensive operations */ if ((shiftlen == skb->len) && (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) return 0; if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { if (to == MAX_SKB_FRAGS) return 0; fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; todo -= skb_frag_size(fragfrom); from++; to++; } else { __skb_frag_ref(fragfrom); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; to++; break; } } /* Ready to "commit" this state change to tgt */ skb_shinfo(tgt)->nr_frags = to; if (merge >= 0) { fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ to = 0; while (from < skb_shinfo(skb)->nr_frags) skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; skb_shinfo(skb)->nr_frags = to; BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent */ tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; /* Yak, is it really working this way? Some helper please? */ skb->len -= shiftlen; skb->data_len -= shiftlen; skb->truesize -= shiftlen; tgt->len += shiftlen; tgt->data_len += shiftlen; tgt->truesize += shiftlen; return shiftlen; } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { st->lower_offset = from; st->upper_offset = to; st->root_skb = st->cur_skb = skb; st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; st->frag_off = 0; } EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } return 0; } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { unsigned int pg_idx, pg_off, pg_sz; frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; pg_idx = 0; pg_off = skb_frag_off(frag); pg_sz = skb_frag_size(frag); if (skb_frag_must_loop(skb_frag_page(frag))) { pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT; pg_off = offset_in_page(pg_off + st->frag_off); pg_sz = min_t(unsigned int, pg_sz - st->frag_off, PAGE_SIZE - pg_off); } block_limit = pg_sz + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx); *data = (u8 *)st->frag_data + pg_off + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->stepped_offset += pg_sz; st->frag_off += pg_sz; if (st->frag_off == skb_frag_size(frag)) { st->frag_off = 0; st->frag_idx++; } } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; } else if (st->cur_skb->next) { st->cur_skb = st->cur_skb->next; st->frag_idx = 0; goto next_skb; } return 0; } EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { return skb_seq_read(offset, text, TS_SKB_CB(state)); } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { skb_abort_seq_read(TS_SKB_CB(state)); } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { struct ts_state state; unsigned int ret; BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); return (ret <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < MAX_SKB_FRAGS) { get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } return 0; } EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len); return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { skb_frag_t head_frag; struct page *page; page = virt_to_head_page(frag_skb->head); __skb_frag_set_page(&head_frag, page); skb_frag_off_set(&head_frag, frag_skb->data - (unsigned char *)page_address(page)); skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); return head_frag; } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ err = skb_unclone(skb, GFP_ATOMIC); if (err) goto err_linearize; skb_shinfo(skb)->frag_list = NULL; while (list_skb) { nskb = list_skb; list_skb = list_skb->next; err = 0; delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { consume_skb(nskb); nskb = tmp; err = skb_unclone(nskb, GFP_ATOMIC); } else { err = -ENOMEM; } } if (!tail) skb->next = nskb; else tail->next = nskb; if (unlikely(err)) { nskb->next = list_skb; goto err_linearize; } tail = nskb; delta_len += nskb->len; skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; skb_gso_reset(skb); skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto err_linearize; skb_get(skb); return skb; err_linearize: kfree_skb_list(skb->next); skb->next = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(skb_segment_list); int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) { if (unlikely(p->len + skb->len >= 65536)) return -E2BIG; if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; skb_pull(skb, skb_gro_offset(skb)); NAPI_GRO_CB(p)->last = skb; NAPI_GRO_CB(p)->count++; p->data_len += skb->len; /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; NAPI_GRO_CB(skb)->same_flow = 1; return 0; } /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; struct sk_buff *frag_skb; skb_frag_t *frag; __be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { struct sk_buff *check_skb; for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG. */ features &= ~NETIF_F_SG; break; } } } __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; /* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length. */ frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal; len -= iter->len; } if (len != frag_len) goto normal; } /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS. */ partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else partial_segs = 0; } normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); if (skb_orphan_frags(head_skb, GFP_ATOMIC)) return ERR_PTR(-ENOMEM); nfrags = skb_shinfo(head_skb)->nr_frags; frag = skb_shinfo(head_skb)->frags; frag_skb = head_skb; do { struct sk_buff *nskb; skb_frag_t *nskb_frag; int hsize; int size; if (unlikely(mss == GSO_BY_FRAGS)) { len = list_skb->len; } else { len = head_skb->len - offset; if (len > mss) len = mss; } hsize = skb_headlen(head_skb) - offset; if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); nskb = skb_clone(list_skb, GFP_ATOMIC); if (unlikely(!nskb)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; frag++; } list_skb = list_skb->next; if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; } hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) goto err; skb_reserve(nskb, headroom); __skb_put(nskb, doffset); } if (segs) tail->next = nskb; else segs = nskb; tail = nskb; __copy_skb_header(nskb, head_skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { if (!csum) { if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) goto err; } continue; } nskb_frag = skb_shinfo(nskb)->frags; skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { if (skb_orphan_frags(list_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, list_skb, GFP_ATOMIC)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { BUG_ON(!list_skb->head_frag); /* to make room for head_frag. */ i--; frag--; } list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS)) { net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); err = -EINVAL; goto err; } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; __skb_frag_ref(nskb_frag); size = skb_frag_size(nskb_frag); if (pos < offset) { skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; frag++; pos += size; } else { skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; perform_csum_check: if (!csum) { if (skb_has_shared_frag(nskb) && __skb_linearize(nskb)) goto err; if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); /* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example) */ segs->prev = tail; if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ for (iter = segs; iter; iter = iter->next) { skb_shinfo(iter)->gso_size = gso_size; skb_shinfo(iter)->gso_segs = partial_segs; skb_shinfo(iter)->gso_type = type; SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; } if (tail->len - doffset <= gso_size) skb_shinfo(tail)->gso_size = 0; else if (tail != segs) skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. */ if (head_skb->destructor == sock_wfree) { swap(tail->truesize, head_skb->truesize); swap(tail->destructor, head_skb->destructor); swap(tail->sk, head_skb->sk); } return segs; err: kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; unsigned int new_truesize; struct sk_buff *lp; if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { skb_frag_t *frag; skb_frag_t *frag2; int i = skbinfo->nr_frags; int nr_frags = pinfo->nr_frags + i; if (nr_frags > MAX_SKB_FRAGS) goto merge; offset -= headlen; pinfo->nr_frags = nr_frags; skbinfo->nr_frags = 0; frag = pinfo->frags + nr_frags; frag2 = skbinfo->frags + i; do { *--frag = *--frag2; } while (--i); skb_frag_off_add(frag, offset); skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); delta_truesize = skb->truesize - new_truesize; skb->truesize = new_truesize; skb->len -= skb->data_len; skb->data_len = 0; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; goto done; } else if (skb->head_frag) { int nr_frags = pinfo->nr_frags; skb_frag_t *frag = pinfo->frags + nr_frags; struct page *page = virt_to_head_page(skb->head); unsigned int first_size = headlen - offset; unsigned int first_offset; if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) goto merge; first_offset = skb->data - (unsigned char *)page_address(page) + offset; pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; __skb_frag_set_page(frag, page); skb_frag_off_set(frag, first_offset); skb_frag_size_set(frag, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); /* We dont need to clear skbinfo->nr_frags here */ new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); delta_truesize = skb->truesize - new_truesize; skb->truesize = new_truesize; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } merge: /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; skb_frag_off_add(&skbinfo->frags[0], eat); skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; offset = headlen; } __skb_pull(skb, offset); if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; NAPI_GRO_CB(p)->last = skb; __skb_header_release(skb); lp = p; done: NAPI_GRO_CB(p)->count++; p->data_len += len; p->truesize += delta_truesize; p->len += len; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; } NAPI_GRO_CB(skb)->same_flow = 1; return 0; } #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info), #endif #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif }; static __always_inline unsigned int skb_ext_total_length(void) { return SKB_EXT_CHUNKSIZEOF(struct skb_ext) + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) skb_ext_type_len[SKB_EXT_BRIDGE_NF] + #endif #ifdef CONFIG_XFRM skb_ext_type_len[SKB_EXT_SEC_PATH] + #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) skb_ext_type_len[TC_SKB_EXT] + #endif #if IS_ENABLED(CONFIG_MPTCP) skb_ext_type_len[SKB_EXT_MPTCP] + #endif 0; } static void skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM >= 8); BUILD_BUG_ON(skb_ext_total_length() > 255); skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } #else static void skb_extensions_init(void) {} #endif void __init skb_init(void) { skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); skb_extensions_init(); } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; if (unlikely(recursion_level >= 24)) return -EMSGSIZE; if (copy > 0) { if (copy > len) copy = len; sg_set_buf(sg, skb->data + offset, copy); elt++; if ((len -= copy) == 0) return elt; offset += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, copy, recursion_level + 1); if (unlikely(ret < 0)) return ret; elt += ret; if ((len -= copy) == 0) return elt; offset += copy; } start = end; } BUG_ON(len); return elt; } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); if (nsg <= 0) return nsg; sg_mark_end(&sg[nsg - 1]); return nsg; } EXPORT_SYMBOL_GPL(skb_to_sgvec); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping mutilple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { int copyflag; int elt; struct sk_buff *skb1, **skb_p; /* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more * space, 128 bytes is fair. */ if (skb_tailroom(skb) < tailbits && pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) return -ENOMEM; /* Voila! */ *trailer = skb; return 1; } /* Misery. We are in troubles, going to mincer fragments... */ elt = 1; skb_p = &skb_shinfo(skb)->frag_list; copyflag = 0; while ((skb1 = *skb_p) != NULL) { int ntail = 0; /* The fragment is partially pulled by someone, * this can happen on input. Copy it and everything * after it. */ if (skb_shared(skb1)) copyflag = 1; /* If the skb is the last, worry about trailer. */ if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } if (copyflag || skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ if (ntail == 0) skb2 = skb_copy(skb1, GFP_ATOMIC); else skb2 = skb_copy_expand(skb1, skb_headroom(skb1), ntail, GFP_ATOMIC); if (unlikely(skb2 == NULL)) return -ENOMEM; if (skb1->sk) skb_set_owner_w(skb2, skb1->sk); /* Looking around. Are we still alive? * OK, link new skb, drop old one */ skb2->next = skb1->next; *skb_p = skb2; kfree_skb(skb1); skb1 = skb2; } elt++; *trailer = skb1; skb_p = &skb1->next; } return elt; } EXPORT_SYMBOL_GPL(skb_cow_data); static void sock_rmem_free(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } static void skb_set_err_queue(struct sk_buff *skb) { /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. * So, it is safe to (mis)use it to mark skbs on the error queue. */ skb->pkt_type = PACKET_OUTGOING; BUILD_BUG_ON(PACKET_OUTGOING == 0); } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); static bool is_icmp_err_skb(const struct sk_buff *skb) { return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6); } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { struct sk_buff_head *q = &sk->sk_error_queue; struct sk_buff *skb, *skb_next = NULL; bool icmp_next = false; unsigned long flags; spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) sk->sk_err = 0; if (skb_next) sk_error_report(sk); return skb; } EXPORT_SYMBOL(sock_dequeue_err_skb); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sk_buff *clone; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return NULL; } clone->sk = sk; clone->destructor = sock_efree; return clone; } EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { struct sock_exterr_skb *serr; int err; BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); ret = sk->sk_socket && sk->sk_socket->file && file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW); read_unlock_bh(&sk->sk_callback_lock); return ret; } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); return; } err: kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { struct sk_buff *skb; bool tsonly, opt_stats = false; if (!sk) return; if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); opt_stats = true; } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { kfree_skb(skb); return; } } if (!skb) return; if (tsonly) { skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else skb->tstamp = ktime_get_real(); __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } if (err) kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; skb_set_transport_header(skb, start); return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { if (skb_headlen(skb) >= len) return 0; /* If we need to pullup then pullup to the max, so we * won't need to do it again. */ if (max > skb->len) max = skb->len; if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) return -ENOMEM; if (skb_headlen(skb) < len) return -EPROTO; return 0; } #define MAX_TCP_HDR_LEN (15 * 4) static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { int err; switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; case IPPROTO_UDP: err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), off + sizeof(struct udphdr)); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct udphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &udp_hdr(skb)->check; } return ERR_PTR(-EPROTO); } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; __sum16 *csum; int err; fragment = false; err = skb_maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN); if (err < 0) goto out; if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); err = -EPROTO; if (fragment) goto out; csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - off, ip_hdr(skb)->protocol, 0); err = 0; out: return err; } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN 256 #define OPT_HDR(type, skb, off) \ (type *)(skb_network_header(skb) + (off)) static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { int err; u8 nexthdr; unsigned int off; unsigned int len; bool fragment; bool done; __sum16 *csum; fragment = false; done = false; off = sizeof(struct ipv6hdr); err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); if (err < 0) goto out; nexthdr = ipv6_hdr(skb)->nexthdr; len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ipv6_opt_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { struct ip_auth_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ip_auth_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ip_auth_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_authlen(hp); break; } case IPPROTO_FRAGMENT: { struct frag_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct frag_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct frag_hdr, skb, off); if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) fragment = true; nexthdr = hp->nexthdr; off += sizeof(struct frag_hdr); break; } default: done = true; break; } } err = -EPROTO; if (!done || fragment) goto out; csum = skb_checksum_setup_ip(skb, nexthdr, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - off, nexthdr, 0); err = 0; out: return err; } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { int err; switch (skb->protocol) { case htons(ETH_P_IP): err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): err = skb_checksum_setup_ipv6(skb, recalculate); break; default: err = -EPROTO; break; } return err; } EXPORT_SYMBOL(skb_checksum_setup); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { struct sk_buff *skb_chk; unsigned int len = skb_transport_offset(skb) + transport_len; int ret; if (skb->len < len) return NULL; else if (skb->len == len) return skb; skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL; ret = pskb_trim_rcsum(skb_chk, len); if (ret) { kfree_skb(skb_chk); return NULL; } return skb_chk; } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { struct sk_buff *skb_chk; unsigned int offset = skb_transport_offset(skb); __sum16 ret; skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err; if (!pskb_may_pull(skb_chk, offset)) goto err; skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); skb_push_rcsum(skb_chk, offset); if (ret) goto err; return skb_chk; err: if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return NULL; } EXPORT_SYMBOL(skb_checksum_trimmed); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); kmem_cache_free(skbuff_head_cache, skb); } else { __kfree_skb(skb); } } EXPORT_SYMBOL(kfree_skb_partial); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; if (skb_cloned(to)) return false; /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. Additionally avoid dealing with clones * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. * In theory we could take full references if @from is cloned and * !@to->pp_recycle but its tricky (due to potential race with * the clone disappearing) and rare, so not worth dealing with. */ if (to->pp_recycle != from->pp_recycle || (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; return true; } to_shinfo = skb_shinfo(to); from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; if (skb_headlen(from) != 0) { struct page *page; unsigned int offset; if (to_shinfo->nr_frags + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) return false; delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { if (to_shinfo->nr_frags + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); memcpy(to_shinfo->frags + to_shinfo->nr_frags, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ for (i = 0; i < from_shinfo->nr_frags; i++) __skb_frag_ref(&from_shinfo->frags[i]); to->truesize += delta; to->len += len; to->data_len += len; *delta_truesize = delta; return true; } EXPORT_SYMBOL(skb_try_coalesce); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulting a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif if (!xnet) return; ipvs_reset(skb); skb->mark = 0; skb->tstamp = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet); /** * skb_gso_transport_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_transport_seglen is used to determine the real size of the * individual segments, including Layer4 headers (TCP/UDP). * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; if (skb->encapsulation) { thlen = skb_inner_transport_header(skb) - skb_transport_header(skb); if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already * accounted for. */ return thlen + shinfo->gso_size; } /** * skb_gso_network_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_network_seglen is used to determine the real size of the * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). * * The MAC/L2 header is not accounted for. */ static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_mac_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_mac_seglen is used to determine the real size of the * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 * headers (TCP/UDP). */ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS * * There are a couple of instances where we have a GSO skb, and we * want to determine what size it would be after it is segmented. * * We might want to check: * - L3+L4+payload size (e.g. IP forwarding) * - L2+L3+L4+payload size (e.g. sanity check before passing to driver) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * * @skb: GSO skb * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * * @max_len: The maximum permissible length. * * Returns true if the segmented length <= max length. */ static inline bool skb_gso_size_check(const struct sk_buff *skb, unsigned int seg_len, unsigned int max_len) { const struct skb_shared_info *shinfo = skb_shinfo(skb); const struct sk_buff *iter; if (shinfo->gso_size != GSO_BY_FRAGS) return seg_len <= max_len; /* Undo this so we can re-use header sizes */ seg_len -= GSO_BY_FRAGS; skb_walk_frags(skb, iter) { if (seg_len + skb_headlen(iter) > max_len) return false; } return true; } /** * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * * skb_gso_validate_network_len validates if a given skb will fit a * wanted MTU once split. It considers L3 headers, L4 headers, and the * payload. */ bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? * * @skb: GSO skb * @len: length to validate against * * skb_gso_validate_mac_len validates if a given skb will fit a wanted * length once split, including L2, L3 and L4 headers and the payload. */ bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len) { return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len); } EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { int mac_len, meta_len; void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } meta_len = skb_metadata_len(skb); if (meta_len) { meta = skb_metadata_end(skb) - meta_len; memmove(meta + VLAN_HLEN, meta, meta_len); } skb->mac_header += VLAN_HLEN; return skb; } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { struct vlan_hdr *vhdr; u16 vlan_tci; if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb); if (unlikely(!skb)) goto err_free; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); return skb; err_free: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_vlan_untag); int skb_ensure_writable(struct sk_buff *skb, int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr; int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); __skb_pull(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; if (skb_network_offset(skb) < ETH_HLEN) skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return err; } EXPORT_SYMBOL(__skb_vlan_pop); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { u16 vlan_tci; __be16 vlan_proto; int err; if (likely(skb_vlan_tag_present(skb))) { __vlan_hwaccel_clear_tag(skb); } else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err; } /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; err = __skb_vlan_pop(skb, &vlan_tci); if (unlikely(err)) return err; __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_pop); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; skb->mac_len += VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_push); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || skb_network_offset(skb) < ETH_HLEN) return -EPROTO; skb_pull_rcsum(skb, ETH_HLEN); skb_reset_mac_header(skb); skb_reset_mac_len(skb); return 0; } EXPORT_SYMBOL(skb_eth_pop); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { struct ethhdr *eth; int err; if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO; err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err; skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_reset_mac_len(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_dest, dst); ether_addr_copy(eth->h_source, src); eth->h_proto = skb->protocol; skb_postpush_rcsum(skb, eth, sizeof(*eth)); return 0; } EXPORT_SYMBOL(skb_eth_push); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { if (skb->ip_summed == CHECKSUM_COMPLETE) { __be16 diff[] = { ~hdr->h_proto, ethertype }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } hdr->h_proto = ethertype; } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL; /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL; err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err; if (!skb->inner_protocol) { skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_push); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return 0; err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN); skb_mod_eth_type(skb, hdr, next_proto); } skb->protocol = next_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } mpls_hdr(skb)->label_stack_entry = mpls_lse; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_update_lse); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { u32 lse; u8 ttl; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) return -ENOMEM; lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) return -EINVAL; lse &= ~MPLS_LS_TTL_MASK; lse |= ttl << MPLS_LS_TTL_SHIFT; return skb_mpls_update_lse(skb, cpu_to_be32(lse)); } EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @max_page_order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask) { int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; unsigned long chunk; struct sk_buff *skb; struct page *page; int i; *errcode = -EMSGSIZE; /* Note this test could be relaxed, if we succeed to allocate * high order pages... */ if (npages > MAX_SKB_FRAGS) return NULL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; skb->truesize += npages << PAGE_SHIFT; for (i = 0; npages > 0; i++) { int order = max_page_order; while (order) { if (npages >= 1 << order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN, order); if (page) goto fill_page; /* Do not retry other high order allocations */ order = 1; max_page_order = 0; } order--; } page = alloc_page(gfp_mask); if (!page) goto failure; fill_page: chunk = min_t(unsigned long, data_len, PAGE_SIZE << order); skb_fill_page_desc(skb, i, page, 0, chunk); data_len -= chunk; npages -= 1 << order; } return skb; failure: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(alloc_skb_with_frags); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb); } else { /* we can reuse existing recount- all we did was * relocate values */ skb_free_head(skb); } skb->head = data; skb->data = data; skb->head_frag = 0; skb_set_end_offset(skb, size); skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct sk_buff *skb, struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (!list) { pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT; } if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_shared(list)) { clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM; insp = list->next; list = clone; } else { /* This may be pulled without problems. */ insp = list; } if (pskb_carve(list, eat, gfp_mask) < 0) { kfree_skb(clone); return -ENOMEM; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; shinfo->frag_list = clone; } return 0; } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(ksize(data)); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + fsize > off) { shinfo->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); k++; } pos += fsize; } shinfo->nr_frags = k; if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); /* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); kfree(data); return -ENOMEM; } skb_release_data(skb); skb->head = data; skb->head_frag = 0; skb->data = data; skb_set_end_offset(skb, size); skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; skb->len -= off; skb->data_len = skb->len; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { int headlen = skb_headlen(skb); if (len < headlen) return pskb_carve_inside_header(skb, len, headlen, gfp); else return pskb_carve_inside_nonlinear(skb, len, headlen, gfp); } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { struct sk_buff *clone = skb_clone(skb, gfp); if (!clone) return NULL; if (pskb_carve(clone, off, gfp) < 0 || pskb_trim(clone, to_copy)) { kfree_skb(clone); return NULL; } return clone; } EXPORT_SYMBOL(pskb_extract); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb)) return; /* Nice, we can free page frag(s) right now */ __pskb_pull_tail(skb, skb->data_len); } /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize. */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags); if (new) { memset(new->offset, 0, sizeof(new->offset)); refcount_set(&new->refcnt, 1); } return new; } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { struct skb_ext *new; if (refcount_read(&old->refcnt) == 1) return old; new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); if (!new) return NULL; memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE); refcount_set(&new->refcnt, 1); #ifdef CONFIG_XFRM if (old_active & (1 << SKB_EXT_SEC_PATH)) { struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH); unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } #endif __skb_ext_put(old); return new; } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); skb_ext_put(skb); newlen = newoff + skb_ext_type_len[id]; ext->chunks = newlen; ext->offset[id] = newoff; skb->extensions = ext; skb->active_extensions = 1 << id; return skb_ext_get_ptr(ext, id); } /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *new, *old = NULL; unsigned int newlen, newoff; if (skb->active_extensions) { old = skb->extensions; new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL; if (__skb_ext_exist(new, id)) goto set_active; newoff = new->chunks; } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); new = __skb_ext_alloc(GFP_ATOMIC); if (!new) return NULL; } newlen = newoff + skb_ext_type_len[id]; new->chunks = newlen; new->offset[id] = newoff; set_active: skb->slow_gro = 1; skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); } EXPORT_SYMBOL(skb_ext_add); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_put(sp->xvec[i]); } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; skb->active_extensions &= ~(1 << id); if (skb->active_extensions == 0) { skb->extensions = NULL; __skb_ext_put(ext); #ifdef CONFIG_XFRM } else if (id == SKB_EXT_SEC_PATH && refcount_read(&ext->refcnt) == 1) { struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH); skb_ext_put_sp(sp); sp->len = 0; #endif } } EXPORT_SYMBOL(__skb_ext_del); void __skb_ext_put(struct skb_ext *ext) { /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op. */ if (refcount_read(&ext->refcnt) == 1) goto free_now; if (!refcount_dec_and_test(&ext->refcnt)) return; free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif kmem_cache_free(skbuff_ext_cache, ext); } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ |
| 361 17 359 | 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 | /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2005, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005 Intel Corporation. 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/mutex.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/module.h> #include <net/arp.h> #include <net/neighbour.h> #include <net/route.h> #include <net/netevent.h> #include <net/ipv6_stubs.h> #include <net/ip6_route.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> #include <rdma/ib_sa.h> #include <rdma/ib.h> #include <rdma/rdma_netlink.h> #include <net/netlink.h> #include "core_priv.h" struct addr_req { struct list_head list; struct sockaddr_storage src_addr; struct sockaddr_storage dst_addr; struct rdma_dev_addr *addr; void *context; void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context); unsigned long timeout; struct delayed_work work; bool resolve_by_gid_attr; /* Consider gid attr in resolve phase */ int status; u32 seq; }; static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0); static DEFINE_SPINLOCK(lock); static LIST_HEAD(req_list); static struct workqueue_struct *addr_wq; static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { [LS_NLA_TYPE_DGID] = {.type = NLA_BINARY, .len = sizeof(struct rdma_nla_ls_gid), .validation_type = NLA_VALIDATE_MIN, .min = sizeof(struct rdma_nla_ls_gid)}, }; static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh) { struct nlattr *tb[LS_NLA_TYPE_MAX] = {}; int ret; if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR) return false; ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh), nlmsg_len(nlh), ib_nl_addr_policy, NULL); if (ret) return false; return true; } static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh) { const struct nlattr *head, *curr; union ib_gid gid; struct addr_req *req; int len, rem; int found = 0; head = (const struct nlattr *)nlmsg_data(nlh); len = nlmsg_len(nlh); nla_for_each_attr(curr, head, len, rem) { if (curr->nla_type == LS_NLA_TYPE_DGID) memcpy(&gid, nla_data(curr), nla_len(curr)); } spin_lock_bh(&lock); list_for_each_entry(req, &req_list, list) { if (nlh->nlmsg_seq != req->seq) continue; /* We set the DGID part, the rest was set earlier */ rdma_addr_set_dgid(req->addr, &gid); req->status = 0; found = 1; break; } spin_unlock_bh(&lock); if (!found) pr_info("Couldn't find request waiting for DGID: %pI6\n", &gid); } int ib_nl_handle_ip_res_resp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { if ((nlh->nlmsg_flags & NLM_F_REQUEST) || !(NETLINK_CB(skb).sk)) return -EPERM; if (ib_nl_is_good_ip_resp(nlh)) ib_nl_process_good_ip_rsep(nlh); return 0; } static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr, const void *daddr, u32 seq, u16 family) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; struct rdma_ls_ip_resolve_header *header; void *data; size_t size; int attrtype; int len; if (family == AF_INET) { size = sizeof(struct in_addr); attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4; } else { size = sizeof(struct in6_addr); attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6; } len = nla_total_size(sizeof(size)); len += NLMSG_ALIGN(sizeof(*header)); skb = nlmsg_new(len, GFP_KERNEL); if (!skb) return -ENOMEM; data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS, RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST); if (!data) { nlmsg_free(skb); return -ENODATA; } /* Construct the family header first */ header = skb_put(skb, NLMSG_ALIGN(sizeof(*header))); header->ifindex = dev_addr->bound_dev_if; nla_put(skb, attrtype, size, daddr); /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, GFP_KERNEL); /* Make the request retry, so when we get the response from userspace * we will have something. */ return -ENODATA; } int rdma_addr_size(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return sizeof(struct sockaddr_in); case AF_INET6: return sizeof(struct sockaddr_in6); case AF_IB: return sizeof(struct sockaddr_ib); default: return 0; } } EXPORT_SYMBOL(rdma_addr_size); int rdma_addr_size_in6(struct sockaddr_in6 *addr) { int ret = rdma_addr_size((struct sockaddr *) addr); return ret <= sizeof(*addr) ? ret : 0; } EXPORT_SYMBOL(rdma_addr_size_in6); int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr) { int ret = rdma_addr_size((struct sockaddr *) addr); return ret <= sizeof(*addr) ? ret : 0; } EXPORT_SYMBOL(rdma_addr_size_kss); /** * rdma_copy_src_l2_addr - Copy netdevice source addresses * @dev_addr: Destination address pointer where to copy the addresses * @dev: Netdevice whose source addresses to copy * * rdma_copy_src_l2_addr() copies source addresses from the specified netdevice. * This includes unicast address, broadcast address, device type and * interface index. */ void rdma_copy_src_l2_addr(struct rdma_dev_addr *dev_addr, const struct net_device *dev) { dev_addr->dev_type = dev->type; memcpy(dev_addr->src_dev_addr, dev->dev_addr, MAX_ADDR_LEN); memcpy(dev_addr->broadcast, dev->broadcast, MAX_ADDR_LEN); dev_addr->bound_dev_if = dev->ifindex; } EXPORT_SYMBOL(rdma_copy_src_l2_addr); static struct net_device * rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in) { struct net_device *dev = NULL; int ret = -EADDRNOTAVAIL; switch (src_in->sa_family) { case AF_INET: dev = __ip_dev_find(net, ((const struct sockaddr_in *)src_in)->sin_addr.s_addr, false); if (dev) ret = 0; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: for_each_netdev_rcu(net, dev) { if (ipv6_chk_addr(net, &((const struct sockaddr_in6 *)src_in)->sin6_addr, dev, 1)) { ret = 0; break; } } break; #endif } return ret ? ERR_PTR(ret) : dev; } int rdma_translate_ip(const struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { struct net_device *dev; if (dev_addr->bound_dev_if) { dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!dev) return -ENODEV; rdma_copy_src_l2_addr(dev_addr, dev); dev_put(dev); return 0; } rcu_read_lock(); dev = rdma_find_ndev_for_src_ip_rcu(dev_addr->net, addr); if (!IS_ERR(dev)) rdma_copy_src_l2_addr(dev_addr, dev); rcu_read_unlock(); return PTR_ERR_OR_ZERO(dev); } EXPORT_SYMBOL(rdma_translate_ip); static void set_timeout(struct addr_req *req, unsigned long time) { unsigned long delay; delay = time - jiffies; if ((long)delay < 0) delay = 0; mod_delayed_work(addr_wq, &req->work, delay); } static void queue_req(struct addr_req *req) { spin_lock_bh(&lock); list_add_tail(&req->list, &req_list); set_timeout(req, req->timeout); spin_unlock_bh(&lock); } static int ib_nl_fetch_ha(struct rdma_dev_addr *dev_addr, const void *daddr, u32 seq, u16 family) { if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) return -EADDRNOTAVAIL; return ib_nl_ip_send_msg(dev_addr, daddr, seq, family); } static int dst_fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr, const void *daddr) { struct neighbour *n; int ret = 0; n = dst_neigh_lookup(dst, daddr); if (!n) return -ENODATA; if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); ret = -ENODATA; } else { neigh_ha_snapshot(dev_addr->dst_dev_addr, n, dst->dev); } neigh_release(n); return ret; } static bool has_gateway(const struct dst_entry *dst, sa_family_t family) { struct rtable *rt; struct rt6_info *rt6; if (family == AF_INET) { rt = container_of(dst, struct rtable, dst); return rt->rt_uses_gateway; } rt6 = container_of(dst, struct rt6_info, dst); return rt6->rt6i_flags & RTF_GATEWAY; } static int fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr, const struct sockaddr *dst_in, u32 seq) { const struct sockaddr_in *dst_in4 = (const struct sockaddr_in *)dst_in; const struct sockaddr_in6 *dst_in6 = (const struct sockaddr_in6 *)dst_in; const void *daddr = (dst_in->sa_family == AF_INET) ? (const void *)&dst_in4->sin_addr.s_addr : (const void *)&dst_in6->sin6_addr; sa_family_t family = dst_in->sa_family; might_sleep(); /* If we have a gateway in IB mode then it must be an IB network */ if (has_gateway(dst, family) && dev_addr->network == RDMA_NETWORK_IB) return ib_nl_fetch_ha(dev_addr, daddr, seq, family); else return dst_fetch_ha(dst, dev_addr, daddr); } static int addr4_resolve(struct sockaddr *src_sock, const struct sockaddr *dst_sock, struct rdma_dev_addr *addr, struct rtable **prt) { struct sockaddr_in *src_in = (struct sockaddr_in *)src_sock; const struct sockaddr_in *dst_in = (const struct sockaddr_in *)dst_sock; __be32 src_ip = src_in->sin_addr.s_addr; __be32 dst_ip = dst_in->sin_addr.s_addr; struct rtable *rt; struct flowi4 fl4; int ret; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = dst_ip; fl4.saddr = src_ip; fl4.flowi4_oif = addr->bound_dev_if; rt = ip_route_output_key(addr->net, &fl4); ret = PTR_ERR_OR_ZERO(rt); if (ret) return ret; src_in->sin_addr.s_addr = fl4.saddr; addr->hoplimit = ip4_dst_hoplimit(&rt->dst); *prt = rt; return 0; } #if IS_ENABLED(CONFIG_IPV6) static int addr6_resolve(struct sockaddr *src_sock, const struct sockaddr *dst_sock, struct rdma_dev_addr *addr, struct dst_entry **pdst) { struct sockaddr_in6 *src_in = (struct sockaddr_in6 *)src_sock; const struct sockaddr_in6 *dst_in = (const struct sockaddr_in6 *)dst_sock; struct flowi6 fl6; struct dst_entry *dst; memset(&fl6, 0, sizeof fl6); fl6.daddr = dst_in->sin6_addr; fl6.saddr = src_in->sin6_addr; fl6.flowi6_oif = addr->bound_dev_if; dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL); if (IS_ERR(dst)) return PTR_ERR(dst); if (ipv6_addr_any(&src_in->sin6_addr)) src_in->sin6_addr = fl6.saddr; addr->hoplimit = ip6_dst_hoplimit(dst); *pdst = dst; return 0; } #else static int addr6_resolve(struct sockaddr *src_sock, const struct sockaddr *dst_sock, struct rdma_dev_addr *addr, struct dst_entry **pdst) { return -EADDRNOTAVAIL; } #endif static int addr_resolve_neigh(const struct dst_entry *dst, const struct sockaddr *dst_in, struct rdma_dev_addr *addr, unsigned int ndev_flags, u32 seq) { int ret = 0; if (ndev_flags & IFF_LOOPBACK) { memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN); } else { if (!(ndev_flags & IFF_NOARP)) { /* If the device doesn't do ARP internally */ ret = fetch_ha(dst, addr, dst_in, seq); } } return ret; } static int copy_src_l2_addr(struct rdma_dev_addr *dev_addr, const struct sockaddr *dst_in, const struct dst_entry *dst, const struct net_device *ndev) { int ret = 0; if (dst->dev->flags & IFF_LOOPBACK) ret = rdma_translate_ip(dst_in, dev_addr); else rdma_copy_src_l2_addr(dev_addr, dst->dev); /* * If there's a gateway and type of device not ARPHRD_INFINIBAND, * we're definitely in RoCE v2 (as RoCE v1 isn't routable) set the * network type accordingly. */ if (has_gateway(dst, dst_in->sa_family) && ndev->type != ARPHRD_INFINIBAND) dev_addr->network = dst_in->sa_family == AF_INET ? RDMA_NETWORK_IPV4 : RDMA_NETWORK_IPV6; else dev_addr->network = RDMA_NETWORK_IB; return ret; } static int rdma_set_src_addr_rcu(struct rdma_dev_addr *dev_addr, unsigned int *ndev_flags, const struct sockaddr *dst_in, const struct dst_entry *dst) { struct net_device *ndev = READ_ONCE(dst->dev); *ndev_flags = ndev->flags; /* A physical device must be the RDMA device to use */ if (ndev->flags & IFF_LOOPBACK) { /* * RDMA (IB/RoCE, iWarp) doesn't run on lo interface or * loopback IP address. So if route is resolved to loopback * interface, translate that to a real ndev based on non * loopback IP address. */ ndev = rdma_find_ndev_for_src_ip_rcu(dev_net(ndev), dst_in); if (IS_ERR(ndev)) return -ENODEV; } return copy_src_l2_addr(dev_addr, dst_in, dst, ndev); } static int set_addr_netns_by_gid_rcu(struct rdma_dev_addr *addr) { struct net_device *ndev; ndev = rdma_read_gid_attr_ndev_rcu(addr->sgid_attr); if (IS_ERR(ndev)) return PTR_ERR(ndev); /* * Since we are holding the rcu, reading net and ifindex * are safe without any additional reference; because * change_net_namespace() in net/core/dev.c does rcu sync * after it changes the state to IFF_DOWN and before * updating netdev fields {net, ifindex}. */ addr->net = dev_net(ndev); addr->bound_dev_if = ndev->ifindex; return 0; } static void rdma_addr_set_net_defaults(struct rdma_dev_addr *addr) { addr->net = &init_net; addr->bound_dev_if = 0; } static int addr_resolve(struct sockaddr *src_in, const struct sockaddr *dst_in, struct rdma_dev_addr *addr, bool resolve_neigh, bool resolve_by_gid_attr, u32 seq) { struct dst_entry *dst = NULL; unsigned int ndev_flags = 0; struct rtable *rt = NULL; int ret; if (!addr->net) { pr_warn_ratelimited("%s: missing namespace\n", __func__); return -EINVAL; } rcu_read_lock(); if (resolve_by_gid_attr) { if (!addr->sgid_attr) { rcu_read_unlock(); pr_warn_ratelimited("%s: missing gid_attr\n", __func__); return -EINVAL; } /* * If the request is for a specific gid attribute of the * rdma_dev_addr, derive net from the netdevice of the * GID attribute. */ ret = set_addr_netns_by_gid_rcu(addr); if (ret) { rcu_read_unlock(); return ret; } } if (src_in->sa_family == AF_INET) { ret = addr4_resolve(src_in, dst_in, addr, &rt); dst = &rt->dst; } else { ret = addr6_resolve(src_in, dst_in, addr, &dst); } if (ret) { rcu_read_unlock(); goto done; } ret = rdma_set_src_addr_rcu(addr, &ndev_flags, dst_in, dst); rcu_read_unlock(); /* * Resolve neighbor destination address if requested and * only if src addr translation didn't fail. */ if (!ret && resolve_neigh) ret = addr_resolve_neigh(dst, dst_in, addr, ndev_flags, seq); if (src_in->sa_family == AF_INET) ip_rt_put(rt); else dst_release(dst); done: /* * Clear the addr net to go back to its original state, only if it was * derived from GID attribute in this context. */ if (resolve_by_gid_attr) rdma_addr_set_net_defaults(addr); return ret; } static void process_one_req(struct work_struct *_work) { struct addr_req *req; struct sockaddr *src_in, *dst_in; req = container_of(_work, struct addr_req, work.work); if (req->status == -ENODATA) { src_in = (struct sockaddr *)&req->src_addr; dst_in = (struct sockaddr *)&req->dst_addr; req->status = addr_resolve(src_in, dst_in, req->addr, true, req->resolve_by_gid_attr, req->seq); if (req->status && time_after_eq(jiffies, req->timeout)) { req->status = -ETIMEDOUT; } else if (req->status == -ENODATA) { /* requeue the work for retrying again */ spin_lock_bh(&lock); if (!list_empty(&req->list)) set_timeout(req, req->timeout); spin_unlock_bh(&lock); return; } } req->callback(req->status, (struct sockaddr *)&req->src_addr, req->addr, req->context); req->callback = NULL; spin_lock_bh(&lock); /* * Although the work will normally have been canceled by the workqueue, * it can still be requeued as long as it is on the req_list. */ cancel_delayed_work(&req->work); if (!list_empty(&req->list)) { list_del_init(&req->list); kfree(req); } spin_unlock_bh(&lock); } int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr, unsigned long timeout_ms, void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context), bool resolve_by_gid_attr, void *context) { struct sockaddr *src_in, *dst_in; struct addr_req *req; int ret = 0; req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) return -ENOMEM; src_in = (struct sockaddr *) &req->src_addr; dst_in = (struct sockaddr *) &req->dst_addr; if (src_addr) { if (src_addr->sa_family != dst_addr->sa_family) { ret = -EINVAL; goto err; } memcpy(src_in, src_addr, rdma_addr_size(src_addr)); } else { src_in->sa_family = dst_addr->sa_family; } memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr)); req->addr = addr; req->callback = callback; req->context = context; req->resolve_by_gid_attr = resolve_by_gid_attr; INIT_DELAYED_WORK(&req->work, process_one_req); req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq); req->status = addr_resolve(src_in, dst_in, addr, true, req->resolve_by_gid_attr, req->seq); switch (req->status) { case 0: req->timeout = jiffies; queue_req(req); break; case -ENODATA: req->timeout = msecs_to_jiffies(timeout_ms) + jiffies; queue_req(req); break; default: ret = req->status; goto err; } return ret; err: kfree(req); return ret; } EXPORT_SYMBOL(rdma_resolve_ip); int roce_resolve_route_from_path(struct sa_path_rec *rec, const struct ib_gid_attr *attr) { union { struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid, dgid; struct rdma_dev_addr dev_addr = {}; int ret; might_sleep(); if (rec->roce.route_resolved) return 0; rdma_gid2ip((struct sockaddr *)&sgid, &rec->sgid); rdma_gid2ip((struct sockaddr *)&dgid, &rec->dgid); if (sgid._sockaddr.sa_family != dgid._sockaddr.sa_family) return -EINVAL; if (!attr || !attr->ndev) return -EINVAL; dev_addr.net = &init_net; dev_addr.sgid_attr = attr; ret = addr_resolve((struct sockaddr *)&sgid, (struct sockaddr *)&dgid, &dev_addr, false, true, 0); if (ret) return ret; if ((dev_addr.network == RDMA_NETWORK_IPV4 || dev_addr.network == RDMA_NETWORK_IPV6) && rec->rec_type != SA_PATH_REC_TYPE_ROCE_V2) return -EINVAL; rec->roce.route_resolved = true; return 0; } /** * rdma_addr_cancel - Cancel resolve ip request * @addr: Pointer to address structure given previously * during rdma_resolve_ip(). * rdma_addr_cancel() is synchronous function which cancels any pending * request if there is any. */ void rdma_addr_cancel(struct rdma_dev_addr *addr) { struct addr_req *req, *temp_req; struct addr_req *found = NULL; spin_lock_bh(&lock); list_for_each_entry_safe(req, temp_req, &req_list, list) { if (req->addr == addr) { /* * Removing from the list means we take ownership of * the req */ list_del_init(&req->list); found = req; break; } } spin_unlock_bh(&lock); if (!found) return; /* * sync canceling the work after removing it from the req_list * guarentees no work is running and none will be started. */ cancel_delayed_work_sync(&found->work); kfree(found); } EXPORT_SYMBOL(rdma_addr_cancel); struct resolve_cb_context { struct completion comp; int status; }; static void resolve_cb(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context) { ((struct resolve_cb_context *)context)->status = status; complete(&((struct resolve_cb_context *)context)->comp); } int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, const union ib_gid *dgid, u8 *dmac, const struct ib_gid_attr *sgid_attr, int *hoplimit) { struct rdma_dev_addr dev_addr; struct resolve_cb_context ctx; union { struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid_addr, dgid_addr; int ret; rdma_gid2ip((struct sockaddr *)&sgid_addr, sgid); rdma_gid2ip((struct sockaddr *)&dgid_addr, dgid); memset(&dev_addr, 0, sizeof(dev_addr)); dev_addr.net = &init_net; dev_addr.sgid_attr = sgid_attr; init_completion(&ctx.comp); ret = rdma_resolve_ip((struct sockaddr *)&sgid_addr, (struct sockaddr *)&dgid_addr, &dev_addr, 1000, resolve_cb, true, &ctx); if (ret) return ret; wait_for_completion(&ctx.comp); ret = ctx.status; if (ret) return ret; memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN); *hoplimit = dev_addr.hoplimit; return 0; } static int netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct addr_req *req; if (event == NETEVENT_NEIGH_UPDATE) { struct neighbour *neigh = ctx; if (neigh->nud_state & NUD_VALID) { spin_lock_bh(&lock); list_for_each_entry(req, &req_list, list) set_timeout(req, jiffies); spin_unlock_bh(&lock); } } return 0; } static struct notifier_block nb = { .notifier_call = netevent_callback }; int addr_init(void) { addr_wq = alloc_ordered_workqueue("ib_addr", 0); if (!addr_wq) return -ENOMEM; register_netevent_notifier(&nb); return 0; } void addr_cleanup(void) { unregister_netevent_notifier(&nb); destroy_workqueue(addr_wq); WARN_ON(!list_empty(&req_list)); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _DCCP_H #define _DCCP_H /* * net/dccp/dccp.h * * An implementation of the DCCP protocol * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> * Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz> */ #include <linux/dccp.h> #include <linux/ktime.h> #include <net/snmp.h> #include <net/sock.h> #include <net/tcp.h> #include "ackvec.h" /* * DCCP - specific warning and debugging macros. */ #define DCCP_WARN(fmt, ...) \ net_warn_ratelimited("%s: " fmt, __func__, ##__VA_ARGS__) #define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \ __FILE__, __LINE__, __func__) #define DCCP_BUG(a...) do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0) #define DCCP_BUG_ON(cond) do { if (unlikely((cond) != 0)) \ DCCP_BUG("\"%s\" holds (exception!)", \ __stringify(cond)); \ } while (0) #define DCCP_PRINTK(enable, fmt, args...) do { if (enable) \ printk(fmt, ##args); \ } while(0) #define DCCP_PR_DEBUG(enable, fmt, a...) DCCP_PRINTK(enable, KERN_DEBUG \ "%s: " fmt, __func__, ##a) #ifdef CONFIG_IP_DCCP_DEBUG extern bool dccp_debug; #define dccp_pr_debug(format, a...) DCCP_PR_DEBUG(dccp_debug, format, ##a) #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else #define dccp_pr_debug(format, a...) do {} while (0) #define dccp_pr_debug_cat(format, a...) do {} while (0) #define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; DECLARE_PER_CPU(unsigned int, dccp_orphan_count); void dccp_time_wait(struct sock *sk, int state, int timeo); /* * Set safe upper bounds for header and option length. Since Data Offset is 8 * bits (RFC 4340, sec. 5.1), the total header length can never be more than * 4 * 255 = 1020 bytes. The largest possible header length is 28 bytes (X=1): * - DCCP-Response with ACK Subheader and 4 bytes of Service code OR * - DCCP-Reset with ACK Subheader and 4 bytes of Reset Code fields * Hence a safe upper bound for the maximum option length is 1020-28 = 992 */ #define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t)) #define DCCP_MAX_PACKET_HDR 28 #define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR) #define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER) /* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */ #define DCCP_FEATNEG_OVERHEAD (32 * sizeof(uint32_t)) #define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ /* RFC 1122, 4.2.3.1 initial RTO value */ #define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ)) /* * The maximum back-off value for retransmissions. This is needed for * - retransmitting client-Requests (sec. 8.1.1), * - retransmitting Close/CloseReq when closing (sec. 8.3), * - feature-negotiation retransmission (sec. 6.6.3), * - Acks in client-PARTOPEN state (sec. 8.1.5). */ #define DCCP_RTO_MAX ((unsigned int)(64 * HZ)) /* * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4 */ #define DCCP_SANE_RTT_MIN 100 #define DCCP_FALLBACK_RTT (USEC_PER_SEC / 5) #define DCCP_SANE_RTT_MAX (3 * USEC_PER_SEC) /* sysctl variables for DCCP */ extern int sysctl_dccp_request_retries; extern int sysctl_dccp_retries1; extern int sysctl_dccp_retries2; extern int sysctl_dccp_tx_qlen; extern int sysctl_dccp_sync_ratelimit; /* * 48-bit sequence number arithmetic (signed and unsigned) */ #define INT48_MIN 0x800000000000LL /* 2^47 */ #define UINT48_MAX 0xFFFFFFFFFFFFLL /* 2^48 - 1 */ #define COMPLEMENT48(x) (0x1000000000000LL - (x)) /* 2^48 - x */ #define TO_SIGNED48(x) (((x) < INT48_MIN)? (x) : -COMPLEMENT48( (x))) #define TO_UNSIGNED48(x) (((x) >= 0)? (x) : COMPLEMENT48(-(x))) #define ADD48(a, b) (((a) + (b)) & UINT48_MAX) #define SUB48(a, b) ADD48((a), COMPLEMENT48(b)) static inline void dccp_inc_seqno(u64 *seqno) { *seqno = ADD48(*seqno, 1); } /* signed mod-2^48 distance: pos. if seqno1 < seqno2, neg. if seqno1 > seqno2 */ static inline s64 dccp_delta_seqno(const u64 seqno1, const u64 seqno2) { u64 delta = SUB48(seqno2, seqno1); return TO_SIGNED48(delta); } /* is seq1 < seq2 ? */ static inline int before48(const u64 seq1, const u64 seq2) { return (s64)((seq2 << 16) - (seq1 << 16)) > 0; } /* is seq1 > seq2 ? */ #define after48(seq1, seq2) before48(seq2, seq1) /* is seq2 <= seq1 <= seq3 ? */ static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3) { return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16); } static inline u64 max48(const u64 seq1, const u64 seq2) { return after48(seq1, seq2) ? seq1 : seq2; } /** * dccp_loss_count - Approximate the number of lost data packets in a burst loss * @s1: last known sequence number before the loss ('hole') * @s2: first sequence number seen after the 'hole' * @ndp: NDP count on packet with sequence number @s2 */ static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp) { s64 delta = dccp_delta_seqno(s1, s2); WARN_ON(delta < 0); delta -= ndp + 1; return delta > 0 ? delta : 0; } /** * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1 */ static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) { return dccp_loss_count(s1, s2, ndp) == 0; } enum { DCCP_MIB_NUM = 0, DCCP_MIB_ACTIVEOPENS, /* ActiveOpens */ DCCP_MIB_ESTABRESETS, /* EstabResets */ DCCP_MIB_CURRESTAB, /* CurrEstab */ DCCP_MIB_OUTSEGS, /* OutSegs */ DCCP_MIB_OUTRSTS, DCCP_MIB_ABORTONTIMEOUT, DCCP_MIB_TIMEOUTS, DCCP_MIB_ABORTFAILED, DCCP_MIB_PASSIVEOPENS, DCCP_MIB_ATTEMPTFAILS, DCCP_MIB_OUTDATAGRAMS, DCCP_MIB_INERRS, DCCP_MIB_OPTMANDATORYERROR, DCCP_MIB_INVALIDOPT, __DCCP_MIB_MAX }; #define DCCP_MIB_MAX __DCCP_MIB_MAX struct dccp_mib { unsigned long mibs[DCCP_MIB_MAX]; }; DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); #define DCCP_INC_STATS(field) SNMP_INC_STATS(dccp_statistics, field) #define __DCCP_INC_STATS(field) __SNMP_INC_STATS(dccp_statistics, field) #define DCCP_DEC_STATS(field) SNMP_DEC_STATS(dccp_statistics, field) /* * Checksumming routines */ static inline unsigned int dccp_csum_coverage(const struct sk_buff *skb) { const struct dccp_hdr* dh = dccp_hdr(skb); if (dh->dccph_cscov == 0) return skb->len; return (dh->dccph_doff + dh->dccph_cscov - 1) * sizeof(u32); } static inline void dccp_csum_outgoing(struct sk_buff *skb) { unsigned int cov = dccp_csum_coverage(skb); if (cov >= skb->len) dccp_hdr(skb)->dccph_cscov = 0; skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0); } void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); int dccp_retransmit_skb(struct sock *sk); void dccp_send_ack(struct sock *sk); void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *rsk); void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); /* * TX Packet Dequeueing Interface */ void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb); bool dccp_qpolicy_full(struct sock *sk); void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb); struct sk_buff *dccp_qpolicy_top(struct sock *sk); struct sk_buff *dccp_qpolicy_pop(struct sock *sk); bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param); /* * TX Packet Output and TX Timers */ void dccp_write_xmit(struct sock *sk); void dccp_write_space(struct sock *sk); void dccp_flush_write_queue(struct sock *sk, long *time_budget); void dccp_init_xmit_timers(struct sock *sk); static inline void dccp_clear_xmit_timers(struct sock *sk) { inet_csk_clear_xmit_timers(sk); } unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); const char *dccp_packet_name(const int type); void dccp_set_state(struct sock *sk, const int state); void dccp_done(struct sock *sk); int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp, struct sk_buff const *skb); int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *dccp_create_openreq_child(const struct sock *sk, const struct request_sock *req, const struct sk_buff *skb); int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req); int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct dccp_hdr *dh, unsigned int len); int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned int len); void dccp_destruct_common(struct sock *sk); int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk); void dccp_close(struct sock *sk, long timeout); struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst, struct request_sock *req); int dccp_connect(struct sock *sk); int dccp_disconnect(struct sock *sk, int flags); int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); void dccp_shutdown(struct sock *sk, int how); int inet_dccp_listen(struct socket *sock, int backlog); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait); int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); void dccp_req_err(struct sock *sk, u64 seq); struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb); int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); void dccp_send_close(struct sock *sk, const int active); int dccp_invalid_packet(struct sk_buff *skb); u32 dccp_sample_rtt(struct sock *sk, long delta); static inline bool dccp_bad_service_code(const struct sock *sk, const __be32 service) { const struct dccp_sock *dp = dccp_sk(sk); if (dp->dccps_service == service) return false; return !dccp_list_has_service(dp->dccps_service_list, service); } /** * dccp_skb_cb - DCCP per-packet control information * @dccpd_type: one of %dccp_pkt_type (or unknown) * @dccpd_ccval: CCVal field (5.1), see e.g. RFC 4342, 8.1 * @dccpd_reset_code: one of %dccp_reset_codes * @dccpd_reset_data: Data1..3 fields (depend on @dccpd_reset_code) * @dccpd_opt_len: total length of all options (5.8) in the packet * @dccpd_seq: sequence number * @dccpd_ack_seq: acknowledgment number subheader field value * * This is used for transmission as well as for reception. */ struct dccp_skb_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; __u8 dccpd_type:4; __u8 dccpd_ccval:4; __u8 dccpd_reset_code, dccpd_reset_data[3]; __u16 dccpd_opt_len; __u64 dccpd_seq; __u64 dccpd_ack_seq; }; #define DCCP_SKB_CB(__skb) ((struct dccp_skb_cb *)&((__skb)->cb[0])) /* RFC 4340, sec. 7.7 */ static inline int dccp_non_data_packet(const struct sk_buff *skb) { const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; return type == DCCP_PKT_ACK || type == DCCP_PKT_CLOSE || type == DCCP_PKT_CLOSEREQ || type == DCCP_PKT_RESET || type == DCCP_PKT_SYNC || type == DCCP_PKT_SYNCACK; } /* RFC 4340, sec. 7.7 */ static inline int dccp_data_packet(const struct sk_buff *skb) { const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; return type == DCCP_PKT_DATA || type == DCCP_PKT_DATAACK || type == DCCP_PKT_REQUEST || type == DCCP_PKT_RESPONSE; } static inline int dccp_packet_without_ack(const struct sk_buff *skb) { const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; return type == DCCP_PKT_DATA || type == DCCP_PKT_REQUEST; } #define DCCP_PKT_WITHOUT_ACK_SEQ (UINT48_MAX << 2) static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss) { struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh + sizeof(*dh)); dh->dccph_seq2 = 0; dh->dccph_seq = htons((gss >> 32) & 0xfffff); dhx->dccph_seq_low = htonl(gss & 0xffffffff); } static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack, const u64 gsr) { dhack->dccph_reserved1 = 0; dhack->dccph_ack_nr_high = htons(gsr >> 32); dhack->dccph_ack_nr_low = htonl(gsr & 0xffffffff); } static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); if (after48(seq, dp->dccps_gsr)) dp->dccps_gsr = seq; /* Sequence validity window depends on remote Sequence Window (7.5.1) */ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); /* * Adjust SWL so that it is not below ISR. In contrast to RFC 4340, * 7.5.1 we perform this check beyond the initial handshake: W/W' are * always > 32, so for the first W/W' packets in the lifetime of a * connection we always have to adjust SWL. * A second reason why we are doing this is that the window depends on * the feature-remote value of Sequence Window: nothing stops the peer * from updating this value while we are busy adjusting SWL for the * first W packets (we would have to count from scratch again then). * Therefore it is safer to always make sure that the Sequence Window * is not artificially extended by a peer who grows SWL downwards by * continually updating the feature-remote Sequence-Window. * If sequence numbers wrap it is bad luck. But that will take a while * (48 bit), and this measure prevents Sequence-number attacks. */ if (before48(dp->dccps_swl, dp->dccps_isr)) dp->dccps_swl = dp->dccps_isr; dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4); } static inline void dccp_update_gss(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); dp->dccps_gss = seq; /* Ack validity window depends on local Sequence Window value (7.5.1) */ dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win); /* Adjust AWL so that it is not below ISS - see comment above for SWL */ if (before48(dp->dccps_awl, dp->dccps_iss)) dp->dccps_awl = dp->dccps_iss; dp->dccps_awh = dp->dccps_gss; } static inline int dccp_ackvec_pending(const struct sock *sk) { return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL && !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec); } static inline int dccp_ack_pending(const struct sock *sk) { return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val); int dccp_feat_finalise_settings(struct dccp_sock *dp); int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq); int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*, struct sk_buff *skb); int dccp_feat_activate_values(struct sock *sk, struct list_head *fn); void dccp_feat_list_purge(struct list_head *fn_list); int dccp_insert_options(struct sock *sk, struct sk_buff *skb); int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *); u32 dccp_timestamp(void); void dccp_timestamping_init(void); int dccp_insert_option(struct sk_buff *skb, unsigned char option, const void *value, unsigned char len); #ifdef CONFIG_SYSCTL int dccp_sysctl_init(void); void dccp_sysctl_exit(void); #else static inline int dccp_sysctl_init(void) { return 0; } static inline void dccp_sysctl_exit(void) { } #endif #endif /* _DCCP_H */ |
| 714 715 667 46 | 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 | /* Netfilter messages via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org>, * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> * (C) 2005-2017 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial netfilter messages via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/module.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/uaccess.h> #include <net/sock.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <net/netlink.h> #include <net/netns/generic.h> #include <linux/netfilter/nfnetlink.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); MODULE_DESCRIPTION("Netfilter messages via netlink socket"); #define nfnl_dereference_protected(id) \ rcu_dereference_protected(table[(id)].subsys, \ lockdep_nfnl_is_held((id))) #define NFNL_MAX_ATTR_COUNT 32 static unsigned int nfnetlink_pernet_id __read_mostly; struct nfnl_net { struct sock *nfnl; }; static struct { struct mutex mutex; const struct nfnetlink_subsystem __rcu *subsys; } table[NFNL_SUBSYS_COUNT]; static struct lock_class_key nfnl_lockdep_keys[NFNL_SUBSYS_COUNT]; static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = { [NFNL_SUBSYS_NONE] = "nfnl_subsys_none", [NFNL_SUBSYS_CTNETLINK] = "nfnl_subsys_ctnetlink", [NFNL_SUBSYS_CTNETLINK_EXP] = "nfnl_subsys_ctnetlink_exp", [NFNL_SUBSYS_QUEUE] = "nfnl_subsys_queue", [NFNL_SUBSYS_ULOG] = "nfnl_subsys_ulog", [NFNL_SUBSYS_OSF] = "nfnl_subsys_osf", [NFNL_SUBSYS_IPSET] = "nfnl_subsys_ipset", [NFNL_SUBSYS_ACCT] = "nfnl_subsys_acct", [NFNL_SUBSYS_CTNETLINK_TIMEOUT] = "nfnl_subsys_cttimeout", [NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper", [NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables", [NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat", [NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook", }; static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_DESTROY] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, }; static struct nfnl_net *nfnl_pernet(struct net *net) { return net_generic(net, nfnetlink_pernet_id); } void nfnl_lock(__u8 subsys_id) { mutex_lock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_lock); void nfnl_unlock(__u8 subsys_id) { mutex_unlock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_unlock); #ifdef CONFIG_PROVE_LOCKING bool lockdep_nfnl_is_held(u8 subsys_id) { return lockdep_is_held(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); #endif int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { u8 cb_id; /* Sanity-check attr_count size to avoid stack buffer overflow. */ for (cb_id = 0; cb_id < n->cb_count; cb_id++) if (WARN_ON(n->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT)) return -EINVAL; nfnl_lock(n->subsys_id); if (table[n->subsys_id].subsys) { nfnl_unlock(n->subsys_id); return -EBUSY; } rcu_assign_pointer(table[n->subsys_id].subsys, n); nfnl_unlock(n->subsys_id); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_register); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); table[n->subsys_id].subsys = NULL; nfnl_unlock(n->subsys_id); synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u16 type) { u8 subsys_id = NFNL_SUBSYS_ID(type); if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; return rcu_dereference(table[subsys_id].subsys); } static inline const struct nfnl_callback * nfnetlink_find_client(u16 type, const struct nfnetlink_subsystem *ss) { u8 cb_id = NFNL_MSG_TYPE(type); if (cb_id >= ss->cb_count) return NULL; return &ss->cb[cb_id]; } int nfnetlink_has_listeners(struct net *net, unsigned int group) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return netlink_has_listeners(nfnlnet->nfnl, group); } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return nlmsg_notify(nfnlnet->nfnl, skb, portid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return netlink_set_err(nfnlnet->nfnl, portid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { struct nfnl_net *nfnlnet = nfnl_pernet(net); int err; err = nlmsg_unicast(nfnlnet->nfnl, skb, portid); if (err == -EAGAIN) err = -ENOBUFS; return err; } EXPORT_SYMBOL_GPL(nfnetlink_unicast); void nfnetlink_broadcast(struct net *net, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation) { struct nfnl_net *nfnlnet = nfnl_pernet(net); netlink_broadcast(nfnlnet->nfnl, skb, portid, group, allocation); } EXPORT_SYMBOL_GPL(nfnetlink_broadcast); /* Process one complete nfnetlink message. */ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); const struct nfnl_callback *nc; const struct nfnetlink_subsystem *ss; int type, err; /* All the messages must at least contain nfgenmsg */ if (nlmsg_len(nlh) < sizeof(struct nfgenmsg)) return 0; type = nlh->nlmsg_type; replay: rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) { #ifdef CONFIG_MODULES rcu_read_unlock(); request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type)); rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) #endif { rcu_read_unlock(); return -EINVAL; } } nc = nfnetlink_find_client(type, ss); if (!nc) { rcu_read_unlock(); return -EINVAL; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nfnl_net *nfnlnet = nfnl_pernet(net); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; __u8 subsys_id = NFNL_SUBSYS_ID(type); struct nfnl_info info = { .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, .nfmsg = nlmsg_data(nlh), .extack = extack, }; /* Sanity-check NFNL_MAX_ATTR_COUNT */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { rcu_read_unlock(); return -ENOMEM; } err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, extack); if (err < 0) { rcu_read_unlock(); return err; } if (!nc->call) { rcu_read_unlock(); return -EINVAL; } switch (nc->type) { case NFNL_CB_RCU: err = nc->call(skb, &info, (const struct nlattr **)cda); rcu_read_unlock(); break; case NFNL_CB_MUTEX: rcu_read_unlock(); nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) { nfnl_unlock(subsys_id); err = -EAGAIN; break; } err = nc->call(skb, &info, (const struct nlattr **)cda); nfnl_unlock(subsys_id); break; default: rcu_read_unlock(); err = -EINVAL; break; } if (err == -EAGAIN) goto replay; return err; } } struct nfnl_err { struct list_head head; struct nlmsghdr *nlh; int err; struct netlink_ext_ack extack; }; static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct nfnl_err *nfnl_err; nfnl_err = kmalloc(sizeof(struct nfnl_err), GFP_KERNEL); if (nfnl_err == NULL) return -ENOMEM; nfnl_err->nlh = nlh; nfnl_err->err = err; nfnl_err->extack = *extack; list_add_tail(&nfnl_err->head, list); return 0; } static void nfnl_err_del(struct nfnl_err *nfnl_err) { list_del(&nfnl_err->head); kfree(nfnl_err); } static void nfnl_err_reset(struct list_head *err_list) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) nfnl_err_del(nfnl_err); } static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) { netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, &nfnl_err->extack); nfnl_err_del(nfnl_err); } } enum { NFNL_BATCH_FAILURE = (1 << 0), NFNL_BATCH_DONE = (1 << 1), NFNL_BATCH_REPLAY = (1 << 2), }; static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u16 subsys_id, u32 genid) { struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; struct netlink_ext_ack extack; LIST_HEAD(err_list); u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; replay_abort: skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) { #ifdef CONFIG_MODULES nfnl_unlock(subsys_id); request_module("nfnetlink-subsys-%d", subsys_id); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) #endif { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } } if (!ss->valid_genid || !ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } if (!try_module_get(ss->owner)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } if (!ss->valid_genid(net, genid)) { module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); return kfree_skb(skb); } nfnl_unlock(subsys_id); while (skb->len >= nlmsg_total_size(0)) { int msglen, type; if (fatal_signal_pending(current)) { nfnl_err_reset(&err_list); err = -EINTR; status = NFNL_BATCH_FAILURE; goto done; } memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) { err = -EINVAL; goto ack; } type = nlh->nlmsg_type; if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; goto ack; } /* We only accept a batch with messages for the same * subsystem. */ if (NFNL_SUBSYS_ID(type) != subsys_id) { err = -EINVAL; goto ack; } nc = nfnetlink_find_client(type, ss); if (!nc) { err = -EINVAL; goto ack; } if (nc->type != NFNL_CB_BATCH) { err = -EINVAL; goto ack; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nfnl_net *nfnlnet = nfnl_pernet(net); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); int attrlen = nlh->nlmsg_len - min_len; struct nfnl_info info = { .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, .nfmsg = nlmsg_data(nlh), .extack = &extack, }; /* Sanity-check NFTA_MAX_ATTR */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { err = -ENOMEM; goto ack; } err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, NULL); if (err < 0) goto ack; err = nc->call(skb, &info, (const struct nlattr **)cda); /* The lock was released to autoload some module, we * have to abort and start from scratch using the * original skb. */ if (err == -EAGAIN) { status |= NFNL_BATCH_REPLAY; goto done; } } ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) { /* Errors are delivered once the full batch has been * processed, this avoids that the same error is * reported several times when replaying the batch. */ if (err == -ENOMEM || nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. */ nfnl_err_reset(&err_list); netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM, NULL); status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, * userspace gets all the errors that the batch * triggers. */ if (err) status |= NFNL_BATCH_FAILURE; } msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { err = ss->commit(net, oskb); if (err == -EAGAIN) { status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { enum nfnl_abort_action abort_action; if (status & NFNL_BATCH_FAILURE) abort_action = NFNL_ABORT_NONE; else abort_action = NFNL_ABORT_VALIDATE; err = ss->abort(net, oskb, abort_action); if (err == -EAGAIN) { nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); status |= NFNL_BATCH_FAILURE; goto replay_abort; } } nfnl_err_deliver(&err_list, oskb); kfree_skb(skb); module_put(ss->owner); } static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { [NFNL_BATCH_GENID] = { .type = NLA_U32 }, }; static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nlattr *attr = (void *)nlh + min_len; struct nlattr *cda[NFNL_BATCH_MAX + 1]; int attrlen = nlh->nlmsg_len - min_len; struct nfgenmsg *nfgenmsg; int msglen, err; u32 gen_id = 0; u16 res_id; msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse_deprecated(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, NULL); if (err < 0) { netlink_ack(skb, nlh, err, NULL); return; } if (cda[NFNL_BATCH_GENID]) gen_id = ntohl(nla_get_be32(cda[NFNL_BATCH_GENID])); nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); /* Work around old nft using host byte order */ if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) res_id = NFNL_SUBSYS_NFTABLES; else res_id = ntohs(nfgenmsg->res_id); nfnetlink_rcv_batch(skb, nlh, res_id, gen_id); } static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_HDRLEN || nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; if (!netlink_net_capable(skb, CAP_NET_ADMIN)) { netlink_ack(skb, nlh, -EPERM, NULL); return; } if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) nfnetlink_rcv_skb_batch(skb, nlh); else netlink_rcv_skb(skb, nfnetlink_rcv_msg); } #ifdef CONFIG_MODULES static int nfnetlink_bind(struct net *net, int group) { const struct nfnetlink_subsystem *ss; int type; if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) return 0; type = nfnl_group2type[group]; rcu_read_lock(); ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) request_module_nowait("nfnetlink-subsys-%d", type); return 0; } #endif static int __net_init nfnetlink_net_init(struct net *net) { struct nfnl_net *nfnlnet = nfnl_pernet(net); struct netlink_kernel_cfg cfg = { .groups = NFNLGRP_MAX, .input = nfnetlink_rcv, #ifdef CONFIG_MODULES .bind = nfnetlink_bind, #endif }; nfnlnet->nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); if (!nfnlnet->nfnl) return -ENOMEM; return 0; } static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) { struct nfnl_net *nfnlnet; struct net *net; list_for_each_entry(net, net_exit_list, exit_list) { nfnlnet = nfnl_pernet(net); netlink_kernel_release(nfnlnet->nfnl); } } static struct pernet_operations nfnetlink_net_ops = { .init = nfnetlink_net_init, .exit_batch = nfnetlink_net_exit_batch, .id = &nfnetlink_pernet_id, .size = sizeof(struct nfnl_net), }; static int __init nfnetlink_init(void) { int i; for (i = NFNLGRP_NONE + 1; i <= NFNLGRP_MAX; i++) BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE); for (i=0; i<NFNL_SUBSYS_COUNT; i++) __mutex_init(&table[i].mutex, nfnl_lockdep_names[i], &nfnl_lockdep_keys[i]); return register_pernet_subsys(&nfnetlink_net_ops); } static void __exit nfnetlink_exit(void) { unregister_pernet_subsys(&nfnetlink_net_ops); } module_init(nfnetlink_init); module_exit(nfnetlink_exit); |
| 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/sysctl.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/xfrm.h> static void __net_init __xfrm_sysctl_init(struct net *net) { net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME; net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE; net->xfrm.sysctl_larval_drop = 1; net->xfrm.sysctl_acq_expires = 30; } #ifdef CONFIG_SYSCTL static struct ctl_table xfrm_table[] = { { .procname = "xfrm_aevent_etime", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_aevent_rseqth", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_larval_drop", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "xfrm_acq_expires", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, {} }; int __net_init xfrm_sysctl_init(struct net *net) { struct ctl_table *table; __xfrm_sysctl_init(net); table = kmemdup(xfrm_table, sizeof(xfrm_table), GFP_KERNEL); if (!table) goto out_kmemdup; table[0].data = &net->xfrm.sysctl_aevent_etime; table[1].data = &net->xfrm.sysctl_aevent_rseqth; table[2].data = &net->xfrm.sysctl_larval_drop; table[3].data = &net->xfrm.sysctl_acq_expires; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; net->xfrm.sysctl_hdr = register_net_sysctl(net, "net/core", table); if (!net->xfrm.sysctl_hdr) goto out_register; return 0; out_register: kfree(table); out_kmemdup: return -ENOMEM; } void __net_exit xfrm_sysctl_fini(struct net *net) { struct ctl_table *table; table = net->xfrm.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->xfrm.sysctl_hdr); kfree(table); } #else int __net_init xfrm_sysctl_init(struct net *net) { __xfrm_sysctl_init(net); return 0; } #endif |
| 5 5 5 5 5 7 7 33 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Authors: Sjur Brendeland * Daniel Martensson */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/fs.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/if_ether.h> #include <linux/ip.h> #include <linux/sched.h> #include <linux/sockios.h> #include <linux/caif/if_caif.h> #include <net/rtnetlink.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/caif_dev.h> /* GPRS PDP connection has MTU to 1500 */ #define GPRS_PDP_MTU 1500 /* 5 sec. connect timeout */ #define CONNECT_TIMEOUT (5 * HZ) #define CAIF_NET_DEFAULT_QUEUE_LEN 500 #define UNDEF_CONNID 0xffffffff /*This list is protected by the rtnl lock. */ static LIST_HEAD(chnl_net_list); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("caif"); enum caif_states { CAIF_CONNECTED = 1, CAIF_CONNECTING, CAIF_DISCONNECTED, CAIF_SHUTDOWN }; struct chnl_net { struct cflayer chnl; struct caif_connect_request conn_req; struct list_head list_field; struct net_device *netdev; char name[256]; wait_queue_head_t netmgmt_wq; /* Flow status to remember and control the transmission. */ bool flowenabled; enum caif_states state; }; static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) { struct sk_buff *skb; struct chnl_net *priv; int pktlen; const u8 *ip_version; u8 buf; priv = container_of(layr, struct chnl_net, chnl); skb = (struct sk_buff *) cfpkt_tonative(pkt); /* Get length of CAIF packet. */ pktlen = skb->len; /* Pass some minimum information and * send the packet to the net stack. */ skb->dev = priv->netdev; /* check the version of IP */ ip_version = skb_header_pointer(skb, 0, 1, &buf); if (!ip_version) { kfree_skb(skb); return -EINVAL; } switch (*ip_version >> 4) { case 4: skb->protocol = htons(ETH_P_IP); break; case 6: skb->protocol = htons(ETH_P_IPV6); break; default: kfree_skb(skb); priv->netdev->stats.rx_errors++; return -EINVAL; } /* If we change the header in loop mode, the checksum is corrupted. */ if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb->ip_summed = CHECKSUM_NONE; netif_rx_any_context(skb); /* Update statistics. */ priv->netdev->stats.rx_packets++; priv->netdev->stats.rx_bytes += pktlen; return 0; } static int delete_device(struct chnl_net *dev) { ASSERT_RTNL(); if (dev->netdev) unregister_netdevice(dev->netdev); return 0; } static void close_work(struct work_struct *work) { struct chnl_net *dev = NULL; struct list_head *list_node; struct list_head *_tmp; rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); if (dev->state == CAIF_SHUTDOWN) dev_close(dev->netdev); } rtnl_unlock(); } static DECLARE_WORK(close_worker, close_work); static void chnl_hold(struct cflayer *lyr) { struct chnl_net *priv = container_of(lyr, struct chnl_net, chnl); dev_hold(priv->netdev); } static void chnl_put(struct cflayer *lyr) { struct chnl_net *priv = container_of(lyr, struct chnl_net, chnl); dev_put(priv->netdev); } static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, int phyid) { struct chnl_net *priv = container_of(layr, struct chnl_net, chnl); pr_debug("NET flowctrl func called flow: %s\n", flow == CAIF_CTRLCMD_FLOW_ON_IND ? "ON" : flow == CAIF_CTRLCMD_INIT_RSP ? "INIT" : flow == CAIF_CTRLCMD_FLOW_OFF_IND ? "OFF" : flow == CAIF_CTRLCMD_DEINIT_RSP ? "CLOSE/DEINIT" : flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "OPEN_FAIL" : flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ? "REMOTE_SHUTDOWN" : "UNKNOWN CTRL COMMAND"); switch (flow) { case CAIF_CTRLCMD_FLOW_OFF_IND: priv->flowenabled = false; netif_stop_queue(priv->netdev); break; case CAIF_CTRLCMD_DEINIT_RSP: priv->state = CAIF_DISCONNECTED; break; case CAIF_CTRLCMD_INIT_FAIL_RSP: priv->state = CAIF_DISCONNECTED; wake_up_interruptible(&priv->netmgmt_wq); break; case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND: priv->state = CAIF_SHUTDOWN; netif_tx_disable(priv->netdev); schedule_work(&close_worker); break; case CAIF_CTRLCMD_FLOW_ON_IND: priv->flowenabled = true; netif_wake_queue(priv->netdev); break; case CAIF_CTRLCMD_INIT_RSP: caif_client_register_refcnt(&priv->chnl, chnl_hold, chnl_put); priv->state = CAIF_CONNECTED; priv->flowenabled = true; netif_wake_queue(priv->netdev); wake_up_interruptible(&priv->netmgmt_wq); break; default: break; } } static netdev_tx_t chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct chnl_net *priv; struct cfpkt *pkt = NULL; int len; int result = -1; /* Get our private data. */ priv = netdev_priv(dev); if (skb->len > priv->netdev->mtu) { pr_warn("Size of skb exceeded MTU\n"); kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } if (!priv->flowenabled) { pr_debug("dropping packets flow off\n"); kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) swap(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); /* Store original SKB length. */ len = skb->len; pkt = cfpkt_fromnative(CAIF_DIR_OUT, (void *) skb); /* Send the packet down the stack. */ result = priv->chnl.dn->transmit(priv->chnl.dn, pkt); if (result) { dev->stats.tx_dropped++; return NETDEV_TX_OK; } /* Update statistics. */ dev->stats.tx_packets++; dev->stats.tx_bytes += len; return NETDEV_TX_OK; } static int chnl_net_open(struct net_device *dev) { struct chnl_net *priv = NULL; int result = -1; int llifindex, headroom, tailroom, mtu; struct net_device *lldev; ASSERT_RTNL(); priv = netdev_priv(dev); if (!priv) { pr_debug("chnl_net_open: no priv\n"); return -ENODEV; } if (priv->state != CAIF_CONNECTING) { priv->state = CAIF_CONNECTING; result = caif_connect_client(dev_net(dev), &priv->conn_req, &priv->chnl, &llifindex, &headroom, &tailroom); if (result != 0) { pr_debug("err: " "Unable to register and open device," " Err:%d\n", result); goto error; } lldev = __dev_get_by_index(dev_net(dev), llifindex); if (lldev == NULL) { pr_debug("no interface?\n"); result = -ENODEV; goto error; } dev->needed_tailroom = tailroom + lldev->needed_tailroom; dev->hard_header_len = headroom + lldev->hard_header_len + lldev->needed_tailroom; /* * MTU, head-room etc is not know before we have a * CAIF link layer device available. MTU calculation may * override initial RTNL configuration. * MTU is minimum of current mtu, link layer mtu pluss * CAIF head and tail, and PDP GPRS contexts max MTU. */ mtu = min_t(int, dev->mtu, lldev->mtu - (headroom + tailroom)); mtu = min_t(int, GPRS_PDP_MTU, mtu); dev_set_mtu(dev, mtu); if (mtu < 100) { pr_warn("CAIF Interface MTU too small (%d)\n", mtu); result = -ENODEV; goto error; } } rtnl_unlock(); /* Release RTNL lock during connect wait */ result = wait_event_interruptible_timeout(priv->netmgmt_wq, priv->state != CAIF_CONNECTING, CONNECT_TIMEOUT); rtnl_lock(); if (result == -ERESTARTSYS) { pr_debug("wait_event_interruptible woken by a signal\n"); result = -ERESTARTSYS; goto error; } if (result == 0) { pr_debug("connect timeout\n"); result = -ETIMEDOUT; goto error; } if (priv->state != CAIF_CONNECTED) { pr_debug("connect failed\n"); result = -ECONNREFUSED; goto error; } pr_debug("CAIF Netdevice connected\n"); return 0; error: caif_disconnect_client(dev_net(dev), &priv->chnl); priv->state = CAIF_DISCONNECTED; pr_debug("state disconnected\n"); return result; } static int chnl_net_stop(struct net_device *dev) { struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); priv->state = CAIF_DISCONNECTED; caif_disconnect_client(dev_net(dev), &priv->chnl); return 0; } static int chnl_net_init(struct net_device *dev) { struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); strncpy(priv->name, dev->name, sizeof(priv->name)); INIT_LIST_HEAD(&priv->list_field); return 0; } static void chnl_net_uninit(struct net_device *dev) { struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); list_del_init(&priv->list_field); } static const struct net_device_ops netdev_ops = { .ndo_open = chnl_net_open, .ndo_stop = chnl_net_stop, .ndo_init = chnl_net_init, .ndo_uninit = chnl_net_uninit, .ndo_start_xmit = chnl_net_start_xmit, }; static void chnl_net_destructor(struct net_device *dev) { struct chnl_net *priv = netdev_priv(dev); caif_free_client(&priv->chnl); } static void ipcaif_net_setup(struct net_device *dev) { struct chnl_net *priv; dev->netdev_ops = &netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = chnl_net_destructor; dev->flags |= IFF_NOARP; dev->flags |= IFF_POINTOPOINT; dev->mtu = GPRS_PDP_MTU; dev->tx_queue_len = CAIF_NET_DEFAULT_QUEUE_LEN; priv = netdev_priv(dev); priv->chnl.receive = chnl_recv_cb; priv->chnl.ctrlcmd = chnl_flowctrl_cb; priv->netdev = dev; priv->conn_req.protocol = CAIFPROTO_DATAGRAM; priv->conn_req.link_selector = CAIF_LINK_HIGH_BANDW; priv->conn_req.priority = CAIF_PRIO_LOW; /* Insert illegal value */ priv->conn_req.sockaddr.u.dgm.connection_id = UNDEF_CONNID; priv->flowenabled = false; init_waitqueue_head(&priv->netmgmt_wq); } static int ipcaif_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct chnl_net *priv; u8 loop; priv = netdev_priv(dev); if (nla_put_u32(skb, IFLA_CAIF_IPV4_CONNID, priv->conn_req.sockaddr.u.dgm.connection_id) || nla_put_u32(skb, IFLA_CAIF_IPV6_CONNID, priv->conn_req.sockaddr.u.dgm.connection_id)) goto nla_put_failure; loop = priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP; if (nla_put_u8(skb, IFLA_CAIF_LOOPBACK, loop)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static void caif_netlink_parms(struct nlattr *data[], struct caif_connect_request *conn_req) { if (!data) { pr_warn("no params data found\n"); return; } if (data[IFLA_CAIF_IPV4_CONNID]) conn_req->sockaddr.u.dgm.connection_id = nla_get_u32(data[IFLA_CAIF_IPV4_CONNID]); if (data[IFLA_CAIF_IPV6_CONNID]) conn_req->sockaddr.u.dgm.connection_id = nla_get_u32(data[IFLA_CAIF_IPV6_CONNID]); if (data[IFLA_CAIF_LOOPBACK]) { if (nla_get_u8(data[IFLA_CAIF_LOOPBACK])) conn_req->protocol = CAIFPROTO_DATAGRAM_LOOP; else conn_req->protocol = CAIFPROTO_DATAGRAM; } } static int ipcaif_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { int ret; struct chnl_net *caifdev; ASSERT_RTNL(); caifdev = netdev_priv(dev); caif_netlink_parms(data, &caifdev->conn_req); ret = register_netdevice(dev); if (ret) pr_warn("device rtml registration failed\n"); else list_add(&caifdev->list_field, &chnl_net_list); /* Use ifindex as connection id, and use loopback channel default. */ if (caifdev->conn_req.sockaddr.u.dgm.connection_id == UNDEF_CONNID) { caifdev->conn_req.sockaddr.u.dgm.connection_id = dev->ifindex; caifdev->conn_req.protocol = CAIFPROTO_DATAGRAM_LOOP; } return ret; } static int ipcaif_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct chnl_net *caifdev; ASSERT_RTNL(); caifdev = netdev_priv(dev); caif_netlink_parms(data, &caifdev->conn_req); netdev_state_change(dev); return 0; } static size_t ipcaif_get_size(const struct net_device *dev) { return /* IFLA_CAIF_IPV4_CONNID */ nla_total_size(4) + /* IFLA_CAIF_IPV6_CONNID */ nla_total_size(4) + /* IFLA_CAIF_LOOPBACK */ nla_total_size(2) + 0; } static const struct nla_policy ipcaif_policy[IFLA_CAIF_MAX + 1] = { [IFLA_CAIF_IPV4_CONNID] = { .type = NLA_U32 }, [IFLA_CAIF_IPV6_CONNID] = { .type = NLA_U32 }, [IFLA_CAIF_LOOPBACK] = { .type = NLA_U8 } }; static struct rtnl_link_ops ipcaif_link_ops __read_mostly = { .kind = "caif", .priv_size = sizeof(struct chnl_net), .setup = ipcaif_net_setup, .maxtype = IFLA_CAIF_MAX, .policy = ipcaif_policy, .newlink = ipcaif_newlink, .changelink = ipcaif_changelink, .get_size = ipcaif_get_size, .fill_info = ipcaif_fill_info, }; static int __init chnl_init_module(void) { return rtnl_link_register(&ipcaif_link_ops); } static void __exit chnl_exit_module(void) { struct chnl_net *dev = NULL; struct list_head *list_node; struct list_head *_tmp; rtnl_link_unregister(&ipcaif_link_ops); rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); list_del_init(list_node); delete_device(dev); } rtnl_unlock(); } module_init(chnl_init_module); module_exit(chnl_exit_module); |
| 6 6 6 4 3 1 1 3 3 1 4 4 5 5 2 2 2 3 3 2 2 5 5 4 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/wireless/nl80211.c */ #include <linux/rtnetlink.h> #include <net/cfg802154.h> #include <net/genetlink.h> #include <net/mac802154.h> #include <net/netlink.h> #include <net/nl802154.h> #include <net/sock.h> #include "nl802154.h" #include "rdev-ops.h" #include "core.h" /* the netlink family */ static struct genl_family nl802154_fam; /* multicast groups */ enum nl802154_multicast_groups { NL802154_MCGRP_CONFIG, }; static const struct genl_multicast_group nl802154_mcgrps[] = { [NL802154_MCGRP_CONFIG] = { .name = "config", }, }; /* returns ERR_PTR values */ static struct wpan_dev * __cfg802154_wpan_dev_from_attrs(struct net *netns, struct nlattr **attrs) { struct cfg802154_registered_device *rdev; struct wpan_dev *result = NULL; bool have_ifidx = attrs[NL802154_ATTR_IFINDEX]; bool have_wpan_dev_id = attrs[NL802154_ATTR_WPAN_DEV]; u64 wpan_dev_id; int wpan_phy_idx = -1; int ifidx = -1; ASSERT_RTNL(); if (!have_ifidx && !have_wpan_dev_id) return ERR_PTR(-EINVAL); if (have_ifidx) ifidx = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]); if (have_wpan_dev_id) { wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]); wpan_phy_idx = wpan_dev_id >> 32; } list_for_each_entry(rdev, &cfg802154_rdev_list, list) { struct wpan_dev *wpan_dev; if (wpan_phy_net(&rdev->wpan_phy) != netns) continue; if (have_wpan_dev_id && rdev->wpan_phy_idx != wpan_phy_idx) continue; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (have_ifidx && wpan_dev->netdev && wpan_dev->netdev->ifindex == ifidx) { result = wpan_dev; break; } if (have_wpan_dev_id && wpan_dev->identifier == (u32)wpan_dev_id) { result = wpan_dev; break; } } if (result) break; } if (result) return result; return ERR_PTR(-ENODEV); } static struct cfg802154_registered_device * __cfg802154_rdev_from_attrs(struct net *netns, struct nlattr **attrs) { struct cfg802154_registered_device *rdev = NULL, *tmp; struct net_device *netdev; ASSERT_RTNL(); if (!attrs[NL802154_ATTR_WPAN_PHY] && !attrs[NL802154_ATTR_IFINDEX] && !attrs[NL802154_ATTR_WPAN_DEV]) return ERR_PTR(-EINVAL); if (attrs[NL802154_ATTR_WPAN_PHY]) rdev = cfg802154_rdev_by_wpan_phy_idx( nla_get_u32(attrs[NL802154_ATTR_WPAN_PHY])); if (attrs[NL802154_ATTR_WPAN_DEV]) { u64 wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]); struct wpan_dev *wpan_dev; bool found = false; tmp = cfg802154_rdev_by_wpan_phy_idx(wpan_dev_id >> 32); if (tmp) { /* make sure wpan_dev exists */ list_for_each_entry(wpan_dev, &tmp->wpan_dev_list, list) { if (wpan_dev->identifier != (u32)wpan_dev_id) continue; found = true; break; } if (!found) tmp = NULL; if (rdev && tmp != rdev) return ERR_PTR(-EINVAL); rdev = tmp; } } if (attrs[NL802154_ATTR_IFINDEX]) { int ifindex = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]); netdev = __dev_get_by_index(netns, ifindex); if (netdev) { if (netdev->ieee802154_ptr) tmp = wpan_phy_to_rdev( netdev->ieee802154_ptr->wpan_phy); else tmp = NULL; /* not wireless device -- return error */ if (!tmp) return ERR_PTR(-EINVAL); /* mismatch -- return error */ if (rdev && tmp != rdev) return ERR_PTR(-EINVAL); rdev = tmp; } } if (!rdev) return ERR_PTR(-ENODEV); if (netns != wpan_phy_net(&rdev->wpan_phy)) return ERR_PTR(-ENODEV); return rdev; } /* This function returns a pointer to the driver * that the genl_info item that is passed refers to. * * The result of this can be a PTR_ERR and hence must * be checked with IS_ERR() for errors. */ static struct cfg802154_registered_device * cfg802154_get_dev_from_info(struct net *netns, struct genl_info *info) { return __cfg802154_rdev_from_attrs(netns, info->attrs); } /* policy for the attributes */ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_WPAN_PHY] = { .type = NLA_U32 }, [NL802154_ATTR_WPAN_PHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, [NL802154_ATTR_IFINDEX] = { .type = NLA_U32 }, [NL802154_ATTR_IFTYPE] = { .type = NLA_U32 }, [NL802154_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, [NL802154_ATTR_WPAN_DEV] = { .type = NLA_U64 }, [NL802154_ATTR_PAGE] = { .type = NLA_U8, }, [NL802154_ATTR_CHANNEL] = { .type = NLA_U8, }, [NL802154_ATTR_TX_POWER] = { .type = NLA_S32, }, [NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, [NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, }, [NL802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [NL802154_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 }, [NL802154_ATTR_SHORT_ADDR] = { .type = NLA_U16, }, [NL802154_ATTR_MIN_BE] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_BE] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_CSMA_BACKOFFS] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, }, [NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, }, [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED }, [NL802154_ATTR_SUPPORTED_COMMANDS] = { .type = NLA_NESTED }, [NL802154_ATTR_ACKREQ_DEFAULT] = { .type = NLA_U8 }, [NL802154_ATTR_PID] = { .type = NLA_U32 }, [NL802154_ATTR_NETNS_FD] = { .type = NLA_U32 }, #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL [NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, }, [NL802154_ATTR_SEC_OUT_LEVEL] = { .type = NLA_U32, }, [NL802154_ATTR_SEC_OUT_KEY_ID] = { .type = NLA_NESTED, }, [NL802154_ATTR_SEC_FRAME_COUNTER] = { .type = NLA_U32 }, [NL802154_ATTR_SEC_LEVEL] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_DEVICE] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_DEVKEY] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_KEY] = { .type = NLA_NESTED }, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL static int nl802154_prepare_wpan_dev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg802154_registered_device **rdev, struct wpan_dev **wpan_dev) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); int err; rtnl_lock(); if (!cb->args[0]) { *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk), info->attrs); if (IS_ERR(*wpan_dev)) { err = PTR_ERR(*wpan_dev); goto out_unlock; } *rdev = wpan_phy_to_rdev((*wpan_dev)->wpan_phy); /* 0 is the first index - add 1 to parse only once */ cb->args[0] = (*rdev)->wpan_phy_idx + 1; cb->args[1] = (*wpan_dev)->identifier; } else { /* subtract the 1 again here */ struct wpan_phy *wpan_phy = wpan_phy_idx_to_wpan_phy(cb->args[0] - 1); struct wpan_dev *tmp; if (!wpan_phy) { err = -ENODEV; goto out_unlock; } *rdev = wpan_phy_to_rdev(wpan_phy); *wpan_dev = NULL; list_for_each_entry(tmp, &(*rdev)->wpan_dev_list, list) { if (tmp->identifier == cb->args[1]) { *wpan_dev = tmp; break; } } if (!*wpan_dev) { err = -ENODEV; goto out_unlock; } } return 0; out_unlock: rtnl_unlock(); return err; } static void nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev) { rtnl_unlock(); } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ /* message building helper */ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) { /* since there is no private header just add the generic one */ return genlmsg_put(skb, portid, seq, &nl802154_fam, flags, cmd); } static int nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask) { struct nlattr *nl_flags = nla_nest_start_noflag(msg, attr); int i; if (!nl_flags) return -ENOBUFS; i = 0; while (mask) { if ((mask & 1) && nla_put_flag(msg, i)) return -ENOBUFS; mask >>= 1; i++; } nla_nest_end(msg, nl_flags); return 0; } static int nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, struct sk_buff *msg) { struct nlattr *nl_page; unsigned long page; nl_page = nla_nest_start_noflag(msg, NL802154_ATTR_CHANNELS_SUPPORTED); if (!nl_page) return -ENOBUFS; for (page = 0; page <= IEEE802154_MAX_PAGE; page++) { if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL, rdev->wpan_phy.supported.channels[page])) return -ENOBUFS; } nla_nest_end(msg, nl_page); return 0; } static int nl802154_put_capabilities(struct sk_buff *msg, struct cfg802154_registered_device *rdev) { const struct wpan_phy_supported *caps = &rdev->wpan_phy.supported; struct nlattr *nl_caps, *nl_channels; int i; nl_caps = nla_nest_start_noflag(msg, NL802154_ATTR_WPAN_PHY_CAPS); if (!nl_caps) return -ENOBUFS; nl_channels = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CHANNELS); if (!nl_channels) return -ENOBUFS; for (i = 0; i <= IEEE802154_MAX_PAGE; i++) { if (caps->channels[i]) { if (nl802154_put_flags(msg, i, caps->channels[i])) return -ENOBUFS; } } nla_nest_end(msg, nl_channels); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { struct nlattr *nl_ed_lvls; nl_ed_lvls = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CCA_ED_LEVELS); if (!nl_ed_lvls) return -ENOBUFS; for (i = 0; i < caps->cca_ed_levels_size; i++) { if (nla_put_s32(msg, i, caps->cca_ed_levels[i])) return -ENOBUFS; } nla_nest_end(msg, nl_ed_lvls); } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { struct nlattr *nl_tx_pwrs; nl_tx_pwrs = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_TX_POWERS); if (!nl_tx_pwrs) return -ENOBUFS; for (i = 0; i < caps->tx_powers_size; i++) { if (nla_put_s32(msg, i, caps->tx_powers[i])) return -ENOBUFS; } nla_nest_end(msg, nl_tx_pwrs); } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { if (nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_MODES, caps->cca_modes) || nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_OPTS, caps->cca_opts)) return -ENOBUFS; } if (nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MINBE, caps->min_minbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MINBE, caps->max_minbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MAXBE, caps->min_maxbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MAXBE, caps->max_maxbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, caps->min_csma_backoffs) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, caps->max_csma_backoffs) || nla_put_s8(msg, NL802154_CAP_ATTR_MIN_FRAME_RETRIES, caps->min_frame_retries) || nla_put_s8(msg, NL802154_CAP_ATTR_MAX_FRAME_RETRIES, caps->max_frame_retries) || nl802154_put_flags(msg, NL802154_CAP_ATTR_IFTYPES, caps->iftypes) || nla_put_u32(msg, NL802154_CAP_ATTR_LBT, caps->lbt)) return -ENOBUFS; nla_nest_end(msg, nl_caps); return 0; } static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, enum nl802154_commands cmd, struct sk_buff *msg, u32 portid, u32 seq, int flags) { struct nlattr *nl_cmds; void *hdr; int i; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) || nla_put_string(msg, NL802154_ATTR_WPAN_PHY_NAME, wpan_phy_name(&rdev->wpan_phy)) || nla_put_u32(msg, NL802154_ATTR_GENERATION, cfg802154_rdev_list_generation)) goto nla_put_failure; if (cmd != NL802154_CMD_NEW_WPAN_PHY) goto finish; /* DUMP PHY PIB */ /* current channel settings */ if (nla_put_u8(msg, NL802154_ATTR_PAGE, rdev->wpan_phy.current_page) || nla_put_u8(msg, NL802154_ATTR_CHANNEL, rdev->wpan_phy.current_channel)) goto nla_put_failure; /* TODO remove this behaviour, we still keep support it for a while * so users can change the behaviour to the new one. */ if (nl802154_send_wpan_phy_channels(rdev, msg)) goto nla_put_failure; /* cca mode */ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, rdev->wpan_phy.cca.mode)) goto nla_put_failure; if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, rdev->wpan_phy.cca.opt)) goto nla_put_failure; } } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { if (nla_put_s32(msg, NL802154_ATTR_TX_POWER, rdev->wpan_phy.transmit_power)) goto nla_put_failure; } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { if (nla_put_s32(msg, NL802154_ATTR_CCA_ED_LEVEL, rdev->wpan_phy.cca_ed_level)) goto nla_put_failure; } if (nl802154_put_capabilities(msg, rdev)) goto nla_put_failure; nl_cmds = nla_nest_start_noflag(msg, NL802154_ATTR_SUPPORTED_COMMANDS); if (!nl_cmds) goto nla_put_failure; i = 0; #define CMD(op, n) \ do { \ if (rdev->ops->op) { \ i++; \ if (nla_put_u32(msg, i, NL802154_CMD_ ## n)) \ goto nla_put_failure; \ } \ } while (0) CMD(add_virtual_intf, NEW_INTERFACE); CMD(del_virtual_intf, DEL_INTERFACE); CMD(set_channel, SET_CHANNEL); CMD(set_pan_id, SET_PAN_ID); CMD(set_short_addr, SET_SHORT_ADDR); CMD(set_backoff_exponent, SET_BACKOFF_EXPONENT); CMD(set_max_csma_backoffs, SET_MAX_CSMA_BACKOFFS); CMD(set_max_frame_retries, SET_MAX_FRAME_RETRIES); CMD(set_lbt_mode, SET_LBT_MODE); CMD(set_ackreq_default, SET_ACKREQ_DEFAULT); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) CMD(set_tx_power, SET_TX_POWER); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) CMD(set_cca_ed_level, SET_CCA_ED_LEVEL); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) CMD(set_cca_mode, SET_CCA_MODE); #undef CMD nla_nest_end(msg, nl_cmds); finish: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } struct nl802154_dump_wpan_phy_state { s64 filter_wpan_phy; long start; }; static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb, struct netlink_callback *cb, struct nl802154_dump_wpan_phy_state *state) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct nlattr **tb = info->attrs; if (tb[NL802154_ATTR_WPAN_PHY]) state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]); if (tb[NL802154_ATTR_WPAN_DEV]) state->filter_wpan_phy = nla_get_u64(tb[NL802154_ATTR_WPAN_DEV]) >> 32; if (tb[NL802154_ATTR_IFINDEX]) { struct net_device *netdev; struct cfg802154_registered_device *rdev; int ifidx = nla_get_u32(tb[NL802154_ATTR_IFINDEX]); netdev = __dev_get_by_index(&init_net, ifidx); if (!netdev) return -ENODEV; if (netdev->ieee802154_ptr) { rdev = wpan_phy_to_rdev( netdev->ieee802154_ptr->wpan_phy); state->filter_wpan_phy = rdev->wpan_phy_idx; } } return 0; } static int nl802154_dump_wpan_phy(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0, ret; struct nl802154_dump_wpan_phy_state *state = (void *)cb->args[0]; struct cfg802154_registered_device *rdev; rtnl_lock(); if (!state) { state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) { rtnl_unlock(); return -ENOMEM; } state->filter_wpan_phy = -1; ret = nl802154_dump_wpan_phy_parse(skb, cb, state); if (ret) { kfree(state); rtnl_unlock(); return ret; } cb->args[0] = (long)state; } list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (!net_eq(wpan_phy_net(&rdev->wpan_phy), sock_net(skb->sk))) continue; if (++idx <= state->start) continue; if (state->filter_wpan_phy != -1 && state->filter_wpan_phy != rdev->wpan_phy_idx) continue; /* attempt to fit multiple wpan_phy data chunks into the skb */ ret = nl802154_send_wpan_phy(rdev, NL802154_CMD_NEW_WPAN_PHY, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (ret < 0) { if ((ret == -ENOBUFS || ret == -EMSGSIZE) && !skb->len && cb->min_dump_alloc < 4096) { cb->min_dump_alloc = 4096; rtnl_unlock(); return 1; } idx--; break; } break; } rtnl_unlock(); state->start = idx; return skb->len; } static int nl802154_dump_wpan_phy_done(struct netlink_callback *cb) { kfree((void *)cb->args[0]); return 0; } static int nl802154_get_wpan_phy(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct cfg802154_registered_device *rdev = info->user_ptr[0]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; if (nl802154_send_wpan_phy(rdev, NL802154_CMD_NEW_WPAN_PHY, msg, info->snd_portid, info->snd_seq, 0) < 0) { nlmsg_free(msg); return -ENOBUFS; } return genlmsg_reply(msg, info); } static inline u64 wpan_dev_id(struct wpan_dev *wpan_dev) { return (u64)wpan_dev->identifier | ((u64)wpan_phy_to_rdev(wpan_dev->wpan_phy)->wpan_phy_idx << 32); } #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL #include <net/ieee802154_netdev.h> static int ieee802154_llsec_send_key_id(struct sk_buff *msg, const struct ieee802154_llsec_key_id *desc) { struct nlattr *nl_dev_addr; if (nla_put_u32(msg, NL802154_KEY_ID_ATTR_MODE, desc->mode)) return -ENOBUFS; switch (desc->mode) { case NL802154_KEY_ID_MODE_IMPLICIT: nl_dev_addr = nla_nest_start_noflag(msg, NL802154_KEY_ID_ATTR_IMPLICIT); if (!nl_dev_addr) return -ENOBUFS; if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_PAN_ID, desc->device_addr.pan_id) || nla_put_u32(msg, NL802154_DEV_ADDR_ATTR_MODE, desc->device_addr.mode)) return -ENOBUFS; switch (desc->device_addr.mode) { case NL802154_DEV_ADDR_SHORT: if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_SHORT, desc->device_addr.short_addr)) return -ENOBUFS; break; case NL802154_DEV_ADDR_EXTENDED: if (nla_put_le64(msg, NL802154_DEV_ADDR_ATTR_EXTENDED, desc->device_addr.extended_addr, NL802154_DEV_ADDR_ATTR_PAD)) return -ENOBUFS; break; default: /* userspace should handle unknown */ break; } nla_nest_end(msg, nl_dev_addr); break; case NL802154_KEY_ID_MODE_INDEX: break; case NL802154_KEY_ID_MODE_INDEX_SHORT: /* TODO renmae short_source? */ if (nla_put_le32(msg, NL802154_KEY_ID_ATTR_SOURCE_SHORT, desc->short_source)) return -ENOBUFS; break; case NL802154_KEY_ID_MODE_INDEX_EXTENDED: if (nla_put_le64(msg, NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, desc->extended_source, NL802154_KEY_ID_ATTR_PAD)) return -ENOBUFS; break; default: /* userspace should handle unknown */ break; } /* TODO key_id to key_idx ? Check naming */ if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { if (nla_put_u8(msg, NL802154_KEY_ID_ATTR_INDEX, desc->id)) return -ENOBUFS; } return 0; } static int nl802154_get_llsec_params(struct sk_buff *msg, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { struct nlattr *nl_key_id; struct ieee802154_llsec_params params; int ret; ret = rdev_get_llsec_params(rdev, wpan_dev, ¶ms); if (ret < 0) return ret; if (nla_put_u8(msg, NL802154_ATTR_SEC_ENABLED, params.enabled) || nla_put_u32(msg, NL802154_ATTR_SEC_OUT_LEVEL, params.out_level) || nla_put_be32(msg, NL802154_ATTR_SEC_FRAME_COUNTER, params.frame_counter)) return -ENOBUFS; nl_key_id = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_OUT_KEY_ID); if (!nl_key_id) return -ENOBUFS; ret = ieee802154_llsec_send_key_id(msg, ¶ms.out_key); if (ret < 0) return ret; nla_nest_end(msg, nl_key_id); return 0; } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ static int nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { struct net_device *dev = wpan_dev->netdev; void *hdr; hdr = nl802154hdr_put(msg, portid, seq, flags, NL802154_CMD_NEW_INTERFACE); if (!hdr) return -1; if (dev && (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex) || nla_put_string(msg, NL802154_ATTR_IFNAME, dev->name))) goto nla_put_failure; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) || nla_put_u32(msg, NL802154_ATTR_IFTYPE, wpan_dev->iftype) || nla_put_u64_64bit(msg, NL802154_ATTR_WPAN_DEV, wpan_dev_id(wpan_dev), NL802154_ATTR_PAD) || nla_put_u32(msg, NL802154_ATTR_GENERATION, rdev->devlist_generation ^ (cfg802154_rdev_list_generation << 2))) goto nla_put_failure; /* address settings */ if (nla_put_le64(msg, NL802154_ATTR_EXTENDED_ADDR, wpan_dev->extended_addr, NL802154_ATTR_PAD) || nla_put_le16(msg, NL802154_ATTR_SHORT_ADDR, wpan_dev->short_addr) || nla_put_le16(msg, NL802154_ATTR_PAN_ID, wpan_dev->pan_id)) goto nla_put_failure; /* ARET handling */ if (nla_put_s8(msg, NL802154_ATTR_MAX_FRAME_RETRIES, wpan_dev->frame_retries) || nla_put_u8(msg, NL802154_ATTR_MAX_BE, wpan_dev->max_be) || nla_put_u8(msg, NL802154_ATTR_MAX_CSMA_BACKOFFS, wpan_dev->csma_retries) || nla_put_u8(msg, NL802154_ATTR_MIN_BE, wpan_dev->min_be)) goto nla_put_failure; /* listen before transmit */ if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt)) goto nla_put_failure; /* ackreq default behaviour */ if (nla_put_u8(msg, NL802154_ATTR_ACKREQ_DEFAULT, wpan_dev->ackreq)) goto nla_put_failure; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) goto out; if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0) goto nla_put_failure; out: #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_interface(struct sk_buff *skb, struct netlink_callback *cb) { int wp_idx = 0; int if_idx = 0; int wp_start = cb->args[0]; int if_start = cb->args[1]; struct cfg802154_registered_device *rdev; struct wpan_dev *wpan_dev; rtnl_lock(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (!net_eq(wpan_phy_net(&rdev->wpan_phy), sock_net(skb->sk))) continue; if (wp_idx < wp_start) { wp_idx++; continue; } if_idx = 0; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (if_idx < if_start) { if_idx++; continue; } if (nl802154_send_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev) < 0) { goto out; } if_idx++; } wp_idx++; } out: rtnl_unlock(); cb->args[0] = wp_idx; cb->args[1] = if_idx; return skb->len; } static int nl802154_get_interface(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_dev *wdev = info->user_ptr[1]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; if (nl802154_send_iface(msg, info->snd_portid, info->snd_seq, 0, rdev, wdev) < 0) { nlmsg_free(msg); return -ENOBUFS; } return genlmsg_reply(msg, info); } static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; enum nl802154_iftype type = NL802154_IFTYPE_UNSPEC; __le64 extended_addr = cpu_to_le64(0x0000000000000000ULL); /* TODO avoid failing a new interface * creation due to pending removal? */ if (!info->attrs[NL802154_ATTR_IFNAME]) return -EINVAL; if (info->attrs[NL802154_ATTR_IFTYPE]) { type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]); if (type > NL802154_IFTYPE_MAX || !(rdev->wpan_phy.supported.iftypes & BIT(type))) return -EINVAL; } if (info->attrs[NL802154_ATTR_EXTENDED_ADDR]) extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]); if (!rdev->ops->add_virtual_intf) return -EOPNOTSUPP; return rdev_add_virtual_intf(rdev, nla_data(info->attrs[NL802154_ATTR_IFNAME]), NET_NAME_USER, type, extended_addr); } static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_dev *wpan_dev = info->user_ptr[1]; if (!rdev->ops->del_virtual_intf) return -EOPNOTSUPP; /* If we remove a wpan device without a netdev then clear * user_ptr[1] so that nl802154_post_doit won't dereference it * to check if it needs to do dev_put(). Otherwise it crashes * since the wpan_dev has been freed, unlike with a netdev where * we need the dev_put() for the netdev to really be freed. */ if (!wpan_dev->netdev) info->user_ptr[1] = NULL; return rdev_del_virtual_intf(rdev, wpan_dev); } static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; u8 channel, page; if (!info->attrs[NL802154_ATTR_PAGE] || !info->attrs[NL802154_ATTR_CHANNEL]) return -EINVAL; page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]); channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]); /* check 802.15.4 constraints */ if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL || !(rdev->wpan_phy.supported.channels[page] & BIT(channel))) return -EINVAL; return rdev_set_channel(rdev, page, channel); } static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_phy_cca cca; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_CCA_MODE]) return -EINVAL; cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]); /* checking 802.15.4 constraints */ if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX || !(rdev->wpan_phy.supported.cca_modes & BIT(cca.mode))) return -EINVAL; if (cca.mode == NL802154_CCA_ENERGY_CARRIER) { if (!info->attrs[NL802154_ATTR_CCA_OPT]) return -EINVAL; cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]); if (cca.opt > NL802154_CCA_OPT_ATTR_MAX || !(rdev->wpan_phy.supported.cca_opts & BIT(cca.opt))) return -EINVAL; } return rdev_set_cca_mode(rdev, &cca); } static int nl802154_set_cca_ed_level(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; s32 ed_level; int i; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_CCA_ED_LEVEL]) return -EINVAL; ed_level = nla_get_s32(info->attrs[NL802154_ATTR_CCA_ED_LEVEL]); for (i = 0; i < rdev->wpan_phy.supported.cca_ed_levels_size; i++) { if (ed_level == rdev->wpan_phy.supported.cca_ed_levels[i]) return rdev_set_cca_ed_level(rdev, ed_level); } return -EINVAL; } static int nl802154_set_tx_power(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; s32 power; int i; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_TX_POWER]) return -EINVAL; power = nla_get_s32(info->attrs[NL802154_ATTR_TX_POWER]); for (i = 0; i < rdev->wpan_phy.supported.tx_powers_size; i++) { if (power == rdev->wpan_phy.supported.tx_powers[i]) return rdev_set_tx_power(rdev, power); } return -EINVAL; } static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; __le16 pan_id; /* conflict here while tx/rx calls */ if (netif_running(dev)) return -EBUSY; if (wpan_dev->lowpan_dev) { if (netif_running(wpan_dev->lowpan_dev)) return -EBUSY; } /* don't change address fields on monitor */ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || !info->attrs[NL802154_ATTR_PAN_ID]) return -EINVAL; pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]); /* TODO * I am not sure about to check here on broadcast pan_id. * Broadcast is a valid setting, comment from 802.15.4: * If this value is 0xffff, the device is not associated. * * This could useful to simple deassociate an device. */ if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) return -EINVAL; return rdev_set_pan_id(rdev, wpan_dev, pan_id); } static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; __le16 short_addr; /* conflict here while tx/rx calls */ if (netif_running(dev)) return -EBUSY; if (wpan_dev->lowpan_dev) { if (netif_running(wpan_dev->lowpan_dev)) return -EBUSY; } /* don't change address fields on monitor */ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || !info->attrs[NL802154_ATTR_SHORT_ADDR]) return -EINVAL; short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]); /* TODO * I am not sure about to check here on broadcast short_addr. * Broadcast is a valid setting, comment from 802.15.4: * A value of 0xfffe indicates that the device has * associated but has not been allocated an address. A * value of 0xffff indicates that the device does not * have a short address. * * I think we should allow to set these settings but * don't allow to allow socket communication with it. */ if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) || short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)) return -EINVAL; return rdev_set_short_addr(rdev, wpan_dev, short_addr); } static int nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; u8 min_be, max_be; /* should be set on netif open inside phy settings */ if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MIN_BE] || !info->attrs[NL802154_ATTR_MAX_BE]) return -EINVAL; min_be = nla_get_u8(info->attrs[NL802154_ATTR_MIN_BE]); max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]); /* check 802.15.4 constraints */ if (min_be < rdev->wpan_phy.supported.min_minbe || min_be > rdev->wpan_phy.supported.max_minbe || max_be < rdev->wpan_phy.supported.min_maxbe || max_be > rdev->wpan_phy.supported.max_maxbe || min_be > max_be) return -EINVAL; return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be); } static int nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; u8 max_csma_backoffs; /* conflict here while other running iface settings */ if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]) return -EINVAL; max_csma_backoffs = nla_get_u8( info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]); /* check 802.15.4 constraints */ if (max_csma_backoffs < rdev->wpan_phy.supported.min_csma_backoffs || max_csma_backoffs > rdev->wpan_phy.supported.max_csma_backoffs) return -EINVAL; return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs); } static int nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; s8 max_frame_retries; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]) return -EINVAL; max_frame_retries = nla_get_s8( info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]); /* check 802.15.4 constraints */ if (max_frame_retries < rdev->wpan_phy.supported.min_frame_retries || max_frame_retries > rdev->wpan_phy.supported.max_frame_retries) return -EINVAL; return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries); } static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; int mode; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_LBT_MODE]) return -EINVAL; mode = nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); if (mode != 0 && mode != 1) return -EINVAL; if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt)) return -EINVAL; return rdev_set_lbt_mode(rdev, wpan_dev, mode); } static int nl802154_set_ackreq_default(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; int ackreq; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]) return -EINVAL; ackreq = nla_get_u8(info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]); if (ackreq != 0 && ackreq != 1) return -EINVAL; return rdev_set_ackreq_default(rdev, wpan_dev, ackreq); } static int nl802154_wpan_phy_netns(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net *net; int err; if (info->attrs[NL802154_ATTR_PID]) { u32 pid = nla_get_u32(info->attrs[NL802154_ATTR_PID]); net = get_net_ns_by_pid(pid); } else if (info->attrs[NL802154_ATTR_NETNS_FD]) { u32 fd = nla_get_u32(info->attrs[NL802154_ATTR_NETNS_FD]); net = get_net_ns_by_fd(fd); } else { return -EINVAL; } if (IS_ERR(net)) return PTR_ERR(net); err = 0; /* check if anything to do */ if (!net_eq(wpan_phy_net(&rdev->wpan_phy), net)) err = cfg802154_switch_netns(rdev, net); put_net(net); return err; } #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = { [NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 }, [NL802154_DEV_ADDR_ATTR_MODE] = { .type = NLA_U32 }, [NL802154_DEV_ADDR_ATTR_SHORT] = { .type = NLA_U16 }, [NL802154_DEV_ADDR_ATTR_EXTENDED] = { .type = NLA_U64 }, }; static int ieee802154_llsec_parse_dev_addr(struct nlattr *nla, struct ieee802154_addr *addr) { struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, nl802154_dev_addr_policy, NULL)) return -EINVAL; if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE]) return -EINVAL; addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); switch (addr->mode) { case NL802154_DEV_ADDR_SHORT: if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT]) return -EINVAL; addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); break; case NL802154_DEV_ADDR_EXTENDED: if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]) return -EINVAL; addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); break; default: return -EINVAL; } return 0; } static const struct nla_policy nl802154_key_id_policy[NL802154_KEY_ID_ATTR_MAX + 1] = { [NL802154_KEY_ID_ATTR_MODE] = { .type = NLA_U32 }, [NL802154_KEY_ID_ATTR_INDEX] = { .type = NLA_U8 }, [NL802154_KEY_ID_ATTR_IMPLICIT] = { .type = NLA_NESTED }, [NL802154_KEY_ID_ATTR_SOURCE_SHORT] = { .type = NLA_U32 }, [NL802154_KEY_ID_ATTR_SOURCE_EXTENDED] = { .type = NLA_U64 }, }; static int ieee802154_llsec_parse_key_id(struct nlattr *nla, struct ieee802154_llsec_key_id *desc) { struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_KEY_ID_ATTR_MAX, nla, nl802154_key_id_policy, NULL)) return -EINVAL; if (!attrs[NL802154_KEY_ID_ATTR_MODE]) return -EINVAL; desc->mode = nla_get_u32(attrs[NL802154_KEY_ID_ATTR_MODE]); switch (desc->mode) { case NL802154_KEY_ID_MODE_IMPLICIT: if (!attrs[NL802154_KEY_ID_ATTR_IMPLICIT]) return -EINVAL; if (ieee802154_llsec_parse_dev_addr(attrs[NL802154_KEY_ID_ATTR_IMPLICIT], &desc->device_addr) < 0) return -EINVAL; break; case NL802154_KEY_ID_MODE_INDEX: break; case NL802154_KEY_ID_MODE_INDEX_SHORT: if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]) return -EINVAL; desc->short_source = nla_get_le32(attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]); break; case NL802154_KEY_ID_MODE_INDEX_EXTENDED: if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]) return -EINVAL; desc->extended_source = nla_get_le64(attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]); break; default: return -EINVAL; } if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { if (!attrs[NL802154_KEY_ID_ATTR_INDEX]) return -EINVAL; /* TODO change id to idx */ desc->id = nla_get_u8(attrs[NL802154_KEY_ID_ATTR_INDEX]); } return 0; } static int nl802154_set_llsec_params(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_params params; u32 changed = 0; int ret; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (info->attrs[NL802154_ATTR_SEC_ENABLED]) { u8 enabled; enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); if (enabled != 0 && enabled != 1) return -EINVAL; params.enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); changed |= IEEE802154_LLSEC_PARAM_ENABLED; } if (info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID]) { ret = ieee802154_llsec_parse_key_id(info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID], ¶ms.out_key); if (ret < 0) return ret; changed |= IEEE802154_LLSEC_PARAM_OUT_KEY; } if (info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]) { params.out_level = nla_get_u32(info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]); if (params.out_level > NL802154_SECLEVEL_MAX) return -EINVAL; changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL; } if (info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]) { params.frame_counter = nla_get_be32(info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]); changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER; } return rdev_set_llsec_params(rdev, wpan_dev, ¶ms, changed); } static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_key_entry *key) { void *hdr; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32]; struct nlattr *nl_key, *nl_key_id; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_key = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_KEY); if (!nl_key) goto nla_put_failure; nl_key_id = nla_nest_start_noflag(msg, NL802154_KEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; if (ieee802154_llsec_send_key_id(msg, &key->id) < 0) goto nla_put_failure; nla_nest_end(msg, nl_key_id); if (nla_put_u8(msg, NL802154_KEY_ATTR_USAGE_FRAMES, key->key->frame_types)) goto nla_put_failure; if (key->key->frame_types & BIT(NL802154_FRAME_CMD)) { /* TODO for each nested */ memset(commands, 0, sizeof(commands)); commands[7] = key->key->cmd_frame_ids; if (nla_put(msg, NL802154_KEY_ATTR_USAGE_CMDS, sizeof(commands), commands)) goto nla_put_failure; } if (nla_put(msg, NL802154_KEY_ATTR_BYTES, NL802154_KEY_SIZE, key->key->key)) goto nla_put_failure; nla_nest_end(msg, nl_key); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_key_entry *key; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(key, &table->keys, list) { if (nl802154_send_key(skb, NL802154_CMD_NEW_SEC_KEY, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, key) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_key_policy[NL802154_KEY_ATTR_MAX + 1] = { [NL802154_KEY_ATTR_ID] = { NLA_NESTED }, /* TODO handle it as for_each_nested and NLA_FLAG? */ [NL802154_KEY_ATTR_USAGE_FRAMES] = { NLA_U8 }, /* TODO handle it as for_each_nested, not static array? */ [NL802154_KEY_ATTR_USAGE_CMDS] = { .len = NL802154_CMD_FRAME_NR_IDS / 8 }, [NL802154_KEY_ATTR_BYTES] = { .len = NL802154_KEY_SIZE }, }; static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key key = { }; struct ieee802154_llsec_key_id id = { }; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { }; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_KEY] || nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] || !attrs[NL802154_KEY_ATTR_BYTES]) return -EINVAL; if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; key.frame_types = nla_get_u8(attrs[NL802154_KEY_ATTR_USAGE_FRAMES]); if (key.frame_types > BIT(NL802154_FRAME_MAX) || ((key.frame_types & BIT(NL802154_FRAME_CMD)) && !attrs[NL802154_KEY_ATTR_USAGE_CMDS])) return -EINVAL; if (attrs[NL802154_KEY_ATTR_USAGE_CMDS]) { /* TODO for each nested */ nla_memcpy(commands, attrs[NL802154_KEY_ATTR_USAGE_CMDS], NL802154_CMD_FRAME_NR_IDS / 8); /* TODO understand the -EINVAL logic here? last condition */ if (commands[0] || commands[1] || commands[2] || commands[3] || commands[4] || commands[5] || commands[6] || commands[7] > BIT(NL802154_CMD_FRAME_MAX)) return -EINVAL; key.cmd_frame_ids = commands[7]; } else { key.cmd_frame_ids = 0; } nla_memcpy(key.key, attrs[NL802154_KEY_ATTR_BYTES], NL802154_KEY_SIZE); if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; return rdev_add_llsec_key(rdev, wpan_dev, &id, &key); } static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key_id id; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_KEY] || nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; return rdev_del_llsec_key(rdev, wpan_dev, &id); } static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_device *dev_desc) { void *hdr; struct nlattr *nl_device; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_device = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVICE); if (!nl_device) goto nla_put_failure; if (nla_put_u32(msg, NL802154_DEV_ATTR_FRAME_COUNTER, dev_desc->frame_counter) || nla_put_le16(msg, NL802154_DEV_ATTR_PAN_ID, dev_desc->pan_id) || nla_put_le16(msg, NL802154_DEV_ATTR_SHORT_ADDR, dev_desc->short_addr) || nla_put_le64(msg, NL802154_DEV_ATTR_EXTENDED_ADDR, dev_desc->hwaddr, NL802154_DEV_ATTR_PAD) || nla_put_u8(msg, NL802154_DEV_ATTR_SECLEVEL_EXEMPT, dev_desc->seclevel_exempt) || nla_put_u32(msg, NL802154_DEV_ATTR_KEY_MODE, dev_desc->key_mode)) goto nla_put_failure; nla_nest_end(msg, nl_device); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_device *dev; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(dev, &table->devices, list) { if (nl802154_send_device(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, dev) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_dev_policy[NL802154_DEV_ATTR_MAX + 1] = { [NL802154_DEV_ATTR_FRAME_COUNTER] = { NLA_U32 }, [NL802154_DEV_ATTR_PAN_ID] = { .type = NLA_U16 }, [NL802154_DEV_ATTR_SHORT_ADDR] = { .type = NLA_U16 }, [NL802154_DEV_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 }, [NL802154_DEV_ATTR_SECLEVEL_EXEMPT] = { NLA_U8 }, [NL802154_DEV_ATTR_KEY_MODE] = { NLA_U32 }, }; static int ieee802154_llsec_parse_device(struct nlattr *nla, struct ieee802154_llsec_device *dev) { struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, nla, nl802154_dev_policy, NULL)) return -EINVAL; memset(dev, 0, sizeof(*dev)); if (!attrs[NL802154_DEV_ATTR_FRAME_COUNTER] || !attrs[NL802154_DEV_ATTR_PAN_ID] || !attrs[NL802154_DEV_ATTR_SHORT_ADDR] || !attrs[NL802154_DEV_ATTR_EXTENDED_ADDR] || !attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT] || !attrs[NL802154_DEV_ATTR_KEY_MODE]) return -EINVAL; /* TODO be32 */ dev->frame_counter = nla_get_u32(attrs[NL802154_DEV_ATTR_FRAME_COUNTER]); dev->pan_id = nla_get_le16(attrs[NL802154_DEV_ATTR_PAN_ID]); dev->short_addr = nla_get_le16(attrs[NL802154_DEV_ATTR_SHORT_ADDR]); /* TODO rename hwaddr to extended_addr */ dev->hwaddr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); dev->seclevel_exempt = nla_get_u8(attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT]); dev->key_mode = nla_get_u32(attrs[NL802154_DEV_ATTR_KEY_MODE]); if (dev->key_mode > NL802154_DEVKEY_MAX || (dev->seclevel_exempt != 0 && dev->seclevel_exempt != 1)) return -EINVAL; return 0; } static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_device dev_desc; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE], &dev_desc) < 0) return -EINVAL; return rdev_add_device(rdev, wpan_dev, &dev_desc); } static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVICE] || nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]) return -EINVAL; extended_addr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); return rdev_del_device(rdev, wpan_dev, extended_addr); } static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *devkey) { void *hdr; struct nlattr *nl_devkey, *nl_key_id; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_devkey = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVKEY); if (!nl_devkey) goto nla_put_failure; if (nla_put_le64(msg, NL802154_DEVKEY_ATTR_EXTENDED_ADDR, extended_addr, NL802154_DEVKEY_ATTR_PAD) || nla_put_u32(msg, NL802154_DEVKEY_ATTR_FRAME_COUNTER, devkey->frame_counter)) goto nla_put_failure; nl_key_id = nla_nest_start_noflag(msg, NL802154_DEVKEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; if (ieee802154_llsec_send_key_id(msg, &devkey->key_id) < 0) goto nla_put_failure; nla_nest_end(msg, nl_key_id); nla_nest_end(msg, nl_devkey); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_device_key *kpos; struct ieee802154_llsec_device *dpos; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; /* TODO look if remove devkey and do some nested attribute */ list_for_each_entry(dpos, &table->devices, list) { list_for_each_entry(kpos, &dpos->keys, list) { if (nl802154_send_devkey(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, dpos->hwaddr, kpos) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_devkey_policy[NL802154_DEVKEY_ATTR_MAX + 1] = { [NL802154_DEVKEY_ATTR_FRAME_COUNTER] = { NLA_U32 }, [NL802154_DEVKEY_ATTR_EXTENDED_ADDR] = { NLA_U64 }, [NL802154_DEVKEY_ATTR_ID] = { NLA_NESTED }, }; static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; struct ieee802154_llsec_device_key key; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0) return -EINVAL; if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] || !attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) return -EINVAL; /* TODO change key.id ? */ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], &key.key_id) < 0) return -ENOBUFS; /* TODO be32 */ key.frame_counter = nla_get_u32(attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER]); /* TODO change naming hwaddr -> extended_addr * check unique identifier short+pan OR extended_addr */ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); return rdev_add_devkey(rdev, wpan_dev, extended_addr, &key); } static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; struct ieee802154_llsec_device_key key; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) return -EINVAL; /* TODO change key.id ? */ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], &key.key_id) < 0) return -ENOBUFS; /* TODO change naming hwaddr -> extended_addr * check unique identifier short+pan OR extended_addr */ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); return rdev_del_devkey(rdev, wpan_dev, extended_addr, &key); } static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_seclevel *sl) { void *hdr; struct nlattr *nl_seclevel; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_seclevel = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_LEVEL); if (!nl_seclevel) goto nla_put_failure; if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_FRAME, sl->frame_type) || nla_put_u32(msg, NL802154_SECLEVEL_ATTR_LEVELS, sl->sec_levels) || nla_put_u8(msg, NL802154_SECLEVEL_ATTR_DEV_OVERRIDE, sl->device_override)) goto nla_put_failure; if (sl->frame_type == NL802154_FRAME_CMD) { if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_CMD_FRAME, sl->cmd_frame_id)) goto nla_put_failure; } nla_nest_end(msg, nl_seclevel); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_seclevel *sl; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(sl, &table->security_levels, list) { if (nl802154_send_seclevel(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, sl) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_seclevel_policy[NL802154_SECLEVEL_ATTR_MAX + 1] = { [NL802154_SECLEVEL_ATTR_LEVELS] = { .type = NLA_U8 }, [NL802154_SECLEVEL_ATTR_FRAME] = { .type = NLA_U32 }, [NL802154_SECLEVEL_ATTR_CMD_FRAME] = { .type = NLA_U32 }, [NL802154_SECLEVEL_ATTR_DEV_OVERRIDE] = { .type = NLA_U8 }, }; static int llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl) { struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_SECLEVEL_ATTR_MAX, nla, nl802154_seclevel_policy, NULL)) return -EINVAL; memset(sl, 0, sizeof(*sl)); if (!attrs[NL802154_SECLEVEL_ATTR_LEVELS] || !attrs[NL802154_SECLEVEL_ATTR_FRAME] || !attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]) return -EINVAL; sl->sec_levels = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_LEVELS]); sl->frame_type = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_FRAME]); sl->device_override = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]); if (sl->frame_type > NL802154_FRAME_MAX || (sl->device_override != 0 && sl->device_override != 1)) return -EINVAL; if (sl->frame_type == NL802154_FRAME_CMD) { if (!attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]) return -EINVAL; sl->cmd_frame_id = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]); if (sl->cmd_frame_id > NL802154_CMD_FRAME_MAX) return -EINVAL; } return 0; } static int nl802154_add_llsec_seclevel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; return rdev_add_seclevel(rdev, wpan_dev, &sl); } static int nl802154_del_llsec_seclevel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; return rdev_del_seclevel(rdev, wpan_dev, &sl); } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ #define NL802154_FLAG_NEED_WPAN_PHY 0x01 #define NL802154_FLAG_NEED_NETDEV 0x02 #define NL802154_FLAG_NEED_RTNL 0x04 #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 #define NL802154_FLAG_NEED_WPAN_DEV 0x10 static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev; struct wpan_dev *wpan_dev; struct net_device *dev; bool rtnl = ops->internal_flags & NL802154_FLAG_NEED_RTNL; if (rtnl) rtnl_lock(); if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_PHY) { rdev = cfg802154_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { if (rtnl) rtnl_unlock(); return PTR_ERR(rdev); } info->user_ptr[0] = rdev; } else if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV || ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { ASSERT_RTNL(); wpan_dev = __cfg802154_wpan_dev_from_attrs(genl_info_net(info), info->attrs); if (IS_ERR(wpan_dev)) { if (rtnl) rtnl_unlock(); return PTR_ERR(wpan_dev); } dev = wpan_dev->netdev; rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV) { if (!dev) { if (rtnl) rtnl_unlock(); return -EINVAL; } info->user_ptr[1] = dev; } else { info->user_ptr[1] = wpan_dev; } if (dev) { if (ops->internal_flags & NL802154_FLAG_CHECK_NETDEV_UP && !netif_running(dev)) { if (rtnl) rtnl_unlock(); return -ENETDOWN; } dev_hold(dev); } info->user_ptr[0] = rdev; } return 0; } static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { if (info->user_ptr[1]) { if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { struct wpan_dev *wpan_dev = info->user_ptr[1]; dev_put(wpan_dev->netdev); } else { dev_put(info->user_ptr[1]); } } if (ops->internal_flags & NL802154_FLAG_NEED_RTNL) rtnl_unlock(); } static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_GET_WPAN_PHY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, .doit = nl802154_get_wpan_phy, .dumpit = nl802154_dump_wpan_phy, .done = nl802154_dump_wpan_phy_done, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_get_interface, .dumpit = nl802154_dump_interface, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_new_interface, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_interface, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CHANNEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_channel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CCA_MODE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_cca_mode, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CCA_ED_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_cca_ed_level, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_TX_POWER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_tx_power, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_WPAN_PHY_NETNS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_wpan_phy_netns, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_PAN_ID, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_pan_id, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_SHORT_ADDR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_short_addr, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_BACKOFF_EXPONENT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_backoff_exponent, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_max_csma_backoffs, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_max_frame_retries, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_LBT_MODE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_lbt_mode, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_ACKREQ_DEFAULT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_ackreq_default, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL { .cmd = NL802154_CMD_SET_SEC_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_llsec_params, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching key id? */ .dumpit = nl802154_dump_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, /* TODO unique identifier must short+pan OR extended_addr */ { .cmd = NL802154_CMD_GET_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching extended_addr? */ .dumpit = nl802154_dump_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, /* TODO remove complete devkey, put it as nested? */ { .cmd = NL802154_CMD_GET_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO doit by matching ??? */ .dumpit = nl802154_dump_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching frame_type? */ .dumpit = nl802154_dump_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* TODO match frame_type only? */ .doit = nl802154_del_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static struct genl_family nl802154_fam __ro_after_init = { .name = NL802154_GENL_NAME, /* have users key off the name instead */ .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ .maxattr = NL802154_ATTR_MAX, .policy = nl802154_policy, .netnsok = true, .pre_doit = nl802154_pre_doit, .post_doit = nl802154_post_doit, .module = THIS_MODULE, .ops = nl802154_ops, .n_ops = ARRAY_SIZE(nl802154_ops), .mcgrps = nl802154_mcgrps, .n_mcgrps = ARRAY_SIZE(nl802154_mcgrps), }; /* initialisation/exit functions */ int __init nl802154_init(void) { return genl_register_family(&nl802154_fam); } void nl802154_exit(void) { genl_unregister_family(&nl802154_fam); } |
| 1535 | 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, msg); ), TP_printk("msg=%s", __get_str(msg)) ); #endif /* _TRACE_NETLINK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 180 56 | 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 | /* * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. 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. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H #include "netlink.h" #include "core.h" #include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ #define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 #define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 /* Minimum bearer MTU */ #define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) /* Identifiers for distinguishing between broadcast/multicast and replicast */ #define TIPC_BROADCAST_SUPPORT 1 #define TIPC_REPLICAST_SUPPORT 2 /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; struct tipc_bearer; /** * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: convert media address format to string * @addr2msg: convert from media addr format to discovery msg addr format * @msg2addr: convert from discovery msg addr format to media addr format * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); int (*enable_media)(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, int bufsz); int (*addr2msg)(char *msg, struct tipc_media_addr *addr); int (*msg2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *raw); u32 priority; u32 tolerance; u32 min_win; u32 max_win; u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** * struct tipc_bearer - Generic TIPC bearer structure * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes * care of initializing all other fields. */ struct tipc_bearer { void __rcu *media_ptr; /* initialized by media */ u32 mtu; /* initialized by media */ struct tipc_media_addr addr; /* initialized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; struct packet_type pt; struct rcu_head rcu; u32 priority; u32 min_win; u32 max_win; u32 tolerance; u32 domain; u32 identity; struct tipc_discoverer *disc; char net_plane; u16 encap_hlen; unsigned long up; refcount_t refcnt; }; struct tipc_bearer_names { char media_name[TIPC_MAX_MEDIA_NAME]; char if_name[TIPC_MAX_IF_NAME]; }; /* * TIPC routines available to supported media types */ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b); /* * Routines made available to TIPC by supported media types */ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif #ifdef CONFIG_TIPC_MEDIA_UDP extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]); bool tipc_bearer_hold(struct tipc_bearer *b); void tipc_bearer_put(struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest); void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); int tipc_attach_loopback(struct net *net); void tipc_detach_loopback(struct net *net); static inline void tipc_loopback_trace(struct net *net, struct sk_buff_head *pkts) { if (unlikely(dev_nit_active(net->loopback_dev))) tipc_clone_to_loopback(net, pkts); } /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) { if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; } #endif /* _TIPC_BEARER_H */ |
| 11 11 11 2 12 6 1 11 2 9 11 6 6 4 2 6 8 8 8 8 8 1 1 14 9 5 4 1 5 7 28 21 3 3 3 4 4 11 5 6 22 22 22 32 11 22 14 14 14 41 27 14 14 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) { if (!filp->f_mapping || !filp->f_mapping->a_ops || !filp->f_mapping->a_ops->direct_IO) return -EINVAL; } if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); spin_unlock(&filp->f_lock); out: return error; } static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { security_file_set_fowner(filp); f_modown(filp, pid, type, force); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; struct pid *pid = NULL; int who = arg, ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { f_modown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(enum rw_hint hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; enum rw_hint hint; u64 h; switch (cmd) { case F_GET_FILE_RW_HINT: h = file_write_hint(file); if (copy_to_user(argp, &h, sizeof(*argp))) return -EFAULT; return 0; case F_SET_FILE_RW_HINT: if (copy_from_user(&h, argp, sizeof(h))) return -EFAULT; hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; spin_lock(&file->f_lock); file->f_write_hint = hint; spin_unlock(&file->f_lock); return 0; case F_GET_RW_HINT: h = inode->i_write_hint; if (copy_to_user(argp, &h, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: if (copy_from_user(&h, argp, sizeof(h))) return -EFAULT; hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; inode_lock(inode); inode->i_write_hint = hint; inode_unlock(inode); return 0; default: return -EINVAL; } } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, arg & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(arg)) { break; } err = 0; filp->f_owner.signum = arg; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, arg); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, arg); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, arg); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, arg); break; case F_GET_RW_HINT: case F_SET_RW_HINT: case F_GET_FILE_RW_HINT: case F_SET_FILE_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __read_mostly; static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); } /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 4 4 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Tag allocation using scalable bitmaps. Uses active queue tracking to support * fairer distribution of tags between multiple submitters when a shared tag map * is used. * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blk-mq.h> #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-mq-tag.h" /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail * to get tag when first time, the other shared-tag users could reserve * budget for it. */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) atomic_inc(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) atomic_inc(&hctx->tags->active_queues); } return true; } /* * Wakeup all potentially sleeping on tags */ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) { sbitmap_queue_wake_all(tags->bitmap_tags); if (include_reserve) sbitmap_queue_wake_all(tags->breserved_tags); } /* * If a previously busy queue goes inactive, potential waiters could now * be allowed to queue. Wake them up and check. */ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (blk_mq_is_sbitmap_shared(hctx->flags)) { if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; atomic_dec(&set->active_queues_shared_sbitmap); } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; atomic_dec(&tags->active_queues); } blk_mq_tag_wakeup_all(tags, false); } static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) && !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; if (data->shallow_depth) return __sbitmap_queue_get_shallow(bt, data->shallow_depth); else return __sbitmap_queue_get(bt); } unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt; struct sbq_wait_state *ws; DEFINE_SBQ_WAIT(wait); unsigned int tag_offset; int tag; if (data->flags & BLK_MQ_REQ_RESERVED) { if (unlikely(!tags->nr_reserved_tags)) { WARN_ON_ONCE(1); return BLK_MQ_NO_TAG; } bt = tags->breserved_tags; tag_offset = 0; } else { bt = tags->bitmap_tags; tag_offset = tags->nr_reserved_tags; } tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) goto found_tag; if (data->flags & BLK_MQ_REQ_NOWAIT) return BLK_MQ_NO_TAG; ws = bt_wait_ptr(bt, data->hctx); do { struct sbitmap_queue *bt_prev; /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for * some to complete. */ blk_mq_run_hw_queue(data->hctx, false); /* * Retry tag allocation after running the hardware queue, * as running the queue may also have found completions. */ tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; bt_prev = bt; io_schedule(); sbitmap_finish_wait(bt, ws, &wait); data->ctx = blk_mq_get_ctx(data->q); data->hctx = blk_mq_map_queue(data->q, data->cmd_flags, data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) bt = tags->breserved_tags; else bt = tags->bitmap_tags; /* * If destination hw queue is changed, fake wake up on * previous queue for compensating the wake up miss, so * other allocations on previous queue won't be starved. */ if (bt != bt_prev) sbitmap_queue_wake_up(bt_prev); ws = bt_wait_ptr(bt, data->hctx); } while (1); sbitmap_finish_wait(bt, ws, &wait); found_tag: /* * Give up this allocation if the hctx is inactive. The caller will * retry on an active hctx. */ if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) { blk_mq_put_tag(tags, data->ctx, tag + tag_offset); return BLK_MQ_NO_TAG; } return tag + tag_offset; } void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; BUG_ON(real_tag >= tags->nr_tags); sbitmap_queue_clear(tags->bitmap_tags, real_tag, ctx->cpu); } else { BUG_ON(tag >= tags->nr_reserved_tags); sbitmap_queue_clear(tags->breserved_tags, tag, ctx->cpu); } } struct bt_iter_data { struct blk_mq_hw_ctx *hctx; busy_iter_fn *fn; void *data; bool reserved; }; static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, unsigned int bitnr) { struct request *rq; unsigned long flags; spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; } static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; struct blk_mq_hw_ctx *hctx = iter_data->hctx; struct blk_mq_tags *tags = hctx->tags; bool reserved = iter_data->reserved; struct request *rq; bool ret = true; if (!reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (rq->q == hctx->queue && rq->mq_hctx == hctx) ret = iter_data->fn(hctx, rq, iter_data->data, reserved); blk_mq_put_rq_ref(rq); return ret; } /** * bt_for_each - iterate over the requests associated with a hardware queue * @hctx: Hardware queue to examine. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each request * associated with @hctx that has been assigned a driver tag. * @fn will be called as follows: @fn(@hctx, rq, @data, @reserved) * where rq is a pointer to a request. Return true to continue * iterating tags, false to stop. * @data: Will be passed as third argument to @fn. * @reserved: Indicates whether @bt is the breserved_tags member or the * bitmap_tags member of struct blk_mq_tags. */ static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt, busy_iter_fn *fn, void *data, bool reserved) { struct bt_iter_data iter_data = { .hctx = hctx, .fn = fn, .data = data, .reserved = reserved, }; sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data); } struct bt_tags_iter_data { struct blk_mq_tags *tags; busy_tag_iter_fn *fn; void *data; unsigned int flags; }; #define BT_TAG_ITER_RESERVED (1 << 0) #define BT_TAG_ITER_STARTED (1 << 1) #define BT_TAG_ITER_STATIC_RQS (1 << 2) static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; bool ret = true; bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (!(iter_data->flags & BT_TAG_ITER_STARTED) || blk_mq_request_started(rq)) ret = iter_data->fn(rq, iter_data->data, reserved); if (!iter_static_rqs) blk_mq_put_rq_ref(rq); return ret; } /** * bt_tags_for_each - iterate over the requests in a tag map * @tags: Tag map to iterate over. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @data, * @reserved) where rq is a pointer to a request. Return true * to continue iterating tags, false to stop. * @data: Will be passed as second argument to @fn. * @flags: BT_TAG_ITER_* */ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, unsigned int flags) { struct bt_tags_iter_data iter_data = { .tags = tags, .fn = fn, .data = data, .flags = flags, }; if (tags->rqs) sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data); } static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv, unsigned int flags) { WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); if (tags->nr_reserved_tags) bt_tags_for_each(tags, tags->breserved_tags, fn, priv, flags | BT_TAG_ITER_RESERVED); bt_tags_for_each(tags, tags->bitmap_tags, fn, priv, flags); } /** * blk_mq_all_tag_iter - iterate over all requests in a tag map * @tags: Tag map to iterate over. * @fn: Pointer to the function that will be called for each * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * Caller has to pass the tag map from which requests are allocated. */ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv) { __blk_mq_all_tag_iter(tags, fn, priv, BT_TAG_ITER_STATIC_RQS); } /** * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set * @tagset: Tag set to iterate over. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * We grab one request reference before calling @fn and release it after * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) { int i; for (i = 0; i < tagset->nr_hw_queues; i++) { if (tagset->tags && tagset->tags[i]) __blk_mq_all_tag_iter(tagset->tags[i], fn, priv, BT_TAG_ITER_STARTED); } } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data, bool reserved) { unsigned *count = data; if (blk_mq_request_completed(rq)) (*count)++; return true; } /** * blk_mq_tagset_wait_completed_request - Wait until all scheduled request * completions have finished. * @tagset: Tag set to drain completed request * * Note: This function has to be run after all IO queues are shutdown */ void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset) { while (true) { unsigned count = 0; blk_mq_tagset_busy_iter(tagset, blk_mq_tagset_count_completed_rqs, &count); if (!count) break; msleep(5); } } EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request); /** * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag * @q: Request queue to examine. * @fn: Pointer to the function that will be called for each request * on @q. @fn will be called as follows: @fn(hctx, rq, @priv, * reserved) where rq is a pointer to a request and hctx points * to the hardware queue associated with the request. 'reserved' * indicates whether or not @rq is a reserved request. * @priv: Will be passed as third argument to @fn. * * Note: if @q->tag_set is shared with other request queues then @fn will be * called for all requests on all queues that share that tag set and not only * for requests associated with @q. */ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv) { struct blk_mq_hw_ctx *hctx; int i; /* * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx * while the queue is frozen. So we can use q_usage_counter to avoid * racing with it. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_tags *tags = hctx->tags; /* * If no software queues are currently mapped to this * hardware queue, there's nothing to check */ if (!blk_mq_hw_queue_mapped(hctx)) continue; if (tags->nr_reserved_tags) bt_for_each(hctx, tags->breserved_tags, fn, priv, true); bt_for_each(hctx, tags->bitmap_tags, fn, priv, false); } blk_queue_exit(q); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, bool round_robin, int node) { return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL, node); } int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, struct sbitmap_queue *breserved_tags, unsigned int queue_depth, unsigned int reserved, int node, int alloc_policy) { unsigned int depth = queue_depth - reserved; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; if (bt_alloc(bitmap_tags, depth, round_robin, node)) return -ENOMEM; if (bt_alloc(breserved_tags, reserved, round_robin, node)) goto free_bitmap_tags; return 0; free_bitmap_tags: sbitmap_queue_free(bitmap_tags); return -ENOMEM; } static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, int node, int alloc_policy) { int ret; ret = blk_mq_init_bitmaps(&tags->__bitmap_tags, &tags->__breserved_tags, tags->nr_tags, tags->nr_reserved_tags, node, alloc_policy); if (ret) return ret; tags->bitmap_tags = &tags->__bitmap_tags; tags->breserved_tags = &tags->__breserved_tags; return 0; } int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set) { int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); int i, ret; ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags, set->queue_depth, set->reserved_tags, set->numa_node, alloc_policy); if (ret) return ret; for (i = 0; i < set->nr_hw_queues; i++) { struct blk_mq_tags *tags = set->tags[i]; tags->bitmap_tags = &set->__bitmap_tags; tags->breserved_tags = &set->__breserved_tags; } return 0; } void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) { sbitmap_queue_free(&set->__bitmap_tags); sbitmap_queue_free(&set->__breserved_tags); } struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, int node, unsigned int flags) { int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags); struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { pr_err("blk-mq: tag depth too large\n"); return NULL; } tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node); if (!tags) return NULL; tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); if (blk_mq_is_sbitmap_shared(flags)) return tags; if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { kfree(tags); return NULL; } return tags; } void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) { if (!blk_mq_is_sbitmap_shared(flags)) { sbitmap_queue_free(tags->bitmap_tags); sbitmap_queue_free(tags->breserved_tags); } kfree(tags); } int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tagsptr, unsigned int tdepth, bool can_grow) { struct blk_mq_tags *tags = *tagsptr; if (tdepth <= tags->nr_reserved_tags) return -EINVAL; /* * If we are allowed to grow beyond the original size, allocate * a new set of tags before freeing the old one. */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; struct blk_mq_tags *new; bool ret; if (!can_grow) return -EINVAL; /* * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ if (tdepth > MAX_SCHED_RQ) return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, tags->nr_reserved_tags, set->flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { blk_mq_free_rq_map(new, set->flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); blk_mq_free_rq_map(*tagsptr, set->flags); *tagsptr = new; } else { /* * Don't need (or can't) update reserved tags here, they * remain static and should never need resizing. */ sbitmap_queue_resize(tags->bitmap_tags, tdepth - tags->nr_reserved_tags); } return 0; } void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) { sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); } /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag * * The tag field in struct request is unique per hardware queue but not over * all hardware queues. Hence this function that returns a tag with the * hardware context index in the upper bits and the per hardware queue tag in * the lower bits. * * Note: When called for a request that is queued on a non-multiqueue request * queue, the hardware context index is set to zero. */ u32 blk_mq_unique_tag(struct request *rq) { return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); } EXPORT_SYMBOL(blk_mq_unique_tag); |
| 2 2 2 1161 1157 1160 1164 1159 2 2 2 361 816 810 810 6 6 6 6 78 78 78 78 78 | 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 | // 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 <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> #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, 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_large(*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_large(*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_large(*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_large(*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_large(*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; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) 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) && (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" : "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); } 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; 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); 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, u32 pkey, int si_code) { struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ mmap_read_unlock(mm); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static noinline void bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area(regs, error_code, address, 0, SEGV_MAPERR); } 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 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, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, 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_large(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_large(*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; if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ 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; } /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. * * User-mode registers count as a user access even for any * potential system fault or CPU buglet: */ if (user_mode(regs)) { local_irq_enable(); flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; #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 /* * Kernel-mode access to the user address space should only occur * on well-defined single instructions listed in the exception * tables. But, an erroneous kernel fault occurring outside one of * those areas which also holds mmap_lock might deadlock attempting * to validate the fault against the address space. * * Only do the expensive exception table search when we might be at * risk of a deadlock. This happens if we * 1. Failed to acquire mmap_lock, and * 2. The access did not originate in userspace. */ if (unlikely(!mmap_read_trylock(mm))) { if (!user_mode(regs) && !search_exception_tables(regs->ip)) { /* * Fault from code in kernel from * which we do not expect faults. */ bad_area_nosemaphore(regs, error_code, address); return; } retry: mmap_read_lock(mm); } else { /* * The above down_read_trylock() might have succeeded in * which case we'll have missed the might_sleep() from * down_read(): */ might_sleep(); } vma = find_vma(mm, address); if (unlikely(!vma)) { bad_area(regs, error_code, address); return; } if (likely(vma->vm_start <= address)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { bad_area(regs, error_code, address); return; } if (unlikely(expand_stack(vma, address))) { bad_area(regs, error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ good_area: if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, 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; } /* * 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_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); 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) { unsigned long address = read_cr2(); irqentry_state_t state; 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 rcu_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); } |
| 100 83 83 104 104 94 1 19 95 95 93 93 93 9 3 3 15 20 1 12 2 2 1 1 24 7 13 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/ktime.h> #include <linux/seq_file.h> #include <linux/user_namespace.h> #include <linux/nsfs.h> #include <linux/uaccess.h> #include "internal.h" static struct vfsmount *nsfs_mnt; static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); static const struct file_operations ns_file_operations = { .llseek = no_llseek, .unlocked_ioctl = ns_ioctl, }; static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) { struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = dentry->d_fsdata; return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]", ns_ops->name, inode->i_ino); } static void ns_prune_dentry(struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (inode) { struct ns_common *ns = inode->i_private; atomic_long_set(&ns->stashed, 0); } } const struct dentry_operations ns_dentry_operations = { .d_prune = ns_prune_dentry, .d_delete = always_delete_dentry, .d_dname = ns_dname, }; static void nsfs_evict(struct inode *inode) { struct ns_common *ns = inode->i_private; clear_inode(inode); ns->ops->put(ns); } static int __ns_get_path(struct path *path, struct ns_common *ns) { struct vfsmount *mnt = nsfs_mnt; struct dentry *dentry; struct inode *inode; unsigned long d; rcu_read_lock(); d = atomic_long_read(&ns->stashed); if (!d) goto slow; dentry = (struct dentry *)d; if (!lockref_get_not_dead(&dentry->d_lockref)) goto slow; rcu_read_unlock(); ns->ops->put(ns); got_it: path->mnt = mntget(mnt); path->dentry = dentry; return 0; slow: rcu_read_unlock(); inode = new_inode_pseudo(mnt->mnt_sb); if (!inode) { ns->ops->put(ns); return -ENOMEM; } inode->i_ino = ns->inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_flags |= S_IMMUTABLE; inode->i_mode = S_IFREG | S_IRUGO; inode->i_fop = &ns_file_operations; inode->i_private = ns; dentry = d_alloc_anon(mnt->mnt_sb); if (!dentry) { iput(inode); return -ENOMEM; } d_instantiate(dentry, inode); dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { d_delete(dentry); /* make sure ->d_prune() does nothing */ dput(dentry); cpu_relax(); return -EAGAIN; } goto got_it; } int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb, void *private_data) { int ret; do { struct ns_common *ns = ns_get_cb(private_data); if (!ns) return -ENOENT; ret = __ns_get_path(path, ns); } while (ret == -EAGAIN); return ret; } struct ns_get_path_task_args { const struct proc_ns_operations *ns_ops; struct task_struct *task; }; static struct ns_common *ns_get_path_task(void *private_data) { struct ns_get_path_task_args *args = private_data; return args->ns_ops->get(args->task); } int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops) { struct ns_get_path_task_args args = { .ns_ops = ns_ops, .task = task, }; return ns_get_path_cb(path, ns_get_path_task, &args); } int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)) { struct path path = {}; struct file *f; int err; int fd; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; do { struct ns_common *relative; relative = get_ns(ns); if (IS_ERR(relative)) { put_unused_fd(fd); return PTR_ERR(relative); } err = __ns_get_path(&path, relative); } while (err == -EAGAIN); if (err) { put_unused_fd(fd); return err; } f = dentry_open(&path, O_RDONLY, current_cred()); path_put(&path); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else fd_install(fd, f); return fd; } EXPORT_SYMBOL_GPL(open_related_ns); static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct user_namespace *user_ns; struct ns_common *ns = get_proc_ns(file_inode(filp)); uid_t __user *argp; uid_t uid; switch (ioctl) { case NS_GET_USERNS: return open_related_ns(ns, ns_get_owner); case NS_GET_PARENT: if (!ns->ops->get_parent) return -EINVAL; return open_related_ns(ns, ns->ops->get_parent); case NS_GET_NSTYPE: return ns->ops->type; case NS_GET_OWNER_UID: if (ns->ops->type != CLONE_NEWUSER) return -EINVAL; user_ns = container_of(ns, struct user_namespace, ns); argp = (uid_t __user *) arg; uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); default: return -ENOTTY; } } int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops) { struct ns_common *ns; int res = -ENOENT; const char *name; ns = ns_ops->get(task); if (ns) { name = ns_ops->real_ns_name ? : ns_ops->name; res = snprintf(buf, size, "%s:[%u]", name, ns->inum); ns_ops->put(ns); } return res; } bool proc_ns_file(const struct file *file) { return file->f_op == &ns_file_operations; } struct file *proc_ns_fget(int fd) { struct file *file; file = fget(fd); if (!file) return ERR_PTR(-EBADF); if (file->f_op != &ns_file_operations) goto out_invalid; return file; out_invalid: fput(file); return ERR_PTR(-EINVAL); } /** * ns_match() - Returns true if current namespace matches dev/ino provided. * @ns_common: current ns * @dev: dev_t from nsfs that will be matched against current nsfs * @ino: ino_t from nsfs that will be matched against current nsfs * * Return: true if dev and ino matches the current nsfs. */ bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino) { return (ns->inum == ino) && (nsfs_mnt->mnt_sb->s_dev == dev); } static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry) { struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = dentry->d_fsdata; seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino); return 0; } static const struct super_operations nsfs_ops = { .statfs = simple_statfs, .evict_inode = nsfs_evict, .show_path = nsfs_show_path, }; static int nsfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, NSFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &nsfs_ops; ctx->dops = &ns_dentry_operations; return 0; } static struct file_system_type nsfs = { .name = "nsfs", .init_fs_context = nsfs_init_fs_context, .kill_sb = kill_anon_super, }; void __init nsfs_init(void) { nsfs_mnt = kern_mount(&nsfs); if (IS_ERR(nsfs_mnt)) panic("can't set nsfs up\n"); nsfs_mnt->mnt_sb->s_flags &= ~SB_NOUSER; } |
| 45 45 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/in.h> #include <linux/inet.h> #include <linux/list.h> #include <linux/module.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/rculist.h> #include <linux/seq_file.h> #include <linux/socket.h> #include <net/inet_sock.h> #include <net/kcm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tcp.h> #ifdef CONFIG_PROC_FS static struct kcm_mux *kcm_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); return list_first_or_null_rcu(&knet->mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_next(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); struct kcm_mux *m; list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) { if (!pos) return m; --pos; } return NULL; } static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos) { void *p; if (v == SEQ_START_TOKEN) p = kcm_get_first(seq); else p = kcm_get_next(v); ++*pos; return p; } static void *kcm_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; else return kcm_get_idx(seq, *pos - 1); } static void kcm_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } struct kcm_proc_mux_state { struct seq_net_private p; int idx; }; static void kcm_format_mux_header(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); seq_printf(seq, "*** KCM statistics (%d MUX) ****\n", knet->count); seq_printf(seq, "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s", "Object", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Recv-Q", "Rmem", "Send-Q", "Smem", "Status"); /* XXX: pdsts header stuff here */ seq_puts(seq, "\n"); } static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq, int i, int *len) { seq_printf(seq, " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ", kcm->index, kcm->stats.rx_msgs, kcm->stats.rx_bytes, kcm->stats.tx_msgs, kcm->stats.tx_bytes, kcm->sk.sk_receive_queue.qlen, sk_rmem_alloc_get(&kcm->sk), kcm->sk.sk_write_queue.qlen, "-"); if (kcm->tx_psock) seq_printf(seq, "Psck-%u ", kcm->tx_psock->index); if (kcm->tx_wait) seq_puts(seq, "TxWait "); if (kcm->tx_wait_more) seq_puts(seq, "WMore "); if (kcm->rx_wait) seq_puts(seq, "RxWait "); seq_puts(seq, "\n"); } static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, int i, int *len) { seq_printf(seq, " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", psock->index, psock->strp.stats.msgs, psock->strp.stats.bytes, psock->stats.tx_msgs, psock->stats.tx_bytes, psock->sk->sk_receive_queue.qlen, atomic_read(&psock->sk->sk_rmem_alloc), psock->sk->sk_write_queue.qlen, refcount_read(&psock->sk->sk_wmem_alloc)); if (psock->done) seq_puts(seq, "Done "); if (psock->tx_stopped) seq_puts(seq, "TxStop "); if (psock->strp.stopped) seq_puts(seq, "RxStop "); if (psock->tx_kcm) seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); if (!psock->strp.paused && !psock->ready_rx_msg) { if (psock->sk->sk_receive_queue.qlen) { if (psock->strp.need_bytes) seq_printf(seq, "RxWait=%u ", psock->strp.need_bytes); else seq_printf(seq, "RxWait "); } } else { if (psock->strp.paused) seq_puts(seq, "RxPause "); if (psock->ready_rx_msg) seq_puts(seq, "RdyRx "); } seq_puts(seq, "\n"); } static void kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq) { int i, len; struct kcm_sock *kcm; struct kcm_psock *psock; /* mux information */ seq_printf(seq, "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ", "mux", "", mux->stats.rx_msgs, mux->stats.rx_bytes, mux->stats.tx_msgs, mux->stats.tx_bytes, "-", "-", "-", "-"); seq_printf(seq, "KCMs: %d, Psocks %d\n", mux->kcm_socks_cnt, mux->psocks_cnt); /* kcm sock information */ i = 0; spin_lock_bh(&mux->lock); list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) { kcm_format_sock(kcm, seq, i, &len); i++; } i = 0; list_for_each_entry(psock, &mux->psocks, psock_list) { kcm_format_psock(psock, seq, i, &len); i++; } spin_unlock_bh(&mux->lock); } static int kcm_seq_show(struct seq_file *seq, void *v) { struct kcm_proc_mux_state *mux_state; mux_state = seq->private; if (v == SEQ_START_TOKEN) { mux_state->idx = 0; kcm_format_mux_header(seq); } else { kcm_format_mux(v, mux_state->idx, seq); mux_state->idx++; } return 0; } static const struct seq_operations kcm_seq_ops = { .show = kcm_seq_show, .start = kcm_seq_start, .next = kcm_seq_next, .stop = kcm_seq_stop, }; static int kcm_stats_seq_show(struct seq_file *seq, void *v) { struct kcm_psock_stats psock_stats; struct kcm_mux_stats mux_stats; struct strp_aggr_stats strp_stats; struct kcm_mux *mux; struct kcm_psock *psock; struct net *net = seq->private; struct kcm_net *knet = net_generic(net, kcm_net_id); memset(&mux_stats, 0, sizeof(mux_stats)); memset(&psock_stats, 0, sizeof(psock_stats)); memset(&strp_stats, 0, sizeof(strp_stats)); mutex_lock(&knet->mutex); aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); aggregate_psock_stats(&knet->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&knet->aggregate_strp_stats, &strp_stats); list_for_each_entry(mux, &knet->mux_list, kcm_mux_list) { spin_lock_bh(&mux->lock); aggregate_mux_stats(&mux->stats, &mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &strp_stats); list_for_each_entry(psock, &mux->psocks, psock_list) { aggregate_psock_stats(&psock->stats, &psock_stats); save_strp_stats(&psock->strp, &strp_stats); } spin_unlock_bh(&mux->lock); } mutex_unlock(&knet->mutex); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n", "MUX", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "TX-Retries", "Attach", "Unattach", "UnattchRsvd", "RX-RdyDrops"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n", "", mux_stats.rx_msgs, mux_stats.rx_bytes, mux_stats.tx_msgs, mux_stats.tx_bytes, mux_stats.tx_retries, mux_stats.psock_attach, mux_stats.psock_unattach_rsvd, mux_stats.psock_unattach, mux_stats.rx_ready_drops); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Reserved", "Unreserved", "RX-Aborts", "RX-Intr", "RX-Unrecov", "RX-MemFail", "RX-NeedMor", "RX-BadLen", "RX-TooBig", "RX-Timeout", "TX-Aborts"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", "", strp_stats.msgs, strp_stats.bytes, psock_stats.tx_msgs, psock_stats.tx_bytes, psock_stats.reserved, psock_stats.unreserved, strp_stats.aborts, strp_stats.interrupted, strp_stats.unrecov_intr, strp_stats.mem_fail, strp_stats.need_more_hdr, strp_stats.bad_hdr_len, strp_stats.msg_too_big, strp_stats.msg_timeouts, psock_stats.tx_aborts); return 0; } static int kcm_proc_init_net(struct net *net) { if (!proc_create_net_single("kcm_stats", 0444, net->proc_net, kcm_stats_seq_show, NULL)) goto out_kcm_stats; if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops, sizeof(struct kcm_proc_mux_state))) goto out_kcm; return 0; out_kcm: remove_proc_entry("kcm_stats", net->proc_net); out_kcm_stats: return -ENOMEM; } static void kcm_proc_exit_net(struct net *net) { remove_proc_entry("kcm", net->proc_net); remove_proc_entry("kcm_stats", net->proc_net); } static struct pernet_operations kcm_net_ops = { .init = kcm_proc_init_net, .exit = kcm_proc_exit_net, }; int __init kcm_proc_init(void) { return register_pernet_subsys(&kcm_net_ops); } void __exit kcm_proc_exit(void) { unregister_pernet_subsys(&kcm_net_ops); } #endif /* CONFIG_PROC_FS */ |
| 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Helpers for initial module or kernel cmdline parsing Copyright (C) 2001 Rusty Russell. */ #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/device.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/security.h> #ifdef CONFIG_SYSFS /* Protects all built-in parameters, modules use their own param_lock */ static DEFINE_MUTEX(param_lock); /* Use the module's mutex, or if built-in use the built-in mutex */ #ifdef CONFIG_MODULES #define KPARAM_MUTEX(mod) ((mod) ? &(mod)->param_lock : ¶m_lock) #else #define KPARAM_MUTEX(mod) (¶m_lock) #endif static inline void check_kparam_locked(struct module *mod) { BUG_ON(!mutex_is_locked(KPARAM_MUTEX(mod))); } #else static inline void check_kparam_locked(struct module *mod) { } #endif /* !CONFIG_SYSFS */ /* This just allows us to keep track of which parameters are kmalloced. */ struct kmalloced_param { struct list_head list; char val[]; }; static LIST_HEAD(kmalloced_params); static DEFINE_SPINLOCK(kmalloced_params_lock); static void *kmalloc_parameter(unsigned int size) { struct kmalloced_param *p; p = kmalloc(sizeof(*p) + size, GFP_KERNEL); if (!p) return NULL; spin_lock(&kmalloced_params_lock); list_add(&p->list, &kmalloced_params); spin_unlock(&kmalloced_params_lock); return p->val; } /* Does nothing if parameter wasn't kmalloced above. */ static void maybe_kfree_parameter(void *param) { struct kmalloced_param *p; spin_lock(&kmalloced_params_lock); list_for_each_entry(p, &kmalloced_params, list) { if (p->val == param) { list_del(&p->list); kfree(p); break; } } spin_unlock(&kmalloced_params_lock); } static char dash2underscore(char c) { if (c == '-') return '_'; return c; } bool parameqn(const char *a, const char *b, size_t n) { size_t i; for (i = 0; i < n; i++) { if (dash2underscore(a[i]) != dash2underscore(b[i])) return false; } return true; } bool parameq(const char *a, const char *b) { return parameqn(a, b, strlen(a)+1); } static bool param_check_unsafe(const struct kernel_param *kp) { if (kp->flags & KERNEL_PARAM_FL_HWPARAM && security_locked_down(LOCKDOWN_MODULE_PARAMETERS)) return false; if (kp->flags & KERNEL_PARAM_FL_UNSAFE) { pr_notice("Setting dangerous option %s - tainting kernel\n", kp->name); add_taint(TAINT_USER, LOCKDEP_STILL_OK); } return true; } static int parse_one(char *param, char *val, const char *doing, const struct kernel_param *params, unsigned num_params, s16 min_level, s16 max_level, void *arg, int (*handle_unknown)(char *param, char *val, const char *doing, void *arg)) { unsigned int i; int err; /* Find parameter */ for (i = 0; i < num_params; i++) { if (parameq(param, params[i].name)) { if (params[i].level < min_level || params[i].level > max_level) return 0; /* No one handled NULL, so do it here. */ if (!val && !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG)) return -EINVAL; pr_debug("handling %s with %p\n", param, params[i].ops->set); kernel_param_lock(params[i].mod); if (param_check_unsafe(¶ms[i])) err = params[i].ops->set(val, ¶ms[i]); else err = -EPERM; kernel_param_unlock(params[i].mod); return err; } } if (handle_unknown) { pr_debug("doing %s: %s='%s'\n", doing, param, val); return handle_unknown(param, val, doing, arg); } pr_debug("Unknown argument '%s'\n", param); return -ENOENT; } /* Args looks like "foo=bar,bar2 baz=fuz wiz". */ char *parse_args(const char *doing, char *args, const struct kernel_param *params, unsigned num, s16 min_level, s16 max_level, void *arg, int (*unknown)(char *param, char *val, const char *doing, void *arg)) { char *param, *val, *err = NULL; /* Chew leading spaces */ args = skip_spaces(args); if (*args) pr_debug("doing %s, parsing ARGS: '%s'\n", doing, args); while (*args) { int ret; int irq_was_disabled; args = next_arg(args, ¶m, &val); /* Stop at -- */ if (!val && strcmp(param, "--") == 0) return err ?: args; irq_was_disabled = irqs_disabled(); ret = parse_one(param, val, doing, params, num, min_level, max_level, arg, unknown); if (irq_was_disabled && !irqs_disabled()) pr_warn("%s: option '%s' enabled irq's!\n", doing, param); switch (ret) { case 0: continue; case -ENOENT: pr_err("%s: Unknown parameter `%s'\n", doing, param); break; case -ENOSPC: pr_err("%s: `%s' too large for parameter `%s'\n", doing, val ?: "", param); break; default: pr_err("%s: `%s' invalid for parameter `%s'\n", doing, val ?: "", param); break; } err = ERR_PTR(ret); } return err; } /* Lazy bastard, eh? */ #define STANDARD_PARAM_DEF(name, type, format, strtolfn) \ int param_set_##name(const char *val, const struct kernel_param *kp) \ { \ return strtolfn(val, 0, (type *)kp->arg); \ } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ .set = param_set_##name, \ .get = param_get_##name, \ }; \ EXPORT_SYMBOL(param_set_##name); \ EXPORT_SYMBOL(param_get_##name); \ EXPORT_SYMBOL(param_ops_##name) STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); STANDARD_PARAM_DEF(long, long, "%li", kstrtol); STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); STANDARD_PARAM_DEF(hexint, unsigned int, "%#08x", kstrtouint); int param_set_uint_minmax(const char *val, const struct kernel_param *kp, unsigned int min, unsigned int max) { unsigned int num; int ret; if (!val) return -EINVAL; ret = kstrtouint(val, 0, &num); if (ret) return ret; if (num < min || num > max) return -EINVAL; *((unsigned int *)kp->arg) = num; return 0; } EXPORT_SYMBOL_GPL(param_set_uint_minmax); int param_set_charp(const char *val, const struct kernel_param *kp) { if (strlen(val) > 1024) { pr_err("%s: string parameter too long\n", kp->name); return -ENOSPC; } maybe_kfree_parameter(*(char **)kp->arg); /* This is a hack. We can't kmalloc in early boot, and we * don't need to; this mangled commandline is preserved. */ if (slab_is_available()) { *(char **)kp->arg = kmalloc_parameter(strlen(val)+1); if (!*(char **)kp->arg) return -ENOMEM; strcpy(*(char **)kp->arg, val); } else *(const char **)kp->arg = val; return 0; } EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); void param_free_charp(void *arg) { maybe_kfree_parameter(*((char **)arg)); } EXPORT_SYMBOL(param_free_charp); const struct kernel_param_ops param_ops_charp = { .set = param_set_charp, .get = param_get_charp, .free = param_free_charp, }; EXPORT_SYMBOL(param_ops_charp); /* Actually could be a bool or an int, for historical reasons. */ int param_set_bool(const char *val, const struct kernel_param *kp) { /* No equals means "set"... */ if (!val) val = "1"; /* One of =[yYnN01] */ return strtobool(val, kp->arg); } EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); const struct kernel_param_ops param_ops_bool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool, .get = param_get_bool, }; EXPORT_SYMBOL(param_ops_bool); int param_set_bool_enable_only(const char *val, const struct kernel_param *kp) { int err = 0; bool new_value; bool orig_value = *(bool *)kp->arg; struct kernel_param dummy_kp = *kp; dummy_kp.arg = &new_value; err = param_set_bool(val, &dummy_kp); if (err) return err; /* Don't let them unset it once it's set! */ if (!new_value && orig_value) return -EROFS; if (new_value) err = param_set_bool(val, kp); return err; } EXPORT_SYMBOL_GPL(param_set_bool_enable_only); const struct kernel_param_ops param_ops_bool_enable_only = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool_enable_only, .get = param_get_bool, }; EXPORT_SYMBOL_GPL(param_ops_bool_enable_only); /* This one must be bool. */ int param_set_invbool(const char *val, const struct kernel_param *kp) { int ret; bool boolval; struct kernel_param dummy; dummy.arg = &boolval; ret = param_set_bool(val, &dummy); if (ret == 0) *(bool *)kp->arg = !boolval; return ret; } EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); const struct kernel_param_ops param_ops_invbool = { .set = param_set_invbool, .get = param_get_invbool, }; EXPORT_SYMBOL(param_ops_invbool); int param_set_bint(const char *val, const struct kernel_param *kp) { /* Match bool exactly, by re-using it. */ struct kernel_param boolkp = *kp; bool v; int ret; boolkp.arg = &v; ret = param_set_bool(val, &boolkp); if (ret == 0) *(int *)kp->arg = v; return ret; } EXPORT_SYMBOL(param_set_bint); const struct kernel_param_ops param_ops_bint = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bint, .get = param_get_int, }; EXPORT_SYMBOL(param_ops_bint); /* We break the rule and mangle the string. */ static int param_array(struct module *mod, const char *name, const char *val, unsigned int min, unsigned int max, void *elem, int elemsize, int (*set)(const char *, const struct kernel_param *kp), s16 level, unsigned int *num) { int ret; struct kernel_param kp; char save; /* Get the name right for errors. */ kp.name = name; kp.arg = elem; kp.level = level; *num = 0; /* We expect a comma-separated list of values. */ do { int len; if (*num == max) { pr_err("%s: can only take %i arguments\n", name, max); return -EINVAL; } len = strcspn(val, ","); /* nul-terminate and parse */ save = val[len]; ((char *)val)[len] = '\0'; check_kparam_locked(mod); ret = set(val, &kp); if (ret != 0) return ret; kp.arg += elemsize; val += len+1; (*num)++; } while (save == ','); if (*num < min) { pr_err("%s: needs at least %i arguments\n", name, min); return -EINVAL; } return 0; } static int param_array_set(const char *val, const struct kernel_param *kp) { const struct kparam_array *arr = kp->arr; unsigned int temp_num; return param_array(kp->mod, kp->name, val, 1, arr->max, arr->elem, arr->elemsize, arr->ops->set, kp->level, arr->num ?: &temp_num); } static int param_array_get(char *buffer, const struct kernel_param *kp) { int i, off, ret; const struct kparam_array *arr = kp->arr; struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { /* Replace \n with comma */ if (i) buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); if (ret < 0) return ret; off += ret; } buffer[off] = '\0'; return off; } static void param_array_free(void *arg) { unsigned int i; const struct kparam_array *arr = arg; if (arr->ops->free) for (i = 0; i < (arr->num ? *arr->num : arr->max); i++) arr->ops->free(arr->elem + arr->elemsize * i); } const struct kernel_param_ops param_array_ops = { .set = param_array_set, .get = param_array_get, .free = param_array_free, }; EXPORT_SYMBOL(param_array_ops); int param_set_copystring(const char *val, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; if (strlen(val)+1 > kps->maxlen) { pr_err("%s: string doesn't fit in %u chars.\n", kp->name, kps->maxlen-1); return -ENOSPC; } strcpy(kps->string, val); return 0; } EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); const struct kernel_param_ops param_ops_string = { .set = param_set_copystring, .get = param_get_string, }; EXPORT_SYMBOL(param_ops_string); /* sysfs output in /sys/modules/XYZ/parameters/ */ #define to_module_attr(n) container_of(n, struct module_attribute, attr) #define to_module_kobject(n) container_of(n, struct module_kobject, kobj) struct param_attribute { struct module_attribute mattr; const struct kernel_param *param; }; struct module_param_attrs { unsigned int num; struct attribute_group grp; struct param_attribute attrs[]; }; #ifdef CONFIG_SYSFS #define to_param_attr(n) container_of(n, struct param_attribute, mattr) static ssize_t param_attr_show(struct module_attribute *mattr, struct module_kobject *mk, char *buf) { int count; struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->get) return -EPERM; kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); return count; } /* sysfs always hands a nul-terminated string in buf. We rely on that. */ static ssize_t param_attr_store(struct module_attribute *mattr, struct module_kobject *mk, const char *buf, size_t len) { int err; struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->set) return -EPERM; kernel_param_lock(mk->mod); if (param_check_unsafe(attribute->param)) err = attribute->param->ops->set(buf, attribute->param); else err = -EPERM; kernel_param_unlock(mk->mod); if (!err) return len; return err; } #endif #ifdef CONFIG_MODULES #define __modinit #else #define __modinit __init #endif #ifdef CONFIG_SYSFS void kernel_param_lock(struct module *mod) { mutex_lock(KPARAM_MUTEX(mod)); } void kernel_param_unlock(struct module *mod) { mutex_unlock(KPARAM_MUTEX(mod)); } EXPORT_SYMBOL(kernel_param_lock); EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and * create file in sysfs. Returns an error on out of memory. Always cleans up * if there's an error. */ static __modinit int add_sysfs_param(struct module_kobject *mk, const struct kernel_param *kp, const char *name) { struct module_param_attrs *new_mp; struct attribute **new_attrs; unsigned int i; /* We don't bother calling this with invisible parameters. */ BUG_ON(!kp->perm); if (!mk->mp) { /* First allocation. */ mk->mp = kzalloc(sizeof(*mk->mp), GFP_KERNEL); if (!mk->mp) return -ENOMEM; mk->mp->grp.name = "parameters"; /* NULL-terminated attribute array. */ mk->mp->grp.attrs = kzalloc(sizeof(mk->mp->grp.attrs[0]), GFP_KERNEL); /* Caller will cleanup via free_module_param_attrs */ if (!mk->mp->grp.attrs) return -ENOMEM; } /* Enlarge allocations. */ new_mp = krealloc(mk->mp, sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (mk->mp->num + 1), GFP_KERNEL); if (!new_mp) return -ENOMEM; mk->mp = new_mp; /* Extra pointer for NULL terminator */ new_attrs = krealloc(mk->mp->grp.attrs, sizeof(mk->mp->grp.attrs[0]) * (mk->mp->num + 2), GFP_KERNEL); if (!new_attrs) return -ENOMEM; mk->mp->grp.attrs = new_attrs; /* Tack new one on the end. */ memset(&mk->mp->attrs[mk->mp->num], 0, sizeof(mk->mp->attrs[0])); sysfs_attr_init(&mk->mp->attrs[mk->mp->num].mattr.attr); mk->mp->attrs[mk->mp->num].param = kp; mk->mp->attrs[mk->mp->num].mattr.show = param_attr_show; /* Do not allow runtime DAC changes to make param writable. */ if ((kp->perm & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0) mk->mp->attrs[mk->mp->num].mattr.store = param_attr_store; else mk->mp->attrs[mk->mp->num].mattr.store = NULL; mk->mp->attrs[mk->mp->num].mattr.attr.name = (char *)name; mk->mp->attrs[mk->mp->num].mattr.attr.mode = kp->perm; mk->mp->num++; /* Fix up all the pointers, since krealloc can move us */ for (i = 0; i < mk->mp->num; i++) mk->mp->grp.attrs[i] = &mk->mp->attrs[i].mattr.attr; mk->mp->grp.attrs[mk->mp->num] = NULL; return 0; } #ifdef CONFIG_MODULES static void free_module_param_attrs(struct module_kobject *mk) { if (mk->mp) kfree(mk->mp->grp.attrs); kfree(mk->mp); mk->mp = NULL; } /* * module_param_sysfs_setup - setup sysfs support for one module * @mod: module * @kparam: module parameters (array) * @num_params: number of module parameters * * Adds sysfs entries for module parameters under * /sys/module/[mod->name]/parameters/ */ int module_param_sysfs_setup(struct module *mod, const struct kernel_param *kparam, unsigned int num_params) { int i, err; bool params = false; for (i = 0; i < num_params; i++) { if (kparam[i].perm == 0) continue; err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name); if (err) { free_module_param_attrs(&mod->mkobj); return err; } params = true; } if (!params) return 0; /* Create the param group. */ err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); if (err) free_module_param_attrs(&mod->mkobj); return err; } /* * module_param_sysfs_remove - remove sysfs support for one module * @mod: module * * Remove sysfs entries for module parameters and the corresponding * kobject. */ void module_param_sysfs_remove(struct module *mod) { if (mod->mkobj.mp) { sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); /* We are positive that no one is using any param * attrs at this point. Deallocate immediately. */ free_module_param_attrs(&mod->mkobj); } } #endif void destroy_params(const struct kernel_param *params, unsigned num) { unsigned int i; for (i = 0; i < num; i++) if (params[i].ops->free) params[i].ops->free(params[i].arg); } static struct module_kobject * __init locate_module_kobject(const char *name) { struct module_kobject *mk; struct kobject *kobj; int err; kobj = kset_find_obj(module_kset, name); if (kobj) { mk = to_module_kobject(kobj); } else { mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); BUG_ON(!mk); mk->mod = THIS_MODULE; mk->kobj.kset = module_kset; err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); #ifdef CONFIG_MODULES if (!err) err = sysfs_create_file(&mk->kobj, &module_uevent.attr); #endif if (err) { kobject_put(&mk->kobj); pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n", name, err); return NULL; } /* So that we hold reference in both cases. */ kobject_get(&mk->kobj); } return mk; } static void __init kernel_add_sysfs_param(const char *name, const struct kernel_param *kparam, unsigned int name_skip) { struct module_kobject *mk; int err; mk = locate_module_kobject(name); if (!mk) return; /* We need to remove old parameters before adding more. */ if (mk->mp) sysfs_remove_group(&mk->kobj, &mk->mp->grp); /* These should not fail at boot. */ err = add_sysfs_param(mk, kparam, kparam->name + name_skip); BUG_ON(err); err = sysfs_create_group(&mk->kobj, &mk->mp->grp); BUG_ON(err); kobject_uevent(&mk->kobj, KOBJ_ADD); kobject_put(&mk->kobj); } /* * param_sysfs_builtin - add sysfs parameters for built-in modules * * Add module_parameters to sysfs for "modules" built into the kernel. * * The "module" name (KBUILD_MODNAME) is stored before a dot, the * "parameter" name is stored behind a dot in kernel_param->name. So, * extract the "module" name for all built-in kernel_param-eters, * and for all who have the same, call kernel_add_sysfs_param. */ static void __init param_sysfs_builtin(void) { const struct kernel_param *kp; unsigned int name_len; char modname[MODULE_NAME_LEN]; for (kp = __start___param; kp < __stop___param; kp++) { char *dot; if (kp->perm == 0) continue; dot = strchr(kp->name, '.'); if (!dot) { /* This happens for core_param() */ strcpy(modname, "kernel"); name_len = 0; } else { name_len = dot - kp->name + 1; strlcpy(modname, kp->name, name_len); } kernel_add_sysfs_param(modname, kp, name_len); } } ssize_t __modver_version_show(struct module_attribute *mattr, struct module_kobject *mk, char *buf) { struct module_version_attribute *vattr = container_of(mattr, struct module_version_attribute, mattr); return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version); } extern const struct module_version_attribute __start___modver[]; extern const struct module_version_attribute __stop___modver[]; static void __init version_sysfs_builtin(void) { const struct module_version_attribute *vattr; struct module_kobject *mk; int err; for (vattr = __start___modver; vattr < __stop___modver; vattr++) { mk = locate_module_kobject(vattr->module_name); if (mk) { err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); WARN_ON_ONCE(err); kobject_uevent(&mk->kobj, KOBJ_ADD); kobject_put(&mk->kobj); } } } /* module-related sysfs stuff */ static ssize_t module_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct module_attribute *attribute; struct module_kobject *mk; int ret; attribute = to_module_attr(attr); mk = to_module_kobject(kobj); if (!attribute->show) return -EIO; ret = attribute->show(attribute, mk, buf); return ret; } static ssize_t module_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { struct module_attribute *attribute; struct module_kobject *mk; int ret; attribute = to_module_attr(attr); mk = to_module_kobject(kobj); if (!attribute->store) return -EIO; ret = attribute->store(attribute, mk, buf, len); return ret; } static const struct sysfs_ops module_sysfs_ops = { .show = module_attr_show, .store = module_attr_store, }; static int uevent_filter(struct kset *kset, struct kobject *kobj) { struct kobj_type *ktype = get_ktype(kobj); if (ktype == &module_ktype) return 1; return 0; } static const struct kset_uevent_ops module_uevent_ops = { .filter = uevent_filter, }; struct kset *module_kset; int module_sysfs_initialized; static void module_kobj_release(struct kobject *kobj) { struct module_kobject *mk = to_module_kobject(kobj); complete(mk->kobj_completion); } struct kobj_type module_ktype = { .release = module_kobj_release, .sysfs_ops = &module_sysfs_ops, }; /* * param_sysfs_init - wrapper for built-in params support */ static int __init param_sysfs_init(void) { module_kset = kset_create_and_add("module", &module_uevent_ops, NULL); if (!module_kset) { printk(KERN_WARNING "%s (%d): error creating kset\n", __FILE__, __LINE__); return -ENOMEM; } module_sysfs_initialized = 1; version_sysfs_builtin(); param_sysfs_builtin(); return 0; } subsys_initcall(param_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 136 1375 191 118 48 134 134 108 108 97 97 154 154 154 154 74 74 74 70 74 4 2 2 4 2 2 4 1 882 472 894 880 901 900 2 900 25 894 287 893 20 644 2 21 189 17 171 25 20 3 1 3 7 2 1 6 1 4 4 4 1 178 6 10 9 22 170 281 281 416 21 1 20 3 1 4 58 13 11 30 117 6 14 46 13 19 17 2 145 6 6 6 1 1 4 3 2 3 10 37 2 10 5 12 6 4 24 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/rcupdate.h> #include <linux/random.h> #include <linux/smp.h> #include <linux/topology.h> #include <linux/ktime.h> #include <linux/sched.h> #include <linux/uidgid.h> #include <linux/filter.h> #include <linux/ctype.h> #include <linux/jiffies.h> #include <linux/pid_namespace.h> #include <linux/proc_ns.h> #include <linux/security.h> #include "../../lib/kstrtox.h" /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments * * Different map implementations will rely on rcu in map methods * lookup/update/delete, therefore eBPF programs must run under rcu lock * if program is allowed to access maps, so check rcu_read_lock_held in * all three functions. */ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } const struct bpf_func_proto bpf_map_lookup_elem_proto = { .func = bpf_map_lookup_elem, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, }; BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, void *, value, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return map->ops->map_update_elem(map, key, value, flags); } const struct bpf_func_proto bpf_map_update_elem_proto = { .func = bpf_map_update_elem, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, .arg3_type = ARG_PTR_TO_MAP_VALUE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return map->ops->map_delete_elem(map, key); } const struct bpf_func_proto bpf_map_delete_elem_proto = { .func = bpf_map_delete_elem, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, }; BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags) { return map->ops->map_push_elem(map, value, flags); } const struct bpf_func_proto bpf_map_push_elem_proto = { .func = bpf_map_push_elem, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_VALUE, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) { return map->ops->map_pop_elem(map, value); } const struct bpf_func_proto bpf_map_pop_elem_proto = { .func = bpf_map_pop_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) { return map->ops->map_peek_elem(map, value); } const struct bpf_func_proto bpf_map_peek_elem_proto = { .func = bpf_map_peek_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, }; const struct bpf_func_proto bpf_get_prandom_u32_proto = { .func = bpf_user_rnd_u32, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_smp_processor_id) { return smp_processor_id(); } const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .func = bpf_get_smp_processor_id, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_numa_node_id) { return numa_node_id(); } const struct bpf_func_proto bpf_get_numa_node_id_proto = { .func = bpf_get_numa_node_id, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_ktime_get_ns) { /* NMI safe access to clock monotonic */ return ktime_get_mono_fast_ns(); } const struct bpf_func_proto bpf_ktime_get_ns_proto = { .func = bpf_ktime_get_ns, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_ktime_get_boot_ns) { /* NMI safe access to clock boottime */ return ktime_get_boot_fast_ns(); } const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { .func = bpf_ktime_get_boot_ns, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_ktime_get_coarse_ns) { return ktime_get_coarse_ns(); } const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { .func = bpf_ktime_get_coarse_ns, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; if (unlikely(!task)) return -EINVAL; return (u64) task->tgid << 32 | task->pid; } const struct bpf_func_proto bpf_get_current_pid_tgid_proto = { .func = bpf_get_current_pid_tgid, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_current_uid_gid) { struct task_struct *task = current; kuid_t uid; kgid_t gid; if (unlikely(!task)) return -EINVAL; current_uid_gid(&uid, &gid); return (u64) from_kgid(&init_user_ns, gid) << 32 | from_kuid(&init_user_ns, uid); } const struct bpf_func_proto bpf_get_current_uid_gid_proto = { .func = bpf_get_current_uid_gid, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size) { struct task_struct *task = current; if (unlikely(!task)) goto err_clear; strncpy(buf, task->comm, size); /* Verifier guarantees that size > 0. For task->comm exceeding * size, guarantee that buf is %NUL-terminated. Unconditionally * done here to save the size test. */ buf[size - 1] = 0; return 0; err_clear: memset(buf, 0, size); return -EINVAL; } const struct bpf_func_proto bpf_get_current_comm_proto = { .func = bpf_get_current_comm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, }; #if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK) static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) { arch_spinlock_t *l = (void *)lock; union { __u32 val; arch_spinlock_t lock; } u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED }; compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0"); BUILD_BUG_ON(sizeof(*l) != sizeof(__u32)); BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32)); arch_spin_lock(l); } static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) { arch_spinlock_t *l = (void *)lock; arch_spin_unlock(l); } #else static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) { atomic_t *l = (void *)lock; BUILD_BUG_ON(sizeof(*l) != sizeof(*lock)); do { atomic_cond_read_relaxed(l, !VAL); } while (atomic_xchg(l, 1)); } static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) { atomic_t *l = (void *)lock; atomic_set_release(l, 0); } #endif static DEFINE_PER_CPU(unsigned long, irqsave_flags); static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) { unsigned long flags; local_irq_save(flags); __bpf_spin_lock(lock); __this_cpu_write(irqsave_flags, flags); } NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; } const struct bpf_func_proto bpf_spin_lock_proto = { .func = bpf_spin_lock, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, }; static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) { unsigned long flags; flags = __this_cpu_read(irqsave_flags); __bpf_spin_unlock(lock); local_irq_restore(flags); } NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; } const struct bpf_func_proto bpf_spin_unlock_proto = { .func = bpf_spin_unlock, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, }; void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src) { struct bpf_spin_lock *lock; if (lock_src) lock = src + map->spin_lock_off; else lock = dst + map->spin_lock_off; preempt_disable(); __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); __bpf_spin_unlock_irqrestore(lock); preempt_enable(); } BPF_CALL_0(bpf_jiffies64) { return get_jiffies_64(); } const struct bpf_func_proto bpf_jiffies64_proto = { .func = bpf_jiffies64, .gpl_only = false, .ret_type = RET_INTEGER, }; #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp; u64 cgrp_id; rcu_read_lock(); cgrp = task_dfl_cgroup(current); cgrp_id = cgroup_id(cgrp); rcu_read_unlock(); return cgrp_id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .func = bpf_get_current_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) { struct cgroup *cgrp; struct cgroup *ancestor; u64 cgrp_id; rcu_read_lock(); cgrp = task_dfl_cgroup(current); ancestor = cgroup_ancestor(cgrp, ancestor_level); cgrp_id = ancestor ? cgroup_id(ancestor) : 0; rcu_read_unlock(); return cgrp_id; } const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { .func = bpf_get_current_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_BPF 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, }; #endif #define BPF_STRTOX_BASE_MASK 0x1F static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags, unsigned long long *res, bool *is_negative) { unsigned int base = flags & BPF_STRTOX_BASE_MASK; const char *cur_buf = buf; size_t cur_len = buf_len; unsigned int consumed; size_t val_len; char str[64]; if (!buf || !buf_len || !res || !is_negative) return -EINVAL; if (base != 0 && base != 8 && base != 10 && base != 16) return -EINVAL; if (flags & ~BPF_STRTOX_BASE_MASK) return -EINVAL; while (cur_buf < buf + buf_len && isspace(*cur_buf)) ++cur_buf; *is_negative = (cur_buf < buf + buf_len && *cur_buf == '-'); if (*is_negative) ++cur_buf; consumed = cur_buf - buf; cur_len -= consumed; if (!cur_len) return -EINVAL; cur_len = min(cur_len, sizeof(str) - 1); memcpy(str, cur_buf, cur_len); str[cur_len] = '\0'; cur_buf = str; cur_buf = _parse_integer_fixup_radix(cur_buf, &base); val_len = _parse_integer(cur_buf, base, res); if (val_len & KSTRTOX_OVERFLOW) return -ERANGE; if (val_len == 0) return -EINVAL; cur_buf += val_len; consumed += cur_buf - str; return consumed; } static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags, long long *res) { unsigned long long _res; bool is_negative; int err; err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); if (err < 0) return err; if (is_negative) { if ((long long)-_res > 0) return -ERANGE; *res = -_res; } else { if ((long long)_res < 0) return -ERANGE; *res = _res; } return err; } BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags, long *, res) { long long _res; int err; err = __bpf_strtoll(buf, buf_len, flags, &_res); if (err < 0) return err; if (_res != (long)_res) return -ERANGE; *res = _res; return err; } const struct bpf_func_proto bpf_strtol_proto = { .func = bpf_strtol, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, }; BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, unsigned long *, res) { unsigned long long _res; bool is_negative; int err; err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); if (err < 0) return err; if (is_negative) return -EINVAL; if (_res != (unsigned long)_res) return -ERANGE; *res = _res; return err; } const struct bpf_func_proto bpf_strtoul_proto = { .func = bpf_strtoul, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, }; #endif BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, struct bpf_pidns_info *, nsdata, u32, size) { struct task_struct *task = current; struct pid_namespace *pidns; int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_pidns_info))) goto clear; if (unlikely((u64)(dev_t)dev != dev)) goto clear; if (unlikely(!task)) goto clear; pidns = task_active_pid_ns(task); if (unlikely(!pidns)) { err = -ENOENT; goto clear; } if (!ns_match(&pidns->ns, (dev_t)dev, ino)) goto clear; nsdata->pid = task_pid_nr_ns(task, pidns); nsdata->tgid = task_tgid_nr_ns(task, pidns); return 0; clear: memset((void *)nsdata, 0, (size_t) size); return err; } const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = { .func = bpf_get_ns_current_pid_tgid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = { .func = bpf_get_raw_cpu_id, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags, void *, data, u64, size) { if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; return bpf_event_output(map, flags, data, size, NULL, 0, NULL); } const struct bpf_func_proto bpf_event_output_data_proto = { .func = bpf_event_output_data, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size, const void __user *, user_ptr) { int ret = copy_from_user(dst, user_ptr, size); if (unlikely(ret)) { memset(dst, 0, size); ret = -EFAULT; } return ret; } const struct bpf_func_proto bpf_copy_from_user_proto = { .func = bpf_copy_from_user, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) { if (cpu >= nr_cpu_ids) return (unsigned long)NULL; return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu); } const struct bpf_func_proto bpf_per_cpu_ptr_proto = { .func = bpf_per_cpu_ptr, .gpl_only = false, .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY, .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr) { return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr); } const struct bpf_func_proto bpf_this_cpu_ptr_proto = { .func = bpf_this_cpu_ptr, .gpl_only = false, .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY, .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, }; static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, size_t bufsz) { void __user *user_ptr = (__force void __user *)unsafe_ptr; buf[0] = 0; switch (fmt_ptype) { case 's': #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)unsafe_ptr < TASK_SIZE) return strncpy_from_user_nofault(buf, user_ptr, bufsz); fallthrough; #endif case 'k': return strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz); case 'u': return strncpy_from_user_nofault(buf, user_ptr, bufsz); } return -EINVAL; } /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary * arguments representation. */ #define MAX_BPRINTF_BIN_ARGS 512 /* Support executing three nested bprintf helper calls on a given CPU */ #define MAX_BPRINTF_NEST_LEVEL 3 struct bpf_bprintf_buffers { char bin_args[MAX_BPRINTF_BIN_ARGS]; char buf[MAX_BPRINTF_BUF]; }; static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_buffers(struct bpf_bprintf_buffers **bufs) { int nest_level; preempt_disable(); nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); return 0; } void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) { if (!data->bin_args && !data->buf) return; if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) return; this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } /* * bpf_bprintf_prepare - Generic pass on format strings for bprintf-like helpers * * Returns a negative value if fmt is an invalid format string or 0 otherwise. * * This can be used in two ways: * - Format string verification only: when data->get_bin_args is false * - Arguments preparation: in addition to the above verification, it writes in * data->bin_args a binary representation of arguments usable by bstr_printf * where pointers from BPF have been sanitized. * * In argument preparation mode, if 0 is returned, safe temporary buffers are * allocated and bpf_bprintf_cleanup should be called to free them after use. */ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data) { bool get_buffers = (data->get_bin_args && num_args) || data->get_buf; char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end; struct bpf_bprintf_buffers *buffers = NULL; size_t sizeof_cur_arg, sizeof_cur_ip; int err, i, num_spec = 0; u64 cur_arg; char fmt_ptype, cur_ip[16], ip_spec[] = "%pXX"; fmt_end = strnchr(fmt, fmt_size, 0); if (!fmt_end) return -EINVAL; fmt_size = fmt_end - fmt; if (get_buffers && try_get_buffers(&buffers)) return -EBUSY; if (data->get_bin_args) { if (num_args) tmp_buf = buffers->bin_args; tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS; data->bin_args = (u32 *)tmp_buf; } if (data->get_buf) data->buf = buffers->buf; for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { err = -EINVAL; goto out; } if (fmt[i] != '%') continue; if (fmt[i + 1] == '%') { i++; continue; } if (num_spec >= num_args) { err = -EINVAL; goto out; } /* The string is zero-terminated so if fmt[i] != 0, we can * always access fmt[i + 1], in the worst case it will be a 0 */ i++; /* skip optional "[0 +-][num]" width formatting field */ while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || fmt[i] == ' ') i++; if (fmt[i] >= '1' && fmt[i] <= '9') { i++; while (fmt[i] >= '0' && fmt[i] <= '9') i++; } if (fmt[i] == 'p') { sizeof_cur_arg = sizeof(long); if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') && fmt[i + 2] == 's') { fmt_ptype = fmt[i + 1]; i += 2; goto fmt_str; } if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' || fmt[i + 1] == 'x' || fmt[i + 1] == 's' || fmt[i + 1] == 'S') { /* just kernel pointers */ if (tmp_buf) cur_arg = raw_args[num_spec]; i++; goto nocopy_fmt; } if (fmt[i + 1] == 'B') { if (tmp_buf) { err = snprintf(tmp_buf, (tmp_buf_end - tmp_buf), "%pB", (void *)(long)raw_args[num_spec]); tmp_buf += (err + 1); } i++; num_spec++; continue; } /* only support "%pI4", "%pi4", "%pI6" and "%pi6". */ if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') || (fmt[i + 2] != '4' && fmt[i + 2] != '6')) { err = -EINVAL; goto out; } i += 2; if (!tmp_buf) goto nocopy_fmt; sizeof_cur_ip = (fmt[i] == '4') ? 4 : 16; if (tmp_buf_end - tmp_buf < sizeof_cur_ip) { err = -ENOSPC; goto out; } unsafe_ptr = (char *)(long)raw_args[num_spec]; err = copy_from_kernel_nofault(cur_ip, unsafe_ptr, sizeof_cur_ip); if (err < 0) memset(cur_ip, 0, sizeof_cur_ip); /* hack: bstr_printf expects IP addresses to be * pre-formatted as strings, ironically, the easiest way * to do that is to call snprintf. */ ip_spec[2] = fmt[i - 1]; ip_spec[3] = fmt[i]; err = snprintf(tmp_buf, tmp_buf_end - tmp_buf, ip_spec, &cur_ip); tmp_buf += err + 1; num_spec++; continue; } else if (fmt[i] == 's') { fmt_ptype = fmt[i]; fmt_str: if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) { err = -EINVAL; goto out; } if (!tmp_buf) goto nocopy_fmt; if (tmp_buf_end == tmp_buf) { err = -ENOSPC; goto out; } unsafe_ptr = (char *)(long)raw_args[num_spec]; err = bpf_trace_copy_string(tmp_buf, unsafe_ptr, fmt_ptype, tmp_buf_end - tmp_buf); if (err < 0) { tmp_buf[0] = '\0'; err = 1; } tmp_buf += err; num_spec++; continue; } else if (fmt[i] == 'c') { if (!tmp_buf) goto nocopy_fmt; if (tmp_buf_end == tmp_buf) { err = -ENOSPC; goto out; } *tmp_buf = raw_args[num_spec]; tmp_buf++; num_spec++; continue; } sizeof_cur_arg = sizeof(int); if (fmt[i] == 'l') { sizeof_cur_arg = sizeof(long); i++; } if (fmt[i] == 'l') { sizeof_cur_arg = sizeof(long long); i++; } if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x' && fmt[i] != 'X') { err = -EINVAL; goto out; } if (tmp_buf) cur_arg = raw_args[num_spec]; nocopy_fmt: if (tmp_buf) { tmp_buf = PTR_ALIGN(tmp_buf, sizeof(u32)); if (tmp_buf_end - tmp_buf < sizeof_cur_arg) { err = -ENOSPC; goto out; } if (sizeof_cur_arg == 8) { *(u32 *)tmp_buf = *(u32 *)&cur_arg; *(u32 *)(tmp_buf + 4) = *((u32 *)&cur_arg + 1); } else { *(u32 *)tmp_buf = (u32)(long)cur_arg; } tmp_buf += sizeof_cur_arg; } num_spec++; } err = 0; out: if (err) bpf_bprintf_cleanup(data); return err; } BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, }; int err, num_args; if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; /* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we * can safely give an unbounded size. */ err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data); if (err < 0) return err; err = bstr_printf(str, str_size, fmt, data.bin_args); bpf_bprintf_cleanup(&data); return err + 1; } const struct bpf_func_proto bpf_snprintf_proto = { .func = bpf_snprintf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM_OR_NULL, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_CONST_STR, .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; /* BPF map elements can contain 'struct bpf_timer'. * Such map owns all of its BPF timers. * 'struct bpf_timer' is allocated as part of map element allocation * and it's zero initialized. * That space is used to keep 'struct bpf_timer_kern'. * bpf_timer_init() allocates 'struct bpf_hrtimer', inits hrtimer, and * remembers 'struct bpf_map *' pointer it's part of. * bpf_timer_set_callback() increments prog refcnt and assign bpf callback_fn. * bpf_timer_start() arms the timer. * If user space reference to a map goes to zero at this point * ops->map_release_uref callback is responsible for cancelling the timers, * freeing their memory, and decrementing prog's refcnts. * bpf_timer_cancel() cancels the timer and decrements prog's refcnt. * Inner maps can contain bpf timers as well. ops->map_release_uref is * freeing the timers when inner map is replaced or deleted by user space. */ struct bpf_hrtimer { struct hrtimer timer; struct bpf_map *map; struct bpf_prog *prog; void __rcu *callback_fn; void *value; struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ struct bpf_timer_kern { struct bpf_hrtimer *timer; /* bpf_spin_lock is used here instead of spinlock_t to make * sure that it always fits into space resereved by struct bpf_timer * regardless of LOCKDEP and spinlock debug flags. */ struct bpf_spin_lock lock; } __attribute__((aligned(8))); static DEFINE_PER_CPU(struct bpf_hrtimer *, hrtimer_running); static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) { struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); struct bpf_map *map = t->map; void *value = t->value; void *callback_fn; void *key; u32 idx; callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); if (!callback_fn) goto out; /* bpf_timer_cb() runs in hrtimer_run_softirq. It doesn't migrate and * cannot be preempted by another bpf_timer_cb() on the same cpu. * Remember the timer this callback is servicing to prevent * deadlock if callback_fn() calls bpf_timer_cancel() or * bpf_map_delete_elem() on the same timer. */ this_cpu_write(hrtimer_running, t); if (map->map_type == BPF_MAP_TYPE_ARRAY) { struct bpf_array *array = container_of(map, struct bpf_array, map); /* compute the key */ idx = ((char *)value - array->value) / array->elem_size; key = &idx; } else { /* hash or lru */ key = value - round_up(map->key_size, 8); } BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); /* The verifier checked that return value is zero. */ this_cpu_write(hrtimer_running, NULL); out: return HRTIMER_NORESTART; } BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map, u64, flags) { clockid_t clockid = flags & (MAX_CLOCKS - 1); struct bpf_hrtimer *t; int ret = 0; BUILD_BUG_ON(MAX_CLOCKS != 16); BUILD_BUG_ON(sizeof(struct bpf_timer_kern) > sizeof(struct bpf_timer)); BUILD_BUG_ON(__alignof__(struct bpf_timer_kern) != __alignof__(struct bpf_timer)); if (in_nmi()) return -EOPNOTSUPP; if (flags >= MAX_CLOCKS || /* similar to timerfd except _ALARM variants are not supported */ (clockid != CLOCK_MONOTONIC && clockid != CLOCK_REALTIME && clockid != CLOCK_BOOTTIME)) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (t) { ret = -EBUSY; goto out; } /* allocate hrtimer via map_kmalloc to use memcg accounting */ t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node); if (!t) { ret = -ENOMEM; goto out; } t->value = (void *)timer - map->timer_off; t->map = map; t->prog = NULL; rcu_assign_pointer(t->callback_fn, NULL); hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); t->timer.function = bpf_timer_cb; WRITE_ONCE(timer->timer, t); /* Guarantee the order between timer->timer and map->usercnt. So * when there are concurrent uref release and bpf timer init, either * bpf_timer_cancel_and_free() called by uref release reads a no-NULL * timer or atomic64_read() below returns a zero usercnt. */ smp_mb(); if (!atomic64_read(&map->usercnt)) { /* maps with timers must be either held by user space * or pinned in bpffs. */ WRITE_ONCE(timer->timer, NULL); kfree(t); ret = -EPERM; } out: __bpf_spin_unlock_irqrestore(&timer->lock); return ret; } static const struct bpf_func_proto bpf_timer_init_proto = { .func = bpf_timer_init, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_TIMER, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callback_fn, struct bpf_prog_aux *, aux) { struct bpf_prog *prev, *prog = aux->prog; struct bpf_hrtimer *t; int ret = 0; if (in_nmi()) return -EOPNOTSUPP; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { ret = -EINVAL; goto out; } if (!atomic64_read(&t->map->usercnt)) { /* maps with timers must be either held by user space * or pinned in bpffs. Otherwise timer might still be * running even when bpf prog is detached and user space * is gone, since map_release_uref won't ever be called. */ ret = -EPERM; goto out; } prev = t->prog; if (prev != prog) { /* Bump prog refcnt once. Every bpf_timer_set_callback() * can pick different callback_fn-s within the same prog. */ prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { ret = PTR_ERR(prog); goto out; } if (prev) /* Drop prev prog refcnt when swapping with new prog */ bpf_prog_put(prev); t->prog = prog; } rcu_assign_pointer(t->callback_fn, callback_fn); out: __bpf_spin_unlock_irqrestore(&timer->lock); return ret; } static const struct bpf_func_proto bpf_timer_set_callback_proto = { .func = bpf_timer_set_callback, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_TIMER, .arg2_type = ARG_PTR_TO_FUNC, }; BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, flags) { struct bpf_hrtimer *t; int ret = 0; if (in_nmi()) return -EOPNOTSUPP; if (flags) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t || !t->prog) { ret = -EINVAL; goto out; } hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT); out: __bpf_spin_unlock_irqrestore(&timer->lock); return ret; } static const struct bpf_func_proto bpf_timer_start_proto = { .func = bpf_timer_start, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_TIMER, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static void drop_prog_refcnt(struct bpf_hrtimer *t) { struct bpf_prog *prog = t->prog; if (prog) { bpf_prog_put(prog); t->prog = NULL; rcu_assign_pointer(t->callback_fn, NULL); } } BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) { struct bpf_hrtimer *t; int ret = 0; if (in_nmi()) return -EOPNOTSUPP; rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { ret = -EINVAL; goto out; } if (this_cpu_read(hrtimer_running) == t) { /* If bpf callback_fn is trying to bpf_timer_cancel() * its own timer the hrtimer_cancel() will deadlock * since it waits for callback_fn to finish */ ret = -EDEADLK; goto out; } drop_prog_refcnt(t); out: __bpf_spin_unlock_irqrestore(&timer->lock); /* Cancel the timer and wait for associated callback to finish * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); rcu_read_unlock(); return ret; } static const struct bpf_func_proto bpf_timer_cancel_proto = { .func = bpf_timer_cancel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_TIMER, }; /* This function is called by map_delete/update_elem for individual element and * by ops->map_release_uref when the user space reference to a map reaches zero. */ void bpf_timer_cancel_and_free(void *val) { struct bpf_timer_kern *timer = val; struct bpf_hrtimer *t; /* Performance optimization: read timer->timer without lock first. */ if (!READ_ONCE(timer->timer)) return; __bpf_spin_lock_irqsave(&timer->lock); /* re-read it under lock */ t = timer->timer; if (!t) goto out; drop_prog_refcnt(t); /* The subsequent bpf_timer_start/cancel() helpers won't be able to use * this timer, since it won't be initialized. */ WRITE_ONCE(timer->timer, NULL); out: __bpf_spin_unlock_irqrestore(&timer->lock); if (!t) return; /* Cancel the timer and wait for callback to complete if it was running. * If hrtimer_cancel() can be safely called it's safe to call kfree(t) * right after for both preallocated and non-preallocated maps. * The timer->timer = NULL was already done and no code path can * see address 't' anymore. * * Check that bpf_map_delete/update_elem() wasn't called from timer * callback_fn. In such case don't call hrtimer_cancel() (since it will * deadlock) and don't call hrtimer_try_to_cancel() (since it will just * return -1). Though callback_fn is still running on this cpu it's * safe to do kfree(t) because bpf_timer_cb() read everything it needed * from 't'. The bpf subprog callback_fn won't be able to access 't', * since timer->timer = NULL was already done. The timer will be * effectively cancelled because bpf_timer_cb() will return * HRTIMER_NORESTART. */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); kfree_rcu(t, rcu); } const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_get_current_task_btf_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; const struct bpf_func_proto bpf_probe_read_kernel_proto __weak; const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; case BPF_FUNC_map_update_elem: return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; case BPF_FUNC_map_push_elem: return &bpf_map_push_elem_proto; case BPF_FUNC_map_pop_elem: return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_raw_smp_processor_id_proto; case BPF_FUNC_get_numa_node_id: return &bpf_get_numa_node_id_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: return &bpf_ringbuf_reserve_proto; case BPF_FUNC_ringbuf_submit: return &bpf_ringbuf_submit_proto; case BPF_FUNC_ringbuf_discard: return &bpf_ringbuf_discard_proto; case BPF_FUNC_ringbuf_query: return &bpf_ringbuf_query_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; default: break; } if (!bpf_capable()) return NULL; switch (func_id) { case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; case BPF_FUNC_timer_init: return &bpf_timer_init_proto; case BPF_FUNC_timer_set_callback: return &bpf_timer_set_callback_proto; case BPF_FUNC_timer_start: return &bpf_timer_start_proto; case BPF_FUNC_timer_cancel: return &bpf_timer_cancel_proto; default: break; } if (!perfmon_capable()) return NULL; switch (func_id) { case BPF_FUNC_trace_printk: return bpf_get_trace_printk_proto(); case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_task_btf: return &bpf_get_current_task_btf_proto; case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_snprintf: return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; default: return NULL; } } |
| 5 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 | /* * Copyright (c) 2006, 2019 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 <net/sock.h> #include <linux/in.h> #include <linux/ipv6.h> #include <linux/if_arp.h> #include <linux/jhash.h> #include <linux/ratelimit.h> #include "rds.h" static struct rhashtable bind_hash_table; static const struct rhashtable_params ht_parms = { .nelem_hint = 768, .key_len = RDS_BOUND_KEY_LEN, .key_offset = offsetof(struct rds_sock, rs_bound_key), .head_offset = offsetof(struct rds_sock, rs_bound_node), .max_size = 16384, .min_size = 1024, }; /* Create a key for the bind hash table manipulation. Port is in network byte * order. */ static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr, __be16 port, __u32 scope_id) { memcpy(key, addr, sizeof(*addr)); key += sizeof(*addr); memcpy(key, &port, sizeof(port)); key += sizeof(port); memcpy(key, &scope_id, sizeof(scope_id)); } /* * Return the rds_sock bound at the given local address. * * The rx path can race with rds_release. We notice if rds_release() has * marked this socket and don't return a rs ref to the rx path. */ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __u32 scope_id) { u8 key[RDS_BOUND_KEY_LEN]; struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); return rs; } /* returns -ve errno or +ve port */ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, __be16 *port, __u32 scope_id) { int ret = -EADDRINUSE; u16 rover, last; u8 key[RDS_BOUND_KEY_LEN]; if (*port != 0) { rover = be16_to_cpu(*port); if (rover == RDS_FLAG_PROBE_PORT) return -EINVAL; last = rover; } else { rover = max_t(u16, prandom_u32(), 2); last = rover - 1; } do { if (rover == 0) rover++; if (rover == RDS_FLAG_PROBE_PORT) continue; __rds_create_bind_key(key, addr, cpu_to_be16(rover), scope_id); if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms)) continue; memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key)); rs->rs_bound_addr = *addr; net_get_random_once(&rs->rs_hash_initval, sizeof(rs->rs_hash_initval)); rs->rs_bound_port = cpu_to_be16(rover); rs->rs_bound_node.next = NULL; rds_sock_addref(rs); if (!rhashtable_insert_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms)) { *port = rs->rs_bound_port; rs->rs_bound_scope_id = scope_id; ret = 0; rdsdebug("rs %p binding to %pI6c:%d\n", rs, addr, (int)ntohs(*port)); break; } else { rs->rs_bound_addr = in6addr_any; rds_sock_put(rs); ret = -ENOMEM; break; } } while (rover++ != last); return ret; } void rds_remove_bound(struct rds_sock *rs) { if (ipv6_addr_any(&rs->rs_bound_addr)) return; rdsdebug("rs %p unbinding from %pI6c:%d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port)); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rds_sock_put(rs); rs->rs_bound_addr = in6addr_any; } int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; __u32 scope_id = 0; int ret = 0; __be16 port; /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; if (addr_len < sizeof(struct sockaddr_in) || sin->sin_addr.s_addr == htonl(INADDR_ANY) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(sin->sin_addr.s_addr)) return -EINVAL; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; port = sin->sin_port; #if IS_ENABLED(CONFIG_IPV6) } else if (uaddr->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr; int addr_type; if (addr_len < sizeof(struct sockaddr_in6)) return -EINVAL; addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) return -EINVAL; /* 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)) return -EINVAL; } /* The scope ID must be specified for link local address. */ if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) return -EINVAL; scope_id = sin6->sin6_scope_id; } binding_addr = &sin6->sin6_addr; port = sin6->sin6_port; #endif } else { return -EINVAL; } lock_sock(sk); /* RDS socket does not allow re-binding. */ if (!ipv6_addr_any(&rs->rs_bound_addr)) { ret = -EINVAL; goto out; } /* Socket is connected. The binding address should have the same * scope ID as the connected address, except the case when one is * non-link local address (scope_id is 0). */ if (!ipv6_addr_any(&rs->rs_conn_addr) && scope_id && rs->rs_bound_scope_id && scope_id != rs->rs_bound_scope_id) { ret = -EINVAL; goto out; } /* The transport can be set using SO_RDS_TRANSPORT option before the * socket is bound. */ if (rs->rs_transport) { trans = rs->rs_transport; if (!trans->laddr_check || trans->laddr_check(sock_net(sock->sk), binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; goto out; } } else { trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr, scope_id); if (!trans) { ret = -EADDRNOTAVAIL; pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n", __func__, binding_addr); goto out; } rs->rs_transport = trans; } sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) rs->rs_transport = NULL; out: release_sock(sk); return ret; } void rds_bind_lock_destroy(void) { rhashtable_destroy(&bind_hash_table); } int rds_bind_lock_init(void) { return rhashtable_init(&bind_hash_table, &ht_parms); } |
| 92 92 13 13 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/gen_estimator.c Simple rate estimator. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_packed *bstats; spinlock_t *stats_lock; seqcount_t *running; struct gnet_stats_basic_cpu __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u64 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock); __gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = from_timer(est, t, timer); struct gnet_stats_basic_packed b; u64 rate, brate; est_fetch_counters(est, &b); brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (b.packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); est->last_bytes = b.bytes; est->last_packets = b.packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: qdisc running seqcount * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_packed b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (lock) local_bh_disable(); est_fetch_counters(est, &b); if (lock) local_bh_enable(); est->last_bytes = b.bytes; est->last_packets = b.packets; if (lock) spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { del_timer_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); timer_setup(&est->timer, est_timer, 0); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (lock) spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = xchg((__force struct net_rate_estimator **)rate_est, NULL); if (est) { del_timer_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: qdisc running seqcount (might be NULL) * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 11 11 11 4 11 11 11 12 14 14 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 | // SPDX-License-Identifier: GPL-2.0-only /* * LED Triggers Core * * Copyright 2005-2007 Openedhand Ltd. * * Author: Richard Purdie <rpurdie@openedhand.com> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/device.h> #include <linux/timer.h> #include <linux/rwsem.h> #include <linux/leds.h> #include <linux/slab.h> #include <linux/mm.h> #include "leds.h" /* * Nests outside led_cdev->trigger_lock */ static DECLARE_RWSEM(triggers_list_lock); LIST_HEAD(trigger_list); /* Used by LED Class */ static inline bool trigger_relevant(struct led_classdev *led_cdev, struct led_trigger *trig) { return !trig->trigger_type || trig->trigger_type == led_cdev->trigger_type; } ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); struct led_trigger *trig; int ret = count; mutex_lock(&led_cdev->led_access); if (led_sysfs_is_disabled(led_cdev)) { ret = -EBUSY; goto unlock; } if (sysfs_streq(buf, "none")) { led_trigger_remove(led_cdev); goto unlock; } down_read(&triggers_list_lock); list_for_each_entry(trig, &trigger_list, next_trig) { if (sysfs_streq(buf, trig->name) && trigger_relevant(led_cdev, trig)) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, trig); up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); goto unlock; } } /* we come here only if buf matches no trigger */ ret = -EINVAL; up_read(&triggers_list_lock); unlock: mutex_unlock(&led_cdev->led_access); return ret; } EXPORT_SYMBOL_GPL(led_trigger_write); __printf(3, 4) static int led_trigger_snprintf(char *buf, ssize_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); if (size <= 0) i = vsnprintf(NULL, 0, fmt, args); else i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } static int led_trigger_format(char *buf, size_t size, struct led_classdev *led_cdev) { struct led_trigger *trig; int len = led_trigger_snprintf(buf, size, "%s", led_cdev->trigger ? "none" : "[none]"); list_for_each_entry(trig, &trigger_list, next_trig) { bool hit; if (!trigger_relevant(led_cdev, trig)) continue; hit = led_cdev->trigger && !strcmp(led_cdev->trigger->name, trig->name); len += led_trigger_snprintf(buf + len, size - len, " %s%s%s", hit ? "[" : "", trig->name, hit ? "]" : ""); } len += led_trigger_snprintf(buf + len, size - len, "\n"); return len; } /* * It was stupid to create 10000 cpu triggers, but we are stuck with it now. * Don't make that mistake again. We work around it here by creating binary * attribute, which is not limited by length. This is _not_ good design, do not * copy it. */ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); void *data; int len; down_read(&triggers_list_lock); down_read(&led_cdev->trigger_lock); len = led_trigger_format(NULL, 0, led_cdev); data = kvmalloc(len + 1, GFP_KERNEL); if (!data) { up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); return -ENOMEM; } len = led_trigger_format(data, len + 1, led_cdev); up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); len = memory_read_from_buffer(buf, count, &pos, data, len); kvfree(data); return len; } EXPORT_SYMBOL_GPL(led_trigger_read); /* Caller must ensure led_cdev->trigger_lock held */ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) { char *event = NULL; char *envp[2]; const char *name; int ret; if (!led_cdev->trigger && !trig) return 0; name = trig ? trig->name : "none"; event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name); /* Remove any existing trigger */ if (led_cdev->trigger) { spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); /* ensure it's no longer visible on the led_cdevs list */ synchronize_rcu(); cancel_work_sync(&led_cdev->set_brightness_work); led_stop_software_blink(led_cdev); device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_cdev->activated = false; led_set_brightness(led_cdev, LED_OFF); } if (trig) { spin_lock(&trig->leddev_list_lock); list_add_tail_rcu(&led_cdev->trig_list, &trig->led_cdevs); spin_unlock(&trig->leddev_list_lock); led_cdev->trigger = trig; /* * Some activate() calls use led_trigger_event() to initialize * the brightness of the LED for which the trigger is being set. * Ensure the led_cdev is visible on trig->led_cdevs for this. */ synchronize_rcu(); /* * If "set brightness to 0" is pending in workqueue, * we don't want that to be reordered after ->activate() */ flush_work(&led_cdev->set_brightness_work); ret = 0; if (trig->activate) ret = trig->activate(led_cdev); else led_set_brightness(led_cdev, trig->brightness); if (ret) goto err_activate; ret = device_add_groups(led_cdev->dev, trig->groups); if (ret) { dev_err(led_cdev->dev, "Failed to add trigger attributes\n"); goto err_add_groups; } } if (event) { envp[0] = event; envp[1] = NULL; if (kobject_uevent_env(&led_cdev->dev->kobj, KOBJ_CHANGE, envp)) dev_err(led_cdev->dev, "%s: Error sending uevent\n", __func__); kfree(event); } return 0; err_add_groups: if (trig->deactivate) trig->deactivate(led_cdev); err_activate: spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); synchronize_rcu(); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_set_brightness(led_cdev, LED_OFF); kfree(event); return ret; } EXPORT_SYMBOL_GPL(led_trigger_set); void led_trigger_remove(struct led_classdev *led_cdev) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } EXPORT_SYMBOL_GPL(led_trigger_remove); void led_trigger_set_default(struct led_classdev *led_cdev) { struct led_trigger *trig; if (!led_cdev->default_trigger) return; down_read(&triggers_list_lock); down_write(&led_cdev->trigger_lock); list_for_each_entry(trig, &trigger_list, next_trig) { if (!strcmp(led_cdev->default_trigger, trig->name) && trigger_relevant(led_cdev, trig)) { led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER; led_trigger_set(led_cdev, trig); break; } } up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); } EXPORT_SYMBOL_GPL(led_trigger_set_default); /* LED Trigger Interface */ int led_trigger_register(struct led_trigger *trig) { struct led_classdev *led_cdev; struct led_trigger *_trig; spin_lock_init(&trig->leddev_list_lock); INIT_LIST_HEAD(&trig->led_cdevs); down_write(&triggers_list_lock); /* Make sure the trigger's name isn't already in use */ list_for_each_entry(_trig, &trigger_list, next_trig) { if (!strcmp(_trig->name, trig->name) && (trig->trigger_type == _trig->trigger_type || !trig->trigger_type || !_trig->trigger_type)) { up_write(&triggers_list_lock); return -EEXIST; } } /* Add to the list of led triggers */ list_add_tail(&trig->next_trig, &trigger_list); up_write(&triggers_list_lock); /* Register with any LEDs that have this as a default trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (!led_cdev->trigger && led_cdev->default_trigger && !strcmp(led_cdev->default_trigger, trig->name) && trigger_relevant(led_cdev, trig)) { led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER; led_trigger_set(led_cdev, trig); } up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); return 0; } EXPORT_SYMBOL_GPL(led_trigger_register); void led_trigger_unregister(struct led_trigger *trig) { struct led_classdev *led_cdev; if (list_empty_careful(&trig->next_trig)) return; /* Remove from the list of led triggers */ down_write(&triggers_list_lock); list_del_init(&trig->next_trig); up_write(&triggers_list_lock); /* Remove anyone actively using this trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (led_cdev->trigger == trig) led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); } EXPORT_SYMBOL_GPL(led_trigger_unregister); static void devm_led_trigger_release(struct device *dev, void *res) { led_trigger_unregister(*(struct led_trigger **)res); } int devm_led_trigger_register(struct device *dev, struct led_trigger *trig) { struct led_trigger **dr; int rc; dr = devres_alloc(devm_led_trigger_release, sizeof(*dr), GFP_KERNEL); if (!dr) return -ENOMEM; *dr = trig; rc = led_trigger_register(trig); if (rc) devres_free(dr); else devres_add(dev, dr); return rc; } EXPORT_SYMBOL_GPL(devm_led_trigger_register); /* Simple LED Trigger Interface */ void led_trigger_event(struct led_trigger *trig, enum led_brightness brightness) { struct led_classdev *led_cdev; if (!trig) return; trig->brightness = brightness; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_trigger_event); static void led_trigger_blink_setup(struct led_trigger *trig, unsigned long *delay_on, unsigned long *delay_off, int oneshot, int invert) { struct led_classdev *led_cdev; if (!trig) return; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (oneshot) led_blink_set_oneshot(led_cdev, delay_on, delay_off, invert); else led_blink_set(led_cdev, delay_on, delay_off); } rcu_read_unlock(); } void led_trigger_blink(struct led_trigger *trig, unsigned long *delay_on, unsigned long *delay_off) { led_trigger_blink_setup(trig, delay_on, delay_off, 0, 0); } EXPORT_SYMBOL_GPL(led_trigger_blink); void led_trigger_blink_oneshot(struct led_trigger *trig, unsigned long *delay_on, unsigned long *delay_off, int invert) { led_trigger_blink_setup(trig, delay_on, delay_off, 1, invert); } EXPORT_SYMBOL_GPL(led_trigger_blink_oneshot); void led_trigger_register_simple(const char *name, struct led_trigger **tp) { struct led_trigger *trig; int err; trig = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); if (trig) { trig->name = name; err = led_trigger_register(trig); if (err < 0) { kfree(trig); trig = NULL; pr_warn("LED trigger %s failed to register (%d)\n", name, err); } } else { pr_warn("LED trigger %s failed to register (no memory)\n", name); } *tp = trig; } EXPORT_SYMBOL_GPL(led_trigger_register_simple); void led_trigger_unregister_simple(struct led_trigger *trig) { if (trig) led_trigger_unregister(trig); kfree(trig); } EXPORT_SYMBOL_GPL(led_trigger_unregister_simple); |
| 84 53 6 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 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 | /* * net/tipc/link.c: TIPC link code * * Copyright (c) 1996-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. 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. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "subscr.h" #include "link.h" #include "bcast.h" #include "socket.h" #include "name_distr.h" #include "discover.h" #include "netlink.h" #include "monitor.h" #include "trace.h" #include "crypto.h" #include <linux/pkt_sched.h> struct tipc_stats { u32 sent_pkts; u32 recv_pkts; u32 sent_states; u32 recv_states; u32 sent_probes; u32 recv_probes; u32 sent_nacks; u32 recv_nacks; u32 sent_acks; u32 sent_bundled; u32 sent_bundles; u32 recv_bundled; u32 recv_bundles; u32 retransmitted; u32 sent_fragmented; u32 sent_fragments; u32 recv_fragmented; u32 recv_fragments; u32 link_congs; /* # port sends blocked by congestion */ u32 deferred_recv; u32 duplicates; u32 max_queue_sz; /* send queue size high water mark */ u32 accu_queue_sz; /* used for send queue size profiling */ u32 queue_sz_counts; /* used for send queue size profiling */ u32 msg_length_counts; /* used for message length profiling */ u32 msg_lengths_total; /* used for message length profiling */ u32 msg_length_profile[7]; /* used for msg. length profiling */ }; /** * struct tipc_link - TIPC link data structure * @addr: network address of link's peer node * @name: link name character string * @media_addr: media address to use when sending messages over link * @timer: link timer * @net: pointer to namespace struct * @refcnt: reference counter for permanent references (owner node & timer) * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link * @tolerance: minimum link continuity loss needed to reset link [in ms] * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM * @peer_caps: bitmap describing capabilities of peer node * @silent_intv_cnt: # of timer intervals without any reception from peer * @proto_msg: template for control messages generated by link * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @mon_state: cookie with information needed by link monitor * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent * @snt_nxt: next sequence number to use for outbound messages * @ackers: # of peers that needs to ack each packet before it can be released * @acked: # last packet acked by a certain peer. Used for broadcast. * @rcv_nxt: next sequence number to expect for inbound messages * @deferred_queue: deferred queue saved OOS b'cast message received from node * @unacked_window: # of inbound messages rx'd without ack'ing back to peer * @inputq: buffer queue for messages to be delivered upwards * @namedq: buffer queue for name table messages to be delivered upwards * @next_out: ptr to first unsent outbound message in queue * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate * @long_msg_seq_no: next identifier to use for outbound fragmented messages * @reasm_buf: head of partially reassembled inbound message fragments * @bc_rcvr: marks that this is a broadcast receiver link * @stats: collects statistics regarding link activity * @session: session to be used by link * @snd_nxt_state: next send seq number * @rcv_nxt_state: next rcv seq number * @in_session: have received ACTIVATE_MSG from peer * @active: link is active * @if_name: associated interface name * @rst_cnt: link reset counter * @drop_point: seq number for failover handling (FIXME) * @failover_reasm_skb: saved failover msg ptr (FIXME) * @failover_deferdq: deferred message queue for failover processing (FIXME) * @transmq: the link's transmit queue * @backlog: link's backlog by priority (importance) * @snd_nxt: next sequence number to be used * @rcv_unacked: # messages read by user, but not yet acked back to peer * @deferdq: deferred receive queue * @window: sliding window size for congestion handling * @min_win: minimal send window to be used by link * @ssthresh: slow start threshold for congestion handling * @max_win: maximal send window to be used by link * @cong_acks: congestion acks for congestion avoidance (FIXME) * @checkpoint: seq number for congestion window size handling * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message * @last_gap: last gap ack blocks for bcast (FIXME) * @last_ga: ptr to gap ack blocks * @bc_rcvlink: the peer specific link used for broadcast reception * @bc_sndlink: the namespace global link used for broadcast sending * @nack_state: bcast nack state * @bc_peer_is_up: peer has acked the bcast init msg */ struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; struct net *net; /* Management and link supervision data */ u16 peer_session; u16 session; u16 snd_nxt_state; u16 rcv_nxt_state; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; u32 abort_limit; u32 state; u16 peer_caps; bool in_session; bool active; u32 silent_intv_cnt; char if_name[TIPC_MAX_IF_NAME]; u32 priority; char net_plane; struct tipc_mon_state mon_state; u16 rst_cnt; /* Failover/synch */ u16 drop_point; struct sk_buff *failover_reasm_skb; struct sk_buff_head failover_deferdq; /* Max packet negotiation */ u16 mtu; u16 advertised_mtu; /* Sending */ struct sk_buff_head transmq; struct sk_buff_head backlogq; struct { u16 len; u16 limit; struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; /* Reception */ u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; struct sk_buff_head *inputq; struct sk_buff_head *namedq; /* Congestion handling */ struct sk_buff_head wakeupq; u16 window; u16 min_win; u16 ssthresh; u16 max_win; u16 cong_acks; u16 checkpoint; /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; u16 acked; u16 last_gap; struct tipc_gap_ack_blks *last_ga; struct tipc_link *bc_rcvlink; struct tipc_link *bc_sndlink; u8 nack_state; bool bc_peer_is_up; /* Statistics */ struct tipc_stats stats; }; /* * Error message prefixes */ static const char *link_co_err = "Link tunneling error, "; static const char *link_rst_msg = "Resetting link "; /* Send states for broadcast NACKs */ enum { BC_NACK_SND_CONDITIONAL, BC_NACK_SND_UNCONDITIONAL, BC_NACK_SND_SUPPRESS, }; #define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) /* Link FSM states: */ enum { LINK_ESTABLISHED = 0xe, LINK_ESTABLISHING = 0xe << 4, LINK_RESET = 0x1 << 8, LINK_RESETTING = 0x2 << 12, LINK_PEER_RESET = 0xd << 16, LINK_FAILINGOVER = 0xf << 20, LINK_SYNCHING = 0xc << 24 }; /* Link FSM state checking routines */ static int link_is_up(struct tipc_link *l) { return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); } static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, bool probe_reply, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq); static void link_print(struct tipc_link *l, const char *str); static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, struct tipc_link *l, u8 start_index); static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr); static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, bool *retransmitted, int *rc); static void tipc_link_update_cwin(struct tipc_link *l, int released, bool retransmitted); /* * Simple non-static link routines (i.e. referenced outside this file) */ bool tipc_link_is_up(struct tipc_link *l) { return link_is_up(l); } bool tipc_link_peer_is_down(struct tipc_link *l) { return l->state == LINK_PEER_RESET; } bool tipc_link_is_reset(struct tipc_link *l) { return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING); } bool tipc_link_is_establishing(struct tipc_link *l) { return l->state == LINK_ESTABLISHING; } bool tipc_link_is_synching(struct tipc_link *l) { return l->state == LINK_SYNCHING; } bool tipc_link_is_failingover(struct tipc_link *l) { return l->state == LINK_FAILINGOVER; } bool tipc_link_is_blocked(struct tipc_link *l) { return l->state & (LINK_RESETTING | LINK_PEER_RESET | LINK_FAILINGOVER); } static bool link_is_bc_sndlink(struct tipc_link *l) { return !l->bc_sndlink; } static bool link_is_bc_rcvlink(struct tipc_link *l) { return ((l->bc_rcvlink == l) && !link_is_bc_sndlink(l)); } void tipc_link_set_active(struct tipc_link *l, bool active) { l->active = active; } u32 tipc_link_id(struct tipc_link *l) { return l->peer_bearer_id << 16 | l->bearer_id; } int tipc_link_min_win(struct tipc_link *l) { return l->min_win; } int tipc_link_max_win(struct tipc_link *l) { return l->max_win; } int tipc_link_prio(struct tipc_link *l) { return l->priority; } unsigned long tipc_link_tolerance(struct tipc_link *l) { return l->tolerance; } struct sk_buff_head *tipc_link_inputq(struct tipc_link *l) { return l->inputq; } char tipc_link_plane(struct tipc_link *l) { return l->net_plane; } struct net *tipc_link_net(struct tipc_link *l) { return l->net; } void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; } void tipc_link_add_bc_peer(struct tipc_link *snd_l, struct tipc_link *uc_l, struct sk_buff_head *xmitq) { struct tipc_link *rcv_l = uc_l->bc_rcvlink; snd_l->ackers++; rcv_l->acked = snd_l->snd_nxt - 1; snd_l->state = LINK_ESTABLISHED; tipc_link_build_bc_init_msg(uc_l, xmitq); } void tipc_link_remove_bc_peer(struct tipc_link *snd_l, struct tipc_link *rcv_l, struct sk_buff_head *xmitq) { u16 ack = snd_l->snd_nxt - 1; snd_l->ackers--; rcv_l->bc_peer_is_up = true; rcv_l->state = LINK_ESTABLISHED; tipc_link_bc_ack_rcv(rcv_l, ack, 0, NULL, xmitq, NULL); trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!"); tipc_link_reset(rcv_l); rcv_l->state = LINK_RESET; if (!snd_l->ackers) { trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!"); tipc_link_reset(snd_l); snd_l->state = LINK_RESET; __skb_queue_purge(xmitq); } } int tipc_link_bc_peers(struct tipc_link *l) { return l->ackers; } static u16 link_bc_rcv_gap(struct tipc_link *l) { struct sk_buff *skb = skb_peek(&l->deferdq); u16 gap = 0; if (more(l->snd_nxt, l->rcv_nxt)) gap = l->snd_nxt - l->rcv_nxt; if (skb) gap = buf_seqno(skb) - l->rcv_nxt; return gap; } void tipc_link_set_mtu(struct tipc_link *l, int mtu) { l->mtu = mtu; } int tipc_link_mtu(struct tipc_link *l) { return l->mtu; } int tipc_link_mss(struct tipc_link *l) { #ifdef CONFIG_TIPC_CRYPTO return l->mtu - INT_H_SIZE - EMSG_OVERHEAD; #else return l->mtu - INT_H_SIZE; #endif } u16 tipc_link_rcv_nxt(struct tipc_link *l) { return l->rcv_nxt; } u16 tipc_link_acked(struct tipc_link *l) { return l->acked; } char *tipc_link_name(struct tipc_link *l) { return l->name; } u32 tipc_link_state(struct tipc_link *l) { return l->state; } /** * tipc_link_create - create a new link * @net: pointer to associated network namespace * @if_name: associated interface name * @bearer_id: id (index) of associated bearer * @tolerance: link tolerance to be used by link * @net_plane: network plane (A,B,c..) this link belongs to * @mtu: mtu to be advertised by link * @priority: priority to be used by link * @min_win: minimal send window to be used by link * @max_win: maximal send window to be used by link * @session: session to be used by link * @peer: node id of peer node * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending * @bc_rcvlink: the peer specific link used for broadcast reception * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link * @self: local unicast link id * @peer_id: 128-bit ID of peer * * Return: true if link was created, otherwise false */ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, int tolerance, char net_plane, u32 mtu, int priority, u32 min_win, u32 max_win, u32 session, u32 self, u32 peer, u8 *peer_id, u16 peer_caps, struct tipc_link *bc_sndlink, struct tipc_link *bc_rcvlink, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link **link) { char peer_str[NODE_ID_STR_LEN] = {0,}; char self_str[NODE_ID_STR_LEN] = {0,}; struct tipc_link *l; l = kzalloc(sizeof(*l), GFP_ATOMIC); if (!l) return false; *link = l; l->session = session; /* Set link name for unicast links only */ if (peer_id) { tipc_nodeid2string(self_str, tipc_own_id(net)); if (strlen(self_str) > 16) sprintf(self_str, "%x", self); tipc_nodeid2string(peer_str, peer_id); if (strlen(peer_str) > 16) sprintf(peer_str, "%x", peer); } /* Peer i/f name will be completed by reset/activate message */ snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); strcpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; l->in_session = false; l->bearer_id = bearer_id; l->tolerance = tolerance; if (bc_rcvlink) bc_rcvlink->tolerance = tolerance; l->net_plane = net_plane; l->advertised_mtu = mtu; l->mtu = mtu; l->priority = priority; tipc_link_set_queue_limits(l, min_win, max_win); l->ackers = 1; l->bc_sndlink = bc_sndlink; l->bc_rcvlink = bc_rcvlink; l->inputq = inputq; l->namedq = namedq; l->state = LINK_RESETTING; __skb_queue_head_init(&l->transmq); __skb_queue_head_init(&l->backlogq); __skb_queue_head_init(&l->deferdq); __skb_queue_head_init(&l->failover_deferdq); skb_queue_head_init(&l->wakeupq); skb_queue_head_init(l->inputq); return true; } /** * tipc_link_bc_create - create new link to be used for broadcast * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers * @min_win: minimal send window to be used by link * @max_win: maximal send window to be used by link * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link * @ownnode: identity of own node * @peer: node id of peer node * @peer_id: 128-bit ID of peer * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending * * Return: true if link was created, otherwise false */ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, int mtu, u32 min_win, u32 max_win, u16 peer_caps, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, struct tipc_link **link) { struct tipc_link *l; if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win, max_win, 0, ownnode, peer, NULL, peer_caps, bc_sndlink, NULL, inputq, namedq, link)) return false; l = *link; if (peer_id) { char peer_str[NODE_ID_STR_LEN] = {0,}; tipc_nodeid2string(peer_str, peer_id); if (strlen(peer_str) > 16) sprintf(peer_str, "%x", peer); /* Broadcast receiver link name: "broadcast-link:<peer>" */ snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { strcpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); l->state = LINK_RESET; l->ackers = 0; l->bc_rcvlink = l; /* Broadcast send link is always up */ if (link_is_bc_sndlink(l)) l->state = LINK_ESTABLISHED; /* Disable replicast if even a single peer doesn't support it */ if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST)) tipc_bcast_toggle_rcast(net, false); return true; } /** * tipc_link_fsm_evt - link finite state machine * @l: pointer to link * @evt: state machine event to be processed */ int tipc_link_fsm_evt(struct tipc_link *l, int evt) { int rc = 0; int old_state = l->state; switch (l->state) { case LINK_RESETTING: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_FAILURE_EVT: case LINK_FAILOVER_BEGIN_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILOVER_END_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_RESET: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_ESTABLISHING; break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; break; case LINK_FAILURE_EVT: case LINK_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILOVER_END_EVT: break; case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_PEER_RESET: switch (evt) { case LINK_RESET_EVT: l->state = LINK_ESTABLISHING; break; case LINK_PEER_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILURE_EVT: break; case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; case LINK_FAILINGOVER: switch (evt) { case LINK_FAILOVER_END_EVT: l->state = LINK_RESET; break; case LINK_PEER_RESET_EVT: case LINK_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILURE_EVT: break; case LINK_FAILOVER_BEGIN_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_ESTABLISHING: switch (evt) { case LINK_ESTABLISH_EVT: l->state = LINK_ESTABLISHED; break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_FAILURE_EVT: case LINK_PEER_RESET_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_FAILOVER_END_EVT: break; case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_ESTABLISHED: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_FAILURE_EVT: l->state = LINK_RESETTING; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_ESTABLISH_EVT: case LINK_SYNCH_END_EVT: break; case LINK_SYNCH_BEGIN_EVT: l->state = LINK_SYNCHING; break; case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; case LINK_SYNCHING: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_FAILURE_EVT: l->state = LINK_RESETTING; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_ESTABLISH_EVT: case LINK_SYNCH_BEGIN_EVT: break; case LINK_SYNCH_END_EVT: l->state = LINK_ESTABLISHED; break; case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; default: pr_err("Unknown FSM state %x in %s\n", l->state, l->name); } trace_tipc_link_fsm(l->name, old_state, l->state, evt); return rc; illegal_evt: pr_err("Illegal FSM event %x in state %x on link %s\n", evt, l->state, l->name); trace_tipc_link_fsm(l->name, old_state, l->state, evt); return rc; } /* link_profile_stats - update statistical profiling of traffic */ static void link_profile_stats(struct tipc_link *l) { struct sk_buff *skb; struct tipc_msg *msg; int length; /* Update counters used in statistical profiling of send traffic */ l->stats.accu_queue_sz += skb_queue_len(&l->transmq); l->stats.queue_sz_counts++; skb = skb_peek(&l->transmq); if (!skb) return; msg = buf_msg(skb); length = msg_size(msg); if (msg_user(msg) == MSG_FRAGMENTER) { if (msg_type(msg) != FIRST_FRAGMENT) return; length = msg_size(msg_inner_hdr(msg)); } l->stats.msg_lengths_total += length; l->stats.msg_length_counts++; if (length <= 64) l->stats.msg_length_profile[0]++; else if (length <= 256) l->stats.msg_length_profile[1]++; else if (length <= 1024) l->stats.msg_length_profile[2]++; else if (length <= 4096) l->stats.msg_length_profile[3]++; else if (length <= 16384) l->stats.msg_length_profile[4]++; else if (length <= 32768) l->stats.msg_length_profile[5]++; else l->stats.msg_length_profile[6]++; } /** * tipc_link_too_silent - check if link is "too silent" * @l: tipc link to be checked * * Return: true if the link 'silent_intv_cnt' is about to reach the * 'abort_limit' value, otherwise false */ bool tipc_link_too_silent(struct tipc_link *l) { return (l->silent_intv_cnt + 2 > l->abort_limit); } /* tipc_link_timeout - perform periodic task as instructed from node timeout */ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) { int mtyp = 0; int rc = 0; bool state = false; bool probe = false; bool setup = false; u16 bc_snt = l->bc_sndlink->snd_nxt - 1; u16 bc_acked = l->bc_rcvlink->acked; struct tipc_mon_state *mstate = &l->mon_state; trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " "); trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " "); switch (l->state) { case LINK_ESTABLISHED: case LINK_SYNCHING: mtyp = STATE_MSG; link_profile_stats(l); tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id); if (mstate->reset || (l->silent_intv_cnt > l->abort_limit)) return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); state = bc_acked != bc_snt; state |= l->bc_rcvlink->rcv_unacked; state |= l->rcv_unacked; state |= !skb_queue_empty(&l->transmq); probe = mstate->probing; probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; probe |= !skb_queue_empty(&l->deferdq); if (l->snd_nxt == l->checkpoint) { tipc_link_update_cwin(l, 0, 0); probe = true; } l->checkpoint = l->snd_nxt; break; case LINK_RESET: setup = l->rst_cnt++ <= 4; setup |= !(l->rst_cnt % 16); mtyp = RESET_MSG; break; case LINK_ESTABLISHING: setup = true; mtyp = ACTIVATE_MSG; break; case LINK_PEER_RESET: case LINK_RESETTING: case LINK_FAILINGOVER: break; default: break; } if (state || probe || setup) tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq); return rc; } /** * link_schedule_user - schedule a message sender for wakeup after congestion * @l: congested link * @hdr: header of message that is being sent * Create pseudo msg to send back to user when congestion abates */ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) { u32 dnode = tipc_own_addr(l->net); u32 dport = msg_origport(hdr); struct sk_buff *skb; /* Create and schedule wakeup pseudo message */ skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); l->stats.link_congs++; trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!"); return -ELINKCONG; } /** * link_prepare_wakeup - prepare users for wakeup after congestion * @l: congested link * Wake up a number of waiting users, as permitted by available space * in the send queue */ static void link_prepare_wakeup(struct tipc_link *l) { struct sk_buff_head *wakeupq = &l->wakeupq; struct sk_buff_head *inputq = l->inputq; struct sk_buff *skb, *tmp; struct sk_buff_head tmpq; int avail[5] = {0,}; int imp = 0; __skb_queue_head_init(&tmpq); for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; skb_queue_walk_safe(wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; if (avail[imp] <= 0) continue; avail[imp]--; __skb_unlink(skb, wakeupq); __skb_queue_tail(&tmpq, skb); } spin_lock_bh(&inputq->lock); skb_queue_splice_tail(&tmpq, inputq); spin_unlock_bh(&inputq->lock); } /** * tipc_link_set_skb_retransmit_time - set the time at which retransmission of * the given skb should be next attempted * @skb: skb to set a future retransmission time for * @l: link the skb will be transmitted on */ static void tipc_link_set_skb_retransmit_time(struct sk_buff *skb, struct tipc_link *l) { if (link_is_bc_sndlink(l)) TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; else TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; } void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; u32 imp; __skb_queue_head_init(&list); l->in_session = false; /* Force re-synch of peer session number before establishing */ l->peer_session--; l->session++; l->mtu = l->advertised_mtu; spin_lock_bh(&l->wakeupq.lock); skb_queue_splice_init(&l->wakeupq, &list); spin_unlock_bh(&l->wakeupq.lock); spin_lock_bh(&l->inputq->lock); skb_queue_splice_init(&list, l->inputq); spin_unlock_bh(&l->inputq->lock); __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); __skb_queue_purge(&l->failover_deferdq); for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) { l->backlog[imp].len = 0; l->backlog[imp].target_bskb = NULL; } kfree_skb(l->reasm_buf); kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); l->reasm_buf = NULL; l->reasm_tnlmsg = NULL; l->failover_reasm_skb = NULL; l->rcv_unacked = 0; l->snd_nxt = 1; l->rcv_nxt = 1; l->snd_nxt_state = 1; l->rcv_nxt_state = 1; l->acked = 0; l->last_gap = 0; kfree(l->last_ga); l->last_ga = NULL; l->silent_intv_cnt = 0; l->rst_cnt = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); tipc_link_reset_stats(l); } /** * tipc_link_xmit(): enqueue buffer list according to queue situation * @l: link to use * @list: chain of buffers containing message * @xmitq: returned list of packets to be sent by caller * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) { struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff_head *transmq = &l->transmq; struct sk_buff *skb, *_skb; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; int pkt_cnt = skb_queue_len(list); unsigned int mss = tipc_link_mss(l); unsigned int cwin = l->window; unsigned int mtu = l->mtu; struct tipc_msg *hdr; bool new_bundle; int rc = 0; int imp; if (pkt_cnt <= 0) return 0; hdr = buf_msg(skb_peek(list)); if (unlikely(msg_size(hdr) > mtu)) { pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n", skb_queue_len(list), msg_user(hdr), msg_type(hdr), msg_size(hdr), mtu); __skb_queue_purge(list); return -EMSGSIZE; } imp = msg_importance(hdr); /* Allow oversubscription of one data msg per source at congestion */ if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) { if (imp == TIPC_SYSTEM_IMPORTANCE) { pr_warn("%s<%s>, link overflow", link_rst_msg, l->name); return -ENOBUFS; } rc = link_schedule_user(l, hdr); } if (pkt_cnt > 1) { l->stats.sent_fragmented++; l->stats.sent_fragments += pkt_cnt; } /* Prepare each packet for sending, and add to relevant queue: */ while ((skb = __skb_dequeue(list))) { if (likely(skb_queue_len(transmq) < cwin)) { hdr = buf_msg(skb); msg_set_seqno(hdr, seqno); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; l->stats.sent_pkts++; seqno++; continue; } if (tipc_msg_try_bundle(l->backlog[imp].target_bskb, &skb, mss, l->addr, &new_bundle)) { if (skb) { /* Keep a ref. to the skb for next try */ l->backlog[imp].target_bskb = skb; l->backlog[imp].len++; __skb_queue_tail(backlogq, skb); } else { if (new_bundle) { l->stats.sent_bundles++; l->stats.sent_bundled++; } l->stats.sent_bundled++; } continue; } l->backlog[imp].target_bskb = NULL; l->backlog[imp].len += (1 + skb_queue_len(list)); __skb_queue_tail(backlogq, skb); skb_queue_splice_tail_init(list, backlogq); } l->snd_nxt = seqno; return rc; } static void tipc_link_update_cwin(struct tipc_link *l, int released, bool retransmitted) { int bklog_len = skb_queue_len(&l->backlogq); struct sk_buff_head *txq = &l->transmq; int txq_len = skb_queue_len(txq); u16 cwin = l->window; /* Enter fast recovery */ if (unlikely(retransmitted)) { l->ssthresh = max_t(u16, l->window / 2, 300); l->window = min_t(u16, l->ssthresh, l->window); return; } /* Enter slow start */ if (unlikely(!released)) { l->ssthresh = max_t(u16, l->window / 2, 300); l->window = l->min_win; return; } /* Don't increase window if no pressure on the transmit queue */ if (txq_len + bklog_len < cwin) return; /* Don't increase window if there are holes the transmit queue */ if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len) return; l->cong_acks += released; /* Slow start */ if (cwin <= l->ssthresh) { l->window = min_t(u16, cwin + released, l->max_win); return; } /* Congestion avoidance */ if (l->cong_acks < cwin) return; l->window = min_t(u16, ++cwin, l->max_win); l->cong_acks = 0; } static void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; struct sk_buff_head *txq = &l->transmq; struct sk_buff *skb, *_skb; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; struct tipc_msg *hdr; u16 cwin = l->window; u32 imp; while (skb_queue_len(txq) < cwin) { skb = skb_peek(&l->backlogq); if (!skb) break; _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) break; __skb_dequeue(&l->backlogq); hdr = buf_msg(skb); imp = msg_importance(hdr); l->backlog[imp].len--; if (unlikely(skb == l->backlog[imp].target_bskb)) l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; msg_set_seqno(hdr, seqno); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); l->rcv_unacked = 0; l->stats.sent_pkts++; seqno++; } l->snd_nxt = seqno; } /** * link_retransmit_failure() - Detect repeated retransmit failures * @l: tipc link sender * @r: tipc link receiver (= l in case of unicast) * @rc: returned code * * Return: true if the repeated retransmit failures happens, otherwise * false */ static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r, int *rc) { struct sk_buff *skb = skb_peek(&l->transmq); struct tipc_msg *hdr; if (!skb) return false; if (!TIPC_SKB_CB(skb)->retr_cnt) return false; if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp + msecs_to_jiffies(r->tolerance * 10))) return false; hdr = buf_msg(skb); if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr))) return false; pr_warn("Retransmission failure on link <%s>\n", l->name); link_print(l, "State of link "); pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr)); pr_info("sqno %u, prev: %x, dest: %x\n", msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr)); pr_info("retr_stamp %d, retr_cnt %d\n", jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp), TIPC_SKB_CB(skb)->retr_cnt); trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); if (link_is_bc_sndlink(l)) { r->state = LINK_RESET; *rc |= TIPC_LINK_DOWN_EVT; } else { *rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } return true; } /* tipc_data_input - deliver data and name distr msgs to upper layer * * Consumes buffer if message is of right type * Node lock must be held */ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq; struct tipc_msg *hdr = buf_msg(skb); switch (msg_user(hdr)) { case TIPC_LOW_IMPORTANCE: case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { skb_queue_tail(mc_inputq, skb); return true; } fallthrough; case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; case GROUP_PROTOCOL: skb_queue_tail(mc_inputq, skb); return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; skb_queue_tail(l->namedq, skb); return true; case MSG_BUNDLER: case TUNNEL_PROTOCOL: case MSG_FRAGMENTER: case BCAST_PROTOCOL: return false; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: if (TIPC_SKB_CB(skb)->decrypted) { tipc_crypto_msg_rcv(l->net, skb); return true; } fallthrough; #endif default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); return true; } } /* tipc_link_input - process packet that has passed link protocol check * * Consumes buffer */ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq, struct sk_buff **reasm_skb) { struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; struct sk_buff_head tmpq; int usr = msg_user(hdr); int pos = 0; if (usr == MSG_BUNDLER) { skb_queue_head_init(&tmpq); l->stats.recv_bundles++; l->stats.recv_bundled += msg_msgcnt(hdr); while (tipc_msg_extract(skb, &iskb, &pos)) tipc_data_input(l, iskb, &tmpq); tipc_skb_queue_splice_tail(&tmpq, inputq); return 0; } else if (usr == MSG_FRAGMENTER) { l->stats.recv_fragments++; if (tipc_buf_append(reasm_skb, &skb)) { l->stats.recv_fragmented++; tipc_data_input(l, skb, inputq); } else if (!*reasm_skb && !link_is_bc_rcvlink(l)) { pr_warn_ratelimited("Unable to build fragment list\n"); return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } return 0; } else if (usr == BCAST_PROTOCOL) { tipc_bcast_lock(l->net); tipc_link_bc_init_rcv(l->bc_rcvlink, hdr); tipc_bcast_unlock(l->net); } kfree_skb(skb); return 0; } /* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the * inner message along with the ones in the old link's * deferdq * @l: tunnel link * @skb: TUNNEL_PROTOCOL message * @inputq: queue to put messages ready for delivery */ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff **reasm_skb = &l->failover_reasm_skb; struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg; struct sk_buff_head *fdefq = &l->failover_deferdq; struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; int ipos = 0; int rc = 0; u16 seqno; if (msg_type(hdr) == SYNCH_MSG) { kfree_skb(skb); return 0; } /* Not a fragment? */ if (likely(!msg_nof_fragms(hdr))) { if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) { pr_warn_ratelimited("Unable to extract msg, defq: %d\n", skb_queue_len(fdefq)); return 0; } kfree_skb(skb); } else { /* Set fragment type for buf_append */ if (msg_fragm_no(hdr) == 1) msg_set_type(hdr, FIRST_FRAGMENT); else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr)) msg_set_type(hdr, FRAGMENT); else msg_set_type(hdr, LAST_FRAGMENT); if (!tipc_buf_append(reasm_tnlmsg, &skb)) { /* Successful but non-complete reassembly? */ if (*reasm_tnlmsg || link_is_bc_rcvlink(l)) return 0; pr_warn_ratelimited("Unable to reassemble tunnel msg\n"); return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } iskb = skb; } do { seqno = buf_seqno(iskb); if (unlikely(less(seqno, l->drop_point))) { kfree_skb(iskb); continue; } if (unlikely(seqno != l->drop_point)) { __tipc_skb_queue_sorted(fdefq, seqno, iskb); continue; } l->drop_point++; if (!tipc_data_input(l, iskb, inputq)) rc |= tipc_link_input(l, iskb, inputq, reasm_skb); if (unlikely(rc)) break; } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point))); return rc; } /** * tipc_get_gap_ack_blks - get Gap ACK blocks from PROTOCOL/STATE_MSG * @ga: returned pointer to the Gap ACK blocks if any * @l: the tipc link * @hdr: the PROTOCOL/STATE_MSG header * @uc: desired Gap ACK blocks type, i.e. unicast (= 1) or broadcast (= 0) * * Return: the total Gap ACK blocks size */ u16 tipc_get_gap_ack_blks(struct tipc_gap_ack_blks **ga, struct tipc_link *l, struct tipc_msg *hdr, bool uc) { struct tipc_gap_ack_blks *p; u16 sz = 0; /* Does peer support the Gap ACK blocks feature? */ if (l->peer_caps & TIPC_GAP_ACK_BLOCK) { p = (struct tipc_gap_ack_blks *)msg_data(hdr); sz = ntohs(p->len); /* Sanity check */ if (sz == struct_size(p, gacks, size_add(p->ugack_cnt, p->bgack_cnt))) { /* Good, check if the desired type exists */ if ((uc && p->ugack_cnt) || (!uc && p->bgack_cnt)) goto ok; /* Backward compatible: peer might not support bc, but uc? */ } else if (uc && sz == struct_size(p, gacks, p->ugack_cnt)) { if (p->ugack_cnt) { p->bgack_cnt = 0; goto ok; } } } /* Other cases: ignore! */ p = NULL; ok: *ga = p; return sz; } static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, struct tipc_link *l, u8 start_index) { struct tipc_gap_ack *gacks = &ga->gacks[start_index]; struct sk_buff *skb = skb_peek(&l->deferdq); u16 expect, seqno = 0; u8 n = 0; if (!skb) return 0; expect = buf_seqno(skb); skb_queue_walk(&l->deferdq, skb) { seqno = buf_seqno(skb); if (unlikely(more(seqno, expect))) { gacks[n].ack = htons(expect - 1); gacks[n].gap = htons(seqno - expect); if (++n >= MAX_GAP_ACK_BLKS / 2) { pr_info_ratelimited("Gacks on %s: %d, ql: %d!\n", l->name, n, skb_queue_len(&l->deferdq)); return n; } } else if (unlikely(less(seqno, expect))) { pr_warn("Unexpected skb in deferdq!\n"); continue; } expect = seqno + 1; } /* last block */ gacks[n].ack = htons(seqno); gacks[n].gap = 0; n++; return n; } /* tipc_build_gap_ack_blks - build Gap ACK blocks * @l: tipc unicast link * @hdr: the tipc message buffer to store the Gap ACK blocks after built * * The function builds Gap ACK blocks for both the unicast & broadcast receiver * links of a certain peer, the buffer after built has the network data format * as found at the struct tipc_gap_ack_blks definition. * * returns the actual allocated memory size */ static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr) { struct tipc_link *bcl = l->bc_rcvlink; struct tipc_gap_ack_blks *ga; u16 len; ga = (struct tipc_gap_ack_blks *)msg_data(hdr); /* Start with broadcast link first */ tipc_bcast_lock(bcl->net); msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); ga->bgack_cnt = __tipc_build_gap_ack_blks(ga, bcl, 0); tipc_bcast_unlock(bcl->net); /* Now for unicast link, but an explicit NACK only (???) */ ga->ugack_cnt = (msg_seq_gap(hdr)) ? __tipc_build_gap_ack_blks(ga, l, ga->bgack_cnt) : 0; /* Total len */ len = struct_size(ga, gacks, size_add(ga->bgack_cnt, ga->ugack_cnt)); ga->len = htons(len); return len; } /* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing * acked packets, also doing retransmissions if * gaps found * @l: tipc link with transmq queue to be advanced * @r: tipc link "receiver" i.e. in case of broadcast (= "l" if unicast) * @acked: seqno of last packet acked by peer without any gaps before * @gap: # of gap packets * @ga: buffer pointer to Gap ACK blocks from peer * @xmitq: queue for accumulating the retransmitted packets if any * @retransmitted: returned boolean value if a retransmission is really issued * @rc: returned code e.g. TIPC_LINK_DOWN_EVT if a repeated retransmit failures * happens (- unlikely case) * * Return: the number of packets released from the link transmq */ static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, bool *retransmitted, int *rc) { struct tipc_gap_ack_blks *last_ga = r->last_ga, *this_ga = NULL; struct tipc_gap_ack *gacks = NULL; struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr; u32 qlen = skb_queue_len(&l->transmq); u16 nacked = acked, ngap = gap, gack_cnt = 0; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; u16 seqno, n = 0; u16 end = r->acked, start = end, offset = r->last_gap; u16 si = (last_ga) ? last_ga->start_index : 0; bool is_uc = !link_is_bc_sndlink(l); bool bc_has_acked = false; trace_tipc_link_retrans(r, acked + 1, acked + gap, &l->transmq); /* Determine Gap ACK blocks if any for the particular link */ if (ga && is_uc) { /* Get the Gap ACKs, uc part */ gack_cnt = ga->ugack_cnt; gacks = &ga->gacks[ga->bgack_cnt]; } else if (ga) { /* Copy the Gap ACKs, bc part, for later renewal if needed */ this_ga = kmemdup(ga, struct_size(ga, gacks, ga->bgack_cnt), GFP_ATOMIC); if (likely(this_ga)) { this_ga->start_index = 0; /* Start with the bc Gap ACKs */ gack_cnt = this_ga->bgack_cnt; gacks = &this_ga->gacks[0]; } else { /* Hmm, we can get in trouble..., simply ignore it */ pr_warn_ratelimited("Ignoring bc Gap ACKs, no memory\n"); } } /* Advance the link transmq */ skb_queue_walk_safe(&l->transmq, skb, tmp) { seqno = buf_seqno(skb); next_gap_ack: if (less_eq(seqno, nacked)) { if (is_uc) goto release; /* Skip packets peer has already acked */ if (!more(seqno, r->acked)) continue; /* Get the next of last Gap ACK blocks */ while (more(seqno, end)) { if (!last_ga || si >= last_ga->bgack_cnt) break; start = end + offset + 1; end = ntohs(last_ga->gacks[si].ack); offset = ntohs(last_ga->gacks[si].gap); si++; WARN_ONCE(more(start, end) || (!offset && si < last_ga->bgack_cnt) || si > MAX_GAP_ACK_BLKS, "Corrupted Gap ACK: %d %d %d %d %d\n", start, end, offset, si, last_ga->bgack_cnt); } /* Check against the last Gap ACK block */ if (in_range(seqno, start, end)) continue; /* Update/release the packet peer is acking */ bc_has_acked = true; if (--TIPC_SKB_CB(skb)->ackers) continue; release: /* release skb */ __skb_unlink(skb, &l->transmq); kfree_skb(skb); } else if (less_eq(seqno, nacked + ngap)) { /* First gap: check if repeated retrans failures? */ if (unlikely(seqno == acked + 1 && link_retransmit_failure(l, r, rc))) { /* Ignore this bc Gap ACKs if any */ kfree(this_ga); this_ga = NULL; break; } /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; tipc_link_set_skb_retransmit_time(skb, l); _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) continue; hdr = buf_msg(_skb); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; if (!is_uc) r->stats.retransmitted++; *retransmitted = true; /* Increase actual retrans counter & mark first time */ if (!TIPC_SKB_CB(skb)->retr_cnt++) TIPC_SKB_CB(skb)->retr_stamp = jiffies; } else { /* retry with Gap ACK blocks if any */ if (n >= gack_cnt) break; nacked = ntohs(gacks[n].ack); ngap = ntohs(gacks[n].gap); n++; goto next_gap_ack; } } /* Renew last Gap ACK blocks for bc if needed */ if (bc_has_acked) { if (this_ga) { kfree(last_ga); r->last_ga = this_ga; r->last_gap = gap; } else if (last_ga) { if (less(acked, start)) { si--; offset = start - acked - 1; } else if (less(acked, end)) { acked = end; } if (si < last_ga->bgack_cnt) { last_ga->start_index = si; r->last_gap = offset; } else { kfree(last_ga); r->last_ga = NULL; r->last_gap = 0; } } else { r->last_gap = 0; } r->acked = acked; } else { kfree(this_ga); } return qlen - skb_queue_len(&l->transmq); } /* tipc_link_build_state_msg: prepare link state message for transmission * * Note that sending of broadcast ack is coordinated among nodes, to reduce * risk of ack storms towards the sender */ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { if (!l) return 0; /* Broadcast ACK must be sent via a unicast link => defer to caller */ if (link_is_bc_rcvlink(l)) { if (((l->rcv_nxt ^ tipc_own_addr(l->net)) & 0xf) != 0xf) return 0; l->rcv_unacked = 0; /* Use snd_nxt to store peer's snd_nxt in broadcast rcv link */ l->snd_nxt = l->rcv_nxt; return TIPC_LINK_SND_STATE; } /* Unicast ACK */ l->rcv_unacked = 0; l->stats.sent_acks++; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); return 0; } /* tipc_link_build_reset_msg: prepare link RESET or ACTIVATE message */ void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { int mtyp = RESET_MSG; struct sk_buff *skb; if (l->state == LINK_ESTABLISHING) mtyp = ACTIVATE_MSG; tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, 0, xmitq); /* Inform peer that this endpoint is going down if applicable */ skb = skb_peek_tail(xmitq); if (skb && (l->state == LINK_RESET)) msg_set_peer_stopping(buf_msg(skb), 1); } /* tipc_link_build_nack_msg: prepare link nack message for transmission * Note that sending of broadcast NACK is coordinated among nodes, to * reduce the risk of NACK storms towards the sender */ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; struct sk_buff_head *dfq = &l->deferdq; u32 defq_len = skb_queue_len(dfq); int match1, match2; if (link_is_bc_rcvlink(l)) { match1 = def_cnt & 0xf; match2 = tipc_own_addr(l->net) & 0xf; if (match1 == match2) return TIPC_LINK_SND_STATE; return 0; } if (defq_len >= 3 && !((defq_len - 3) % 16)) { u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, rcvgap, 0, 0, xmitq); } return 0; } /* tipc_link_rcv - process TIPC packets/messages arriving from off-node * @l: the link that should handle the message * @skb: TIPC packet * @xmitq: queue to place packets to be sent after this call */ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct sk_buff_head *defq = &l->deferdq; struct tipc_msg *hdr = buf_msg(skb); u16 seqno, rcv_nxt, win_lim; int released = 0; int rc = 0; /* Verify and update link state */ if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) return tipc_link_proto_rcv(l, skb, xmitq); /* Don't send probe at next timeout expiration */ l->silent_intv_cnt = 0; do { hdr = buf_msg(skb); seqno = msg_seqno(hdr); rcv_nxt = l->rcv_nxt; win_lim = rcv_nxt + TIPC_MAX_LINK_WIN; if (unlikely(!link_is_up(l))) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; kfree_skb(skb); break; } /* Drop if outside receive window */ if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) { l->stats.duplicates++; kfree_skb(skb); break; } released += tipc_link_advance_transmq(l, l, msg_ack(hdr), 0, NULL, NULL, NULL, NULL); /* Defer delivery if sequence gap */ if (unlikely(seqno != rcv_nxt)) { if (!__tipc_skb_queue_sorted(defq, seqno, skb)) l->stats.duplicates++; rc |= tipc_link_build_nack_msg(l, xmitq); break; } /* Deliver packet */ l->rcv_nxt++; l->stats.recv_pkts++; if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL)) rc |= tipc_link_tnl_rcv(l, skb, l->inputq); else if (!tipc_data_input(l, skb, l->inputq)) rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) rc |= tipc_link_build_state_msg(l, xmitq); if (unlikely(rc & ~TIPC_LINK_SND_STATE)) break; } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt))); /* Forward queues and wake up waiting users */ if (released) { tipc_link_update_cwin(l, released, 0); tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } return rc; } static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, bool probe_reply, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq) { struct tipc_mon_state *mstate = &l->mon_state; struct sk_buff_head *dfq = &l->deferdq; struct tipc_link *bcl = l->bc_rcvlink; struct tipc_msg *hdr; struct sk_buff *skb; bool node_up = link_is_up(bcl); u16 glen = 0, bc_rcvgap = 0; int dlen = 0; void *data; /* Don't send protocol message during reset or link failover */ if (tipc_link_is_blocked(l)) return; if (!tipc_link_is_up(l) && (mtyp == STATE_MSG)) return; if ((probe || probe_reply) && !skb_queue_empty(dfq)) rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return; hdr = buf_msg(skb); data = msg_data(hdr); msg_set_session(hdr, l->session); msg_set_bearer_id(hdr, l->bearer_id); msg_set_net_plane(hdr, l->net_plane); msg_set_next_sent(hdr, l->snd_nxt); msg_set_ack(hdr, l->rcv_nxt - 1); msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); msg_set_bc_ack_invalid(hdr, !node_up); msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1); msg_set_link_tolerance(hdr, tolerance); msg_set_linkprio(hdr, priority); msg_set_redundant_link(hdr, node_up); msg_set_seq_gap(hdr, 0); msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2); if (mtyp == STATE_MSG) { if (l->peer_caps & TIPC_LINK_PROTO_SEQNO) msg_set_seqno(hdr, l->snd_nxt_state++); msg_set_seq_gap(hdr, rcvgap); bc_rcvgap = link_bc_rcv_gap(bcl); msg_set_bc_gap(hdr, bc_rcvgap); msg_set_probe(hdr, probe); msg_set_is_keepalive(hdr, probe || probe_reply); if (l->peer_caps & TIPC_GAP_ACK_BLOCK) glen = tipc_build_gap_ack_blks(l, hdr); tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + glen + dlen); skb_trim(skb, INT_H_SIZE + glen + dlen); l->stats.sent_states++; l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ if (mtyp == ACTIVATE_MSG) { msg_set_dest_session_valid(hdr, 1); msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } if (probe) l->stats.sent_probes++; if (rcvgap) l->stats.sent_nacks++; if (bc_rcvgap) bcl->stats.sent_nacks++; skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, skb); trace_tipc_proto_build(skb, false, l->name); } void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 onode = tipc_own_addr(l->net); struct tipc_msg *hdr, *ihdr; struct sk_buff_head tnlq; struct sk_buff *skb; u32 dnode = l->addr; __skb_queue_head_init(&tnlq); skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, INT_H_SIZE, BASIC_H_SIZE, dnode, onode, 0, 0, 0); if (!skb) { pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } hdr = buf_msg(skb); msg_set_msgcnt(hdr, 1); msg_set_bearer_id(hdr, l->peer_bearer_id); ihdr = (struct tipc_msg *)msg_data(hdr); tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, BASIC_H_SIZE, dnode); msg_set_errcode(ihdr, TIPC_ERR_NO_PORT); __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, xmitq); } /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets * with contents of the link's transmit and backlog queues. */ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq) { struct sk_buff_head *fdefq = &tnl->failover_deferdq; struct sk_buff *skb, *tnlskb; struct tipc_msg *hdr, tnlhdr; struct sk_buff_head *queue = &l->transmq; struct sk_buff_head tmpxq, tnlq, frags; u16 pktlen, pktcnt, seqno = l->snd_nxt; bool pktcnt_need_update = false; u16 syncpt; int rc; if (!tnl) return; __skb_queue_head_init(&tnlq); /* Link Synching: * From now on, send only one single ("dummy") SYNCH message * to peer. The SYNCH message does not contain any data, just * a header conveying the synch point to the peer. */ if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG, INT_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!tnlskb) { pr_warn("%sunable to create dummy SYNCH_MSG\n", link_co_err); return; } hdr = buf_msg(tnlskb); syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1; msg_set_syncpt(hdr, syncpt); msg_set_bearer_id(hdr, l->peer_bearer_id); __skb_queue_tail(&tnlq, tnlskb); tipc_link_xmit(tnl, &tnlq, xmitq); return; } __skb_queue_head_init(&tmpxq); __skb_queue_head_init(&frags); /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, TIPC_ERR_NO_PORT); if (!skb) { pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, &tmpxq); __skb_queue_purge(&tmpxq); /* Initialize reusable tunnel packet header */ tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); if (mtyp == SYNCH_MSG) pktcnt = l->snd_nxt - buf_seqno(skb_peek(&l->transmq)); else pktcnt = skb_queue_len(&l->transmq); pktcnt += skb_queue_len(&l->backlogq); msg_set_msgcnt(&tnlhdr, pktcnt); msg_set_bearer_id(&tnlhdr, l->peer_bearer_id); tnl: /* Wrap each packet into a tunnel packet */ skb_queue_walk(queue, skb) { hdr = buf_msg(skb); if (queue == &l->backlogq) msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); /* Tunnel link MTU is not large enough? This could be * due to: * 1) Link MTU has just changed or set differently; * 2) Or FAILOVER on the top of a SYNCH message * * The 2nd case should not happen if peer supports * TIPC_TUNNEL_ENHANCED */ if (pktlen > tnl->mtu - INT_H_SIZE) { if (mtyp == FAILOVER_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu, &frags); if (rc) { pr_warn("%sunable to frag msg: rc %d\n", link_co_err, rc); return; } pktcnt += skb_queue_len(&frags) - 1; pktcnt_need_update = true; skb_queue_splice_tail_init(&frags, &tnlq); continue; } /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED * => Just warn it and return! */ pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n", link_co_err, msg_user(hdr), msg_type(hdr), msg_size(hdr)); return; } msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { pr_warn("%sunable to send packet\n", link_co_err); return; } skb_copy_to_linear_data(tnlskb, &tnlhdr, INT_H_SIZE); skb_copy_to_linear_data_offset(tnlskb, INT_H_SIZE, hdr, pktlen); __skb_queue_tail(&tnlq, tnlskb); } if (queue != &l->backlogq) { queue = &l->backlogq; goto tnl; } if (pktcnt_need_update) skb_queue_walk(&tnlq, skb) { hdr = buf_msg(skb); msg_set_msgcnt(hdr, pktcnt); } tipc_link_xmit(tnl, &tnlq, xmitq); if (mtyp == FAILOVER_MSG) { tnl->drop_point = l->rcv_nxt; tnl->failover_reasm_skb = l->reasm_buf; l->reasm_buf = NULL; /* Failover the link's deferdq */ if (unlikely(!skb_queue_empty(fdefq))) { pr_warn("Link failover deferdq not empty: %d!\n", skb_queue_len(fdefq)); __skb_queue_purge(fdefq); } skb_queue_splice_init(&l->deferdq, fdefq); } } /** * tipc_link_failover_prepare() - prepare tnl for link failover * * This is a special version of the precursor - tipc_link_tnl_prepare(), * see the tipc_node_link_failover() for details * * @l: failover link * @tnl: tunnel link * @xmitq: queue for messages to be xmited */ void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff_head *xmitq) { struct sk_buff_head *fdefq = &tnl->failover_deferdq; tipc_link_create_dummy_tnl_msg(tnl, xmitq); /* This failover link endpoint was never established before, * so it has not received anything from peer. * Otherwise, it must be a normal failover situation or the * node has entered SELF_DOWN_PEER_LEAVING and both peer nodes * would have to start over from scratch instead. */ tnl->drop_point = 1; tnl->failover_reasm_skb = NULL; /* Initiate the link's failover deferdq */ if (unlikely(!skb_queue_empty(fdefq))) { pr_warn("Link failover deferdq not empty: %d!\n", skb_queue_len(fdefq)); __skb_queue_purge(fdefq); } } /* tipc_link_validate_msg(): validate message against current link state * Returns true if message should be accepted, otherwise false */ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) { u16 curr_session = l->peer_session; u16 session = msg_session(hdr); int mtyp = msg_type(hdr); if (msg_user(hdr) != LINK_PROTOCOL) return true; switch (mtyp) { case RESET_MSG: if (!l->in_session) return true; /* Accept only RESET with new session number */ return more(session, curr_session); case ACTIVATE_MSG: if (!l->in_session) return true; /* Accept only ACTIVATE with new or current session number */ return !less(session, curr_session); case STATE_MSG: /* Accept only STATE with current session number */ if (!l->in_session) return false; if (session != curr_session) return false; /* Extra sanity check */ if (!link_is_up(l) && msg_ack(hdr)) return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; /* Accept only STATE with new sequence number */ return !less(msg_seqno(hdr), l->rcv_nxt_state); default: return false; } } /* tipc_link_proto_rcv(): receive link level protocol message : * Note that network plane id propagates through the network, and may * change at any time. The node with lowest numerical id determines * network plane */ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); u16 gap = msg_seq_gap(hdr); u16 ack = msg_ack(hdr); u16 rcv_nxt = l->rcv_nxt; u16 rcvgap = 0; int mtyp = msg_type(hdr); int rc = 0, released; char *if_name; void *data; trace_tipc_proto_rcv(skb, false, l->name); if (dlen > U16_MAX) goto exit; if (tipc_link_is_blocked(l) || !xmitq) goto exit; if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); if (skb_linearize(skb)) goto exit; hdr = buf_msg(skb); data = msg_data(hdr); if (!tipc_link_validate_msg(l, hdr)) { trace_tipc_skb_dump(skb, false, "PROTO invalid (1)!"); trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (1)!"); goto exit; } switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: msg_max = msg_max_pkt(hdr); if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) break; if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) break; strncpy(if_name, data, TIPC_MAX_IF_NAME); /* Update own tolerance if peer indicates a non-zero value */ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own priority if peer's priority is higher */ if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; /* If peer is going down we want full re-establish cycle */ if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } /* If this endpoint was re-created while peer was ESTABLISHING * it doesn't know current session number. Force re-synch. */ if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && l->session != msg_dest_session(hdr)) { if (less(l->session, msg_dest_session(hdr))) l->session = msg_dest_session(hdr) + 1; break; } /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); if (l->mtu > msg_max) l->mtu = msg_max; break; case STATE_MSG: /* Validate Gap ACK blocks, drop if invalid */ glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); if (glen > dlen) break; l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) && in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { l->priority = peers_prio; rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } l->silent_intv_cnt = 0; l->stats.recv_states++; if (msg_probe(hdr)) l->stats.recv_probes++; if (!link_is_up(l)) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; break; } tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); /* Send NACK if peer has sent pkts we haven't received yet */ if ((reply || msg_is_keepalive(hdr)) && more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l) && skb_queue_empty(&l->deferdq)) rcvgap = peers_snd_nxt - l->rcv_nxt; if (rcvgap || reply) tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, rcvgap, 0, 0, xmitq); released = tipc_link_advance_transmq(l, l, ack, gap, ga, xmitq, &retransmitted, &rc); if (gap) l->stats.recv_nacks++; if (released || retransmitted) tipc_link_update_cwin(l, released, retransmitted); if (released) tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } exit: kfree_skb(skb); return rc; } /* tipc_link_build_bc_proto_msg() - create broadcast protocol message */ static bool tipc_link_build_bc_proto_msg(struct tipc_link *l, bool bcast, u16 peers_snd_nxt, struct sk_buff_head *xmitq) { struct sk_buff *skb; struct tipc_msg *hdr; struct sk_buff *dfrd_skb = skb_peek(&l->deferdq); u16 ack = l->rcv_nxt - 1; u16 gap_to = peers_snd_nxt - 1; skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return false; hdr = buf_msg(skb); msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1); msg_set_bcast_ack(hdr, ack); msg_set_bcgap_after(hdr, ack); if (dfrd_skb) gap_to = buf_seqno(dfrd_skb) - 1; msg_set_bcgap_to(hdr, gap_to); msg_set_non_seq(hdr, bcast); __skb_queue_tail(xmitq, skb); return true; } /* tipc_link_build_bc_init_msg() - synchronize broadcast link endpoints. * * Give a newly added peer node the sequence number where it should * start receiving and acking broadcast packets. */ static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { struct sk_buff_head list; __skb_queue_head_init(&list); if (!tipc_link_build_bc_proto_msg(l->bc_rcvlink, false, 0, &list)) return; msg_set_bc_ack_invalid(buf_msg(skb_peek(&list)), true); tipc_link_xmit(l, &list, xmitq); } /* tipc_link_bc_init_rcv - receive initial broadcast synch data from peer */ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) { int mtyp = msg_type(hdr); u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); if (link_is_up(l)) return; if (msg_user(hdr) == BCAST_PROTOCOL) { l->rcv_nxt = peers_snd_nxt; l->state = LINK_ESTABLISHED; return; } if (l->peer_caps & TIPC_BCAST_SYNCH) return; if (msg_peer_node_is_up(hdr)) return; /* Compatibility: accept older, less safe initial synch data */ if ((mtyp == RESET_MSG) || (mtyp == ACTIVATE_MSG)) l->rcv_nxt = peers_snd_nxt; } /* tipc_link_bc_sync_rcv - update rcv link according to peer's send state */ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, struct sk_buff_head *xmitq) { u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); int rc = 0; if (!link_is_up(l)) return rc; if (!msg_peer_node_is_up(hdr)) return rc; /* Open when peer acknowledges our bcast init msg (pkt #1) */ if (msg_ack(hdr)) l->bc_peer_is_up = true; if (!l->bc_peer_is_up) return rc; /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) return rc; l->snd_nxt = peers_snd_nxt; if (link_bc_rcv_gap(l)) rc |= TIPC_LINK_SND_STATE; /* Return now if sender supports nack via STATE messages */ if (l->peer_caps & TIPC_BCAST_STATE_NACK) return rc; /* Otherwise, be backwards compatible */ if (!more(peers_snd_nxt, l->rcv_nxt)) { l->nack_state = BC_NACK_SND_CONDITIONAL; return 0; } /* Don't NACK if one was recently sent or peeked */ if (l->nack_state == BC_NACK_SND_SUPPRESS) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; return 0; } /* Conditionally delay NACK sending until next synch rcv */ if (l->nack_state == BC_NACK_SND_CONDITIONAL) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; if ((peers_snd_nxt - l->rcv_nxt) < TIPC_MIN_LINK_WIN) return 0; } /* Send NACK now but suppress next one */ tipc_link_build_bc_proto_msg(l, true, peers_snd_nxt, xmitq); l->nack_state = BC_NACK_SND_SUPPRESS; return 0; } int tipc_link_bc_ack_rcv(struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, struct sk_buff_head *retrq) { struct tipc_link *l = r->bc_sndlink; bool unused = false; int rc = 0; if (!link_is_up(r) || !r->bc_peer_is_up) return 0; if (gap) { l->stats.recv_nacks++; r->stats.recv_nacks++; } if (less(acked, r->acked) || (acked == r->acked && !gap && !ga)) return 0; trace_tipc_link_bc_ack(r, acked, gap, &l->transmq); tipc_link_advance_transmq(l, r, acked, gap, ga, retrq, &unused, &rc); tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); return rc; } /* tipc_link_bc_nack_rcv(): receive broadcast nack message * This function is here for backwards compatibility, since * no BCAST_PROTOCOL/STATE messages occur from TIPC v2.5. */ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); u32 dnode = msg_destnode(hdr); int mtyp = msg_type(hdr); u16 acked = msg_bcast_ack(hdr); u16 from = acked + 1; u16 to = msg_bcgap_to(hdr); u16 peers_snd_nxt = to + 1; int rc = 0; kfree_skb(skb); if (!tipc_link_is_up(l) || !l->bc_peer_is_up) return 0; if (mtyp != STATE_MSG) return 0; if (dnode == tipc_own_addr(l->net)) { rc = tipc_link_bc_ack_rcv(l, acked, to - acked, NULL, xmitq, xmitq); l->stats.recv_nacks++; return rc; } /* Msg for other node => suppress own NACK at next sync if applicable */ if (more(peers_snd_nxt, l->rcv_nxt) && !less(l->rcv_nxt, from)) l->nack_state = BC_NACK_SND_SUPPRESS; return 0; } void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win) { int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE); l->min_win = min_win; l->ssthresh = max_win; l->max_win = max_win; l->window = min_win; l->backlog[TIPC_LOW_IMPORTANCE].limit = min_win * 2; l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = min_win * 4; l->backlog[TIPC_HIGH_IMPORTANCE].limit = min_win * 6; l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = min_win * 8; l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } /** * tipc_link_reset_stats - reset link statistics * @l: pointer to link */ void tipc_link_reset_stats(struct tipc_link *l) { memset(&l->stats, 0, sizeof(l->stats)); } static void link_print(struct tipc_link *l, const char *str) { struct sk_buff *hskb = skb_peek(&l->transmq); u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt - 1; u16 tail = l->snd_nxt - 1; pr_info("%s Link <%s> state %x\n", str, l->name, l->state); pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n", skb_queue_len(&l->transmq), head, tail, skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt); } /* Parse and validate nested (link) properties valid for media, bearer and link */ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]) { int err; err = nla_parse_nested_deprecated(props, TIPC_NLA_PROP_MAX, prop, tipc_nl_prop_policy, NULL); if (err) return err; if (props[TIPC_NLA_PROP_PRIO]) { u32 prio; prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (prio > TIPC_MAX_LINK_PRI) return -EINVAL; } if (props[TIPC_NLA_PROP_TOL]) { u32 tol; tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) return -EINVAL; } if (props[TIPC_NLA_PROP_WIN]) { u32 max_win; max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (max_win < TIPC_DEF_LINK_WIN || max_win > TIPC_MAX_LINK_WIN) return -EINVAL; } return 0; } static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) { int i; struct nlattr *stats; struct nla_map { u32 key; u32 val; }; struct nla_map map[] = { {TIPC_NLA_STATS_RX_INFO, 0}, {TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled}, {TIPC_NLA_STATS_TX_INFO, 0}, {TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles}, {TIPC_NLA_STATS_TX_BUNDLED, s->sent_bundled}, {TIPC_NLA_STATS_MSG_PROF_TOT, (s->msg_length_counts) ? s->msg_length_counts : 1}, {TIPC_NLA_STATS_MSG_LEN_CNT, s->msg_length_counts}, {TIPC_NLA_STATS_MSG_LEN_TOT, s->msg_lengths_total}, {TIPC_NLA_STATS_MSG_LEN_P0, s->msg_length_profile[0]}, {TIPC_NLA_STATS_MSG_LEN_P1, s->msg_length_profile[1]}, {TIPC_NLA_STATS_MSG_LEN_P2, s->msg_length_profile[2]}, {TIPC_NLA_STATS_MSG_LEN_P3, s->msg_length_profile[3]}, {TIPC_NLA_STATS_MSG_LEN_P4, s->msg_length_profile[4]}, {TIPC_NLA_STATS_MSG_LEN_P5, s->msg_length_profile[5]}, {TIPC_NLA_STATS_MSG_LEN_P6, s->msg_length_profile[6]}, {TIPC_NLA_STATS_RX_STATES, s->recv_states}, {TIPC_NLA_STATS_RX_PROBES, s->recv_probes}, {TIPC_NLA_STATS_RX_NACKS, s->recv_nacks}, {TIPC_NLA_STATS_RX_DEFERRED, s->deferred_recv}, {TIPC_NLA_STATS_TX_STATES, s->sent_states}, {TIPC_NLA_STATS_TX_PROBES, s->sent_probes}, {TIPC_NLA_STATS_TX_NACKS, s->sent_nacks}, {TIPC_NLA_STATS_TX_ACKS, s->sent_acks}, {TIPC_NLA_STATS_RETRANSMITTED, s->retransmitted}, {TIPC_NLA_STATS_DUPLICATES, s->duplicates}, {TIPC_NLA_STATS_LINK_CONGS, s->link_congs}, {TIPC_NLA_STATS_MAX_QUEUE, s->max_queue_sz}, {TIPC_NLA_STATS_AVG_QUEUE, s->queue_sz_counts ? (s->accu_queue_sz / s->queue_sz_counts) : 0} }; stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!stats) return -EMSGSIZE; for (i = 0; i < ARRAY_SIZE(map); i++) if (nla_put_u32(skb, map[i].key, map[i].val)) goto msg_full; nla_nest_end(skb, stats); return 0; msg_full: nla_nest_cancel(skb, stats); return -EMSGSIZE; } /* Caller should hold appropriate locks to protect the link */ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_link *link, int nlflags) { u32 self = tipc_own_addr(net); struct nlattr *attrs; struct nlattr *prop; void *hdr; int err; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_LINK_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST, tipc_cluster_mask(self))) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts)) goto attr_msg_full; if (tipc_link_is_up(link)) if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP)) goto attr_msg_full; if (link->active) if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, link->window)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; nla_nest_end(msg->skb, prop); err = __tipc_nl_add_stats(msg->skb, &link->stats); if (err) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, struct tipc_stats *stats) { int i; struct nlattr *nest; struct nla_map { __u32 key; __u32 val; }; struct nla_map map[] = { {TIPC_NLA_STATS_RX_INFO, stats->recv_pkts}, {TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled}, {TIPC_NLA_STATS_TX_INFO, stats->sent_pkts}, {TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles}, {TIPC_NLA_STATS_TX_BUNDLED, stats->sent_bundled}, {TIPC_NLA_STATS_RX_NACKS, stats->recv_nacks}, {TIPC_NLA_STATS_RX_DEFERRED, stats->deferred_recv}, {TIPC_NLA_STATS_TX_NACKS, stats->sent_nacks}, {TIPC_NLA_STATS_TX_ACKS, stats->sent_acks}, {TIPC_NLA_STATS_RETRANSMITTED, stats->retransmitted}, {TIPC_NLA_STATS_DUPLICATES, stats->duplicates}, {TIPC_NLA_STATS_LINK_CONGS, stats->link_congs}, {TIPC_NLA_STATS_MAX_QUEUE, stats->max_queue_sz}, {TIPC_NLA_STATS_AVG_QUEUE, stats->queue_sz_counts ? (stats->accu_queue_sz / stats->queue_sz_counts) : 0} }; nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!nest) return -EMSGSIZE; for (i = 0; i < ARRAY_SIZE(map); i++) if (nla_put_u32(skb, map[i].key, map[i].val)) goto msg_full; nla_nest_end(skb, nest); return 0; msg_full: nla_nest_cancel(skb, nest); return -EMSGSIZE; } int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_link *bcl) { int err; void *hdr; struct nlattr *attrs; struct nlattr *prop; u32 bc_mode = tipc_bcast_get_mode(net); u32 bc_ratio = tipc_bcast_get_broadcast_ratio(net); if (!bcl) return 0; tipc_bcast_lock(net); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); if (!hdr) { tipc_bcast_unlock(net); return -EMSGSIZE; } attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; /* The broadcast link is always up */ if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP)) goto attr_msg_full; if (nla_put_flag(msg->skb, TIPC_NLA_LINK_BROADCAST)) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->max_win)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode)) goto prop_msg_full; if (bc_mode & BCLINK_MODE_SEL) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST_RATIO, bc_ratio)) goto prop_msg_full; nla_nest_end(msg->skb, prop); err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats); if (err) goto attr_msg_full; tipc_bcast_unlock(net); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: tipc_bcast_unlock(net); genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; if (l->bc_rcvlink) l->bc_rcvlink->tolerance = tol; if (link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } void tipc_link_set_prio(struct tipc_link *l, u32 prio, struct sk_buff_head *xmitq) { l->priority = prio; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, prio, xmitq); } void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit) { l->abort_limit = limit; } /** * tipc_link_dump - dump TIPC link data * @l: tipc link to be dumped * @dqueues: bitmask to decide if any link queue to be dumped? * - TIPC_DUMP_NONE: don't dump link queues * - TIPC_DUMP_TRANSMQ: dump link transmq queue * - TIPC_DUMP_BACKLOGQ: dump link backlog queue * - TIPC_DUMP_DEFERDQ: dump link deferd queue * - TIPC_DUMP_INPUTQ: dump link input queue * - TIPC_DUMP_WAKEUP: dump link wakeup queue * - TIPC_DUMP_ALL: dump all the link queues above * @buf: returned buffer of dump data in format */ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf) { int i = 0; size_t sz = (dqueues) ? LINK_LMAX : LINK_LMIN; struct sk_buff_head *list; struct sk_buff *hskb, *tskb; u32 len; if (!l) { i += scnprintf(buf, sz, "link data: (null)\n"); return i; } i += scnprintf(buf, sz, "link data: %x", l->addr); i += scnprintf(buf + i, sz - i, " %x", l->state); i += scnprintf(buf + i, sz - i, " %u", l->in_session); i += scnprintf(buf + i, sz - i, " %u", l->session); i += scnprintf(buf + i, sz - i, " %u", l->peer_session); i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt); i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt); i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt_state); i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt_state); i += scnprintf(buf + i, sz - i, " %x", l->peer_caps); i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt); i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt); i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", l->acked); list = &l->transmq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = &l->deferdq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = &l->backlogq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = l->inputq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u\n", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); if (dqueues & TIPC_DUMP_TRANSMQ) { i += scnprintf(buf + i, sz - i, "transmq: "); i += tipc_list_dump(&l->transmq, false, buf + i); } if (dqueues & TIPC_DUMP_BACKLOGQ) { i += scnprintf(buf + i, sz - i, "backlogq: <%u %u %u %u %u>, ", l->backlog[TIPC_LOW_IMPORTANCE].len, l->backlog[TIPC_MEDIUM_IMPORTANCE].len, l->backlog[TIPC_HIGH_IMPORTANCE].len, l->backlog[TIPC_CRITICAL_IMPORTANCE].len, l->backlog[TIPC_SYSTEM_IMPORTANCE].len); i += tipc_list_dump(&l->backlogq, false, buf + i); } if (dqueues & TIPC_DUMP_DEFERDQ) { i += scnprintf(buf + i, sz - i, "deferdq: "); i += tipc_list_dump(&l->deferdq, false, buf + i); } if (dqueues & TIPC_DUMP_INPUTQ) { i += scnprintf(buf + i, sz - i, "inputq: "); i += tipc_list_dump(l->inputq, false, buf + i); } if (dqueues & TIPC_DUMP_WAKEUP) { i += scnprintf(buf + i, sz - i, "wakeup: "); i += tipc_list_dump(&l->wakeupq, false, buf + i); } return i; } |
| 62 55 54 62 62 62 62 55 55 55 55 62 55 55 55 54 | 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 | #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/pagemap.h> #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/swap.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #ifndef CONFIG_MMU_GATHER_NO_GATHER static bool tlb_next_batch(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; batch = tlb->active; if (batch->next) { tlb->active = batch->next; return true; } if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) return false; batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); if (!batch) return false; tlb->batch_count++; batch->next = NULL; batch->nr = 0; batch->max = MAX_GATHER_BATCH; tlb->active->next = batch; tlb->active = batch; return true; } static void tlb_batch_pages_flush(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { free_pages_and_swap_cache(batch->pages, batch->nr); batch->nr = 0; } tlb->active = &tlb->local; } static void tlb_batch_list_free(struct mmu_gather *tlb) { struct mmu_gather_batch *batch, *next; for (batch = tlb->local.next; batch; batch = next) { next = batch->next; free_pages((unsigned long)batch, 0); } tlb->local.next = NULL; } bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { struct mmu_gather_batch *batch; VM_BUG_ON(!tlb->end); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE VM_WARN_ON(tlb->page_size != page_size); #endif batch = tlb->active; /* * Add the page and check if we are full. If so * force a flush. */ batch->pages[batch->nr++] = page; if (batch->nr == batch->max) { if (!tlb_next_batch(tlb)) return true; batch = tlb->active; } VM_BUG_ON_PAGE(batch->nr > batch->max, page); return false; } #endif /* MMU_GATHER_NO_GATHER */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE static void __tlb_remove_table_free(struct mmu_table_batch *batch) { int i; for (i = 0; i < batch->nr; i++) __tlb_remove_table(batch->tables[i]); free_page((unsigned long)batch); } #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * Semi RCU freeing of the page directories. * * This is needed by some architectures to implement software pagetable walkers. * * gup_fast() and other software pagetable walkers do a lockless page-table * walk and therefore needs some synchronization with the freeing of the page * directories. The chosen means to accomplish that is by disabling IRQs over * the walk. * * Architectures that use IPIs to flush TLBs will then automagically DTRT, * since we unlink the page, flush TLBs, free the page. Since the disabling of * IRQs delays the completion of the TLB flush we can never observe an already * freed page. * * Architectures that do not have this (PPC) need to delay the freeing by some * other means, this is that means. * * What we do is batch the freed directory pages (tables) and RCU free them. * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling * holds off grace periods. * * However, in order to batch these pages we need to allocate storage, this * allocation is deep inside the MM code and can thus easily fail on memory * pressure. To guarantee progress we fall back to single table freeing, see * the implementation of tlb_remove_table_one(). * */ static void tlb_remove_table_smp_sync(void *arg) { /* Simply deliver the interrupt */ } void tlb_remove_table_sync_one(void) { /* * This isn't an RCU grace period and hence the page-tables cannot be * assumed to be actually RCU-freed. * * It is however sufficient for software page-table walkers that rely on * IRQ disabling. */ smp_call_function(tlb_remove_table_smp_sync, NULL, 1); } static void tlb_remove_table_rcu(struct rcu_head *head) { __tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu)); } static void tlb_remove_table_free(struct mmu_table_batch *batch) { call_rcu(&batch->rcu, tlb_remove_table_rcu); } #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ static void tlb_remove_table_free(struct mmu_table_batch *batch) { __tlb_remove_table_free(batch); } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ /* * If we want tlb_remove_table() to imply TLB invalidates. */ static inline void tlb_table_invalidate(struct mmu_gather *tlb) { if (tlb_needs_table_invalidate()) { /* * Invalidate page-table caches used by hardware walkers. Then * we still need to RCU-sched wait while freeing the pages * because software walkers can still be in-flight. */ tlb_flush_mmu_tlbonly(tlb); } } static void tlb_remove_table_one(void *table) { tlb_remove_table_sync_one(); __tlb_remove_table(table); } static void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; if (*batch) { tlb_table_invalidate(tlb); tlb_remove_table_free(*batch); *batch = NULL; } } void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; if (*batch == NULL) { *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { tlb_table_invalidate(tlb); tlb_remove_table_one(table); return; } (*batch)->nr = 0; } (*batch)->tables[(*batch)->nr++] = table; if ((*batch)->nr == MAX_TABLE_BATCH) tlb_table_flush(tlb); } static inline void tlb_table_init(struct mmu_gather *tlb) { tlb->batch = NULL; } #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_table_flush(struct mmu_gather *tlb) { } static inline void tlb_table_init(struct mmu_gather *tlb) { } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ static void tlb_flush_mmu_free(struct mmu_gather *tlb) { tlb_table_flush(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_pages_flush(tlb); #endif } void tlb_flush_mmu(struct mmu_gather *tlb) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_mmu_free(tlb); } static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { tlb->mm = mm; tlb->fullmm = fullmm; #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb->need_flush_all = 0; tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); tlb->active = &tlb->local; tlb->batch_count = 0; #endif tlb_table_init(tlb); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE tlb->page_size = 0; #endif __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } /** * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, false); } /** * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * In this case, @mm is without users and we're going to destroy the * full address space (exit/execve). * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, true); } /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish * * Called at the end of the shootdown operation to free up any resources that * were required. */ void tlb_finish_mmu(struct mmu_gather *tlb) { /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB * flush by batching, one thread may end up seeing inconsistent PTEs * and result in having stale TLB entries. So flush TLB forcefully * if we detect parallel PTE batching threads. * * However, some syscalls, e.g. munmap(), may free page tables, this * needs force flush everything in the given range. Otherwise this * may result in having stale TLB entries for some architectures, * e.g. aarch64, that could specify flush what level TLB. */ if (mm_tlb_flush_nested(tlb->mm)) { /* * The aarch64 yields better performance with fullmm by * avoiding multiple CPUs spamming TLBI messages at the * same time. * * On x86 non-fullmm doesn't yield significant difference * against fullmm. */ tlb->fullmm = 1; __tlb_reset_range(tlb); tlb->freed_tables = 1; } tlb_flush_mmu(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_list_free(tlb); #endif dec_tlb_flush_pending(tlb->mm); } |
| 34 34 22 21 1 22 22 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Socket Closing - normal and abnormal * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/workqueue.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_tx.h" #include "smc_cdc.h" #include "smc_close.h" /* release the clcsock that is assigned to the smc_sock */ void smc_clcsock_release(struct smc_sock *smc) { struct socket *tcp; if (smc->listen_smc && current_work() != &smc->smc_listen_work) cancel_work_sync(&smc->smc_listen_work); mutex_lock(&smc->clcsock_release_lock); if (smc->clcsock) { tcp = smc->clcsock; smc->clcsock = NULL; sock_release(tcp); } mutex_unlock(&smc->clcsock_release_lock); } static void smc_close_cleanup_listen(struct sock *parent) { struct sock *sk; /* Close non-accepted connections */ while ((sk = smc_accept_dequeue(parent, NULL))) smc_close_non_accepted(sk); } /* wait for sndbuf data being transmitted */ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = &smc->sk; if (!timeout) return; if (!smc_tx_prepared_sends(&smc->conn)) return; smc->wait_close_tx_prepared = 1; add_wait_queue(sk_sleep(sk), &wait); while (!signal_pending(current) && timeout) { int rc; rc = sk_wait_event(sk, &timeout, !smc_tx_prepared_sends(&smc->conn) || READ_ONCE(sk->sk_err) == ECONNABORTED || READ_ONCE(sk->sk_err) == ECONNRESET || smc->conn.killed, &wait); if (rc) break; } remove_wait_queue(sk_sleep(sk), &wait); smc->wait_close_tx_prepared = 0; } void smc_close_wake_tx_prepared(struct smc_sock *smc) { if (smc->wait_close_tx_prepared) /* wake up socket closing */ smc->sk.sk_state_change(&smc->sk); } static int smc_close_wr(struct smc_connection *conn) { conn->local_tx_ctrl.conn_state_flags.peer_done_writing = 1; return smc_cdc_get_slot_and_msg_send(conn); } static int smc_close_final(struct smc_connection *conn) { if (atomic_read(&conn->bytes_to_rcv)) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; else conn->local_tx_ctrl.conn_state_flags.peer_conn_closed = 1; if (conn->killed) return -EPIPE; return smc_cdc_get_slot_and_msg_send(conn); } int smc_close_abort(struct smc_connection *conn) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; return smc_cdc_get_slot_and_msg_send(conn); } static void smc_close_cancel_work(struct smc_sock *smc) { struct sock *sk = &smc->sk; release_sock(sk); if (cancel_work_sync(&smc->conn.close_work)) sock_put(sk); cancel_delayed_work_sync(&smc->conn.tx_work); lock_sock(sk); } /* terminate smc socket abnormally - active abort * link group is terminated, i.e. RDMA communication no longer possible */ void smc_close_active_abort(struct smc_sock *smc) { struct sock *sk = &smc->sk; bool release_clcsock = false; if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) { sk->sk_err = ECONNABORTED; if (smc->clcsock && smc->clcsock->sk) tcp_abort(smc->clcsock->sk, ECONNABORTED); } switch (sk->sk_state) { case SMC_ACTIVE: case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; sock_put(sk); /* (postponed) passive closing */ break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; sock_put(sk); /* passive closing */ break; case SMC_PROCESSABORT: case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; break; case SMC_INIT: case SMC_PEERABORTWAIT: case SMC_CLOSED: break; } smc_sock_set_flag(sk, SOCK_DEAD); sk->sk_state_change(sk); if (release_clcsock) { release_sock(sk); smc_clcsock_release(smc); lock_sock(sk); } } static inline bool smc_close_sent_any_close(struct smc_connection *conn) { return conn->local_tx_ctrl.conn_state_flags.peer_conn_abort || conn->local_tx_ctrl.conn_state_flags.peer_conn_closed; } int smc_close_active(struct smc_sock *smc) { struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int old_state; long timeout; int rc = 0; int rc1 = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; old_state = sk->sk_state; again: switch (sk->sk_state) { case SMC_INIT: sk->sk_state = SMC_CLOSED; break; case SMC_LISTEN: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; smc->clcsock->sk->sk_user_data = NULL; rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); release_sock(sk); flush_work(&smc->tcp_listen_work); lock_sock(sk); break; case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state == SMC_ACTIVE) { /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; /* actively shutdown clcsock before peer close it, * prevent peer from entering TIME_WAIT state. */ if (smc->clcsock && smc->clcsock->sk) { rc1 = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); rc = rc ? rc : rc1; } } else { /* peer event has changed the state */ goto again; } break; case SMC_APPFINCLOSEWAIT: /* socket already shutdown wr or both (active close) */ if (txflags->peer_done_writing && !smc_close_sent_any_close(conn)) { /* just shutdown wr done, send close request */ rc = smc_close_final(conn); } sk->sk_state = SMC_CLOSED; break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_APPCLOSEWAIT1 && sk->sk_state != SMC_APPCLOSEWAIT2) goto again; /* confirm close from peer */ rc = smc_close_final(conn); if (smc_cdc_rxed_any_close(conn)) { /* peer has closed the socket already */ sk->sk_state = SMC_CLOSED; sock_put(sk); /* postponed passive closing */ } else { /* peer has just issued a shutdown write */ sk->sk_state = SMC_PEERFINCLOSEWAIT; } break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: if (txflags->peer_done_writing && !smc_close_sent_any_close(conn)) { /* just shutdown wr done, send close request */ rc = smc_close_final(conn); } /* peer sending PeerConnectionClosed will cause transition */ break; case SMC_PEERFINCLOSEWAIT: /* peer sending PeerConnectionClosed will cause transition */ break; case SMC_PROCESSABORT: rc = smc_close_abort(conn); sk->sk_state = SMC_CLOSED; break; case SMC_PEERABORTWAIT: sk->sk_state = SMC_CLOSED; break; case SMC_CLOSED: /* nothing to do, add tracing in future patch */ break; } if (old_state != sk->sk_state) sk->sk_state_change(sk); return rc; } static void smc_close_passive_abort_received(struct smc_sock *smc) { struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; struct sock *sk = &smc->sk; switch (sk->sk_state) { case SMC_INIT: case SMC_ACTIVE: case SMC_APPCLOSEWAIT1: sk->sk_state = SMC_PROCESSABORT; sock_put(sk); /* passive closing */ break; case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PROCESSABORT; break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: if (txflags->peer_done_writing && !smc_close_sent_any_close(&smc->conn)) /* just shutdown, but not yet closed locally */ sk->sk_state = SMC_PROCESSABORT; else sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ break; case SMC_APPCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ break; case SMC_PEERABORTWAIT: sk->sk_state = SMC_CLOSED; break; case SMC_PROCESSABORT: /* nothing to do, add tracing in future patch */ break; } } /* Either some kind of closing has been received: peer_conn_closed, * peer_conn_abort, or peer_done_writing * or the link group of the connection terminates abnormally. */ static void smc_close_passive_work(struct work_struct *work) { struct smc_connection *conn = container_of(work, struct smc_connection, close_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_cdc_conn_state_flags *rxflags; bool release_clcsock = false; struct sock *sk = &smc->sk; int old_state; lock_sock(sk); old_state = sk->sk_state; rxflags = &conn->local_rx_ctrl.conn_state_flags; if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); release_sock(&smc->sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(&smc->sk); goto wakeup; } switch (sk->sk_state) { case SMC_INIT: sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; /* postpone sock_put() for passive closing to cover * received SEND_SHUTDOWN as well */ break; case SMC_PEERCLOSEWAIT1: if (rxflags->peer_done_writing) sk->sk_state = SMC_PEERCLOSEWAIT2; fallthrough; /* to check for closing */ case SMC_PEERCLOSEWAIT2: if (!smc_cdc_rxed_any_close(conn)) break; if (sock_flag(sk, SOCK_DEAD) && smc_close_sent_any_close(conn)) { /* smc_release has already been called locally */ sk->sk_state = SMC_CLOSED; } else { /* just shutdown, but not yet closed locally */ sk->sk_state = SMC_APPFINCLOSEWAIT; } sock_put(sk); /* passive closing */ break; case SMC_PEERFINCLOSEWAIT: if (smc_cdc_rxed_any_close(conn)) { sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ } break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: /* postpone sock_put() for passive closing to cover * received SEND_SHUTDOWN as well */ break; case SMC_APPFINCLOSEWAIT: case SMC_PEERABORTWAIT: case SMC_PROCESSABORT: case SMC_CLOSED: /* nothing to do, add tracing in future patch */ break; } wakeup: sk->sk_data_ready(sk); /* wakeup blocked rcvbuf consumers */ sk->sk_write_space(sk); /* wakeup blocked sndbuf producers */ if (old_state != sk->sk_state) { sk->sk_state_change(sk); if ((sk->sk_state == SMC_CLOSED) && (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); if (smc->clcsock) release_clcsock = true; } } release_sock(sk); if (release_clcsock) smc_clcsock_release(smc); sock_put(sk); /* sock_hold done by schedulers of close_work */ } int smc_close_shutdown_write(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int old_state; long timeout; int rc = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; old_state = sk->sk_state; again: switch (sk->sk_state) { case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_ACTIVE) goto again; /* send close wr request */ rc = smc_close_wr(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; break; case SMC_APPCLOSEWAIT1: /* passive close */ if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_APPCLOSEWAIT1) goto again; /* confirm close from peer */ rc = smc_close_wr(conn); sk->sk_state = SMC_APPCLOSEWAIT2; break; case SMC_APPCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_APPFINCLOSEWAIT: case SMC_PROCESSABORT: case SMC_PEERABORTWAIT: /* nothing to do, add tracing in future patch */ break; } if (old_state != sk->sk_state) sk->sk_state_change(sk); return rc; } /* Initialize close properties on connection establishment. */ void smc_close_init(struct smc_sock *smc) { INIT_WORK(&smc->conn.close_work, smc_close_passive_work); } |
| 62 1 8 5 1 3 61 60 9 50 10 60 60 60 60 60 50 10 60 61 62 62 61 62 8 60 60 60 62 62 8 8 8 62 62 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC remote transport endpoint record management * * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/udp.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/slab.h> #include <linux/hashtable.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> #include <net/route.h> #include <net/ip6_route.h> #include "ar-internal.h" /* * Hash a peer key. */ static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local, const struct sockaddr_rxrpc *srx) { const u16 *p; unsigned int i, size; unsigned long hash_key; _enter(""); hash_key = (unsigned long)local / __alignof__(*local); hash_key += srx->transport_type; hash_key += srx->transport_len; hash_key += srx->transport.family; switch (srx->transport.family) { case AF_INET: hash_key += (u16 __force)srx->transport.sin.sin_port; size = sizeof(srx->transport.sin.sin_addr); p = (u16 *)&srx->transport.sin.sin_addr; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: hash_key += (u16 __force)srx->transport.sin.sin_port; size = sizeof(srx->transport.sin6.sin6_addr); p = (u16 *)&srx->transport.sin6.sin6_addr; break; #endif default: WARN(1, "AF_RXRPC: Unsupported transport address family\n"); return 0; } /* Step through the peer address in 16-bit portions for speed */ for (i = 0; i < size; i += sizeof(*p), p++) hash_key += *p; _leave(" 0x%lx", hash_key); return hash_key; } /* * Compare a peer to a key. Return -ve, 0 or +ve to indicate less than, same * or greater than. * * Unfortunately, the primitives in linux/hashtable.h don't allow for sorted * buckets and mid-bucket insertion, so we don't make full use of this * information at this point. */ static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer, struct rxrpc_local *local, const struct sockaddr_rxrpc *srx, unsigned long hash_key) { long diff; diff = ((peer->hash_key - hash_key) ?: ((unsigned long)peer->local - (unsigned long)local) ?: (peer->srx.transport_type - srx->transport_type) ?: (peer->srx.transport_len - srx->transport_len) ?: (peer->srx.transport.family - srx->transport.family)); if (diff != 0) return diff; switch (srx->transport.family) { case AF_INET: return ((u16 __force)peer->srx.transport.sin.sin_port - (u16 __force)srx->transport.sin.sin_port) ?: memcmp(&peer->srx.transport.sin.sin_addr, &srx->transport.sin.sin_addr, sizeof(struct in_addr)); #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: return ((u16 __force)peer->srx.transport.sin6.sin6_port - (u16 __force)srx->transport.sin6.sin6_port) ?: memcmp(&peer->srx.transport.sin6.sin6_addr, &srx->transport.sin6.sin6_addr, sizeof(struct in6_addr)); #endif default: BUG(); } } /* * Look up a remote transport endpoint for the specified address using RCU. */ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( struct rxrpc_local *local, const struct sockaddr_rxrpc *srx, unsigned long hash_key) { struct rxrpc_peer *peer; struct rxrpc_net *rxnet = local->rxnet; hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 && refcount_read(&peer->ref) > 0) return peer; } return NULL; } /* * Look up a remote transport endpoint for the specified address using RCU. */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, const struct sockaddr_rxrpc *srx) { struct rxrpc_peer *peer; unsigned long hash_key = rxrpc_peer_hash_key(local, srx); peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer) { _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); _leave(" = %p {u=%d}", peer, refcount_read(&peer->ref)); } return peer; } /* * assess the MTU size for the network interface through which this peer is * reached */ static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, struct rxrpc_peer *peer) { struct net *net = sock_net(&rx->sk); struct dst_entry *dst; struct rtable *rt; struct flowi fl; struct flowi4 *fl4 = &fl.u.ip4; #ifdef CONFIG_AF_RXRPC_IPV6 struct flowi6 *fl6 = &fl.u.ip6; #endif peer->if_mtu = 1500; memset(&fl, 0, sizeof(fl)); switch (peer->srx.transport.family) { case AF_INET: rt = ip_route_output_ports( net, fl4, NULL, peer->srx.transport.sin.sin_addr.s_addr, 0, htons(7000), htons(7001), IPPROTO_UDP, 0, 0); if (IS_ERR(rt)) { _leave(" [route err %ld]", PTR_ERR(rt)); return; } dst = &rt->dst; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: fl6->flowi6_iif = LOOPBACK_IFINDEX; fl6->flowi6_scope = RT_SCOPE_UNIVERSE; fl6->flowi6_proto = IPPROTO_UDP; memcpy(&fl6->daddr, &peer->srx.transport.sin6.sin6_addr, sizeof(struct in6_addr)); fl6->fl6_dport = htons(7001); fl6->fl6_sport = htons(7000); dst = ip6_route_output(net, NULL, fl6); if (dst->error) { _leave(" [route err %d]", dst->error); return; } break; #endif default: BUG(); } peer->if_mtu = dst_mtu(dst); dst_release(dst); _leave(" [if_mtu %u]", peer->if_mtu); } /* * Allocate a peer. */ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) { const void *here = __builtin_return_address(0); struct rxrpc_peer *peer; _enter(""); peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { refcount_set(&peer->ref, 1); peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); spin_lock_init(&peer->rtt_input_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); rxrpc_peer_init_rtt(peer); if (RXRPC_TX_SMSS > 2190) peer->cong_cwnd = 2; else if (RXRPC_TX_SMSS > 1095) peer->cong_cwnd = 3; else peer->cong_cwnd = 4; trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); } _leave(" = %p", peer); return peer; } /* * Initialise peer record. */ static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, unsigned long hash_key) { peer->hash_key = hash_key; rxrpc_assess_MTU_size(rx, peer); peer->mtu = peer->if_mtu; peer->rtt_last_req = ktime_get_real(); switch (peer->srx.transport.family) { case AF_INET: peer->hdrsize = sizeof(struct iphdr); break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: peer->hdrsize = sizeof(struct ipv6hdr); break; #endif default: BUG(); } switch (peer->srx.transport_type) { case SOCK_DGRAM: peer->hdrsize += sizeof(struct udphdr); break; default: BUG(); } peer->hdrsize += sizeof(struct rxrpc_wire_header); peer->maxdata = peer->mtu - peer->hdrsize; } /* * Set up a new peer. */ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, struct sockaddr_rxrpc *srx, unsigned long hash_key, gfp_t gfp) { struct rxrpc_peer *peer; _enter(""); peer = rxrpc_alloc_peer(local, gfp); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); rxrpc_init_peer(rx, peer, hash_key); } _leave(" = %p", peer); return peer; } static void rxrpc_free_peer(struct rxrpc_peer *peer) { rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } /* * Set up a new incoming peer. There shouldn't be any other matching peers * since we've already done a search in the list from the non-reentrant context * (the data_ready handler) that is the only place we can add new peers. */ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); spin_unlock(&rxnet->peer_hash_lock); } /* * obtain a remote transport endpoint for the specified address */ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key = rxrpc_peer_hash_key(local, srx); _enter("{%pISp}", &srx->transport); /* search the peer list first */ rcu_read_lock(); peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; rcu_read_unlock(); if (!peer) { /* The peer is not yet present in hash - create a candidate * for a new record and then redo the search. */ candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp); if (!candidate) { _leave(" = NULL [nomem]"); return NULL; } spin_lock_bh(&rxnet->peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; if (!peer) { hash_add_rcu(rxnet->peer_hash, &candidate->hash_link, hash_key); list_add_tail(&candidate->keepalive_link, &rxnet->peer_keepalive_new); } spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) rxrpc_free_peer(candidate); else peer = candidate; } _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); _leave(" = %p {u=%d}", peer, refcount_read(&peer->ref)); return peer; } /* * Get a ref on a peer record. */ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); int r; __refcount_inc(&peer->ref, &r); trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); return peer; } /* * Get a ref on a peer record unless its usage has already reached 0. */ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); int r; if (peer) { if (__refcount_inc_not_zero(&peer->ref, &r)) trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); else peer = NULL; } return peer; } /* * Discard a peer record. */ static void __rxrpc_put_peer(struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = peer->local->rxnet; ASSERT(hlist_empty(&peer->error_targets)); spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); rxrpc_free_peer(peer); } /* * Drop a ref on a peer record. */ void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); unsigned int debug_id; bool dead; int r; if (peer) { debug_id = peer->debug_id; dead = __refcount_dec_and_test(&peer->ref, &r); trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); if (dead) __rxrpc_put_peer(peer); } } /* * Drop a ref on a peer record where the caller already holds the * peer_hash_lock. */ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); unsigned int debug_id = peer->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&peer->ref, &r); trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); if (dead) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); rxrpc_free_peer(peer); } } /* * Make sure all peer records have been discarded. */ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) { struct rxrpc_peer *peer; int i; for (i = 0; i < HASH_SIZE(rxnet->peer_hash); i++) { if (hlist_empty(&rxnet->peer_hash[i])) continue; hlist_for_each_entry(peer, &rxnet->peer_hash[i], hash_link) { pr_err("Leaked peer %u {%u} %pISp\n", peer->debug_id, refcount_read(&peer->ref), &peer->srx.transport); } } } /** * rxrpc_kernel_get_peer - Get the peer address of a call * @sock: The socket on which the call is in progress. * @call: The call to query * @_srx: Where to place the result * * Get the address of the remote peer in a call. */ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, struct sockaddr_rxrpc *_srx) { *_srx = call->peer->srx; } EXPORT_SYMBOL(rxrpc_kernel_get_peer); /** * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query * @_srtt: Where to store the SRTT value. * * Get the call's peer smoothed RTT in uS. */ bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, u32 *_srtt) { struct rxrpc_peer *peer = call->peer; if (peer->rtt_count == 0) { *_srtt = 1000000; /* 1S */ return false; } *_srtt = call->peer->srtt_us >> 3; return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); |
| 40 39 40 45 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip6_flowlabel.c IPv6 flowlabel manager. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/pid_namespace.h> #include <linux/jump_label_ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/rawv6.h> #include <net/transp_v6.h> #include <linux/uaccess.h> #define FL_MIN_LINGER 6 /* Minimal linger. It is set to 6sec specified in old IPv6 RFC. Well, it was reasonable value. */ #define FL_MAX_LINGER 150 /* Maximal linger timeout */ /* FL hash table */ #define FL_MAX_PER_SOCK 32 #define FL_MAX_SIZE 4096 #define FL_HASH_MASK 255 #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) static atomic_t fl_size = ATOMIC_INIT(0); static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(struct timer_list *unused); static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc); /* FL hash table lock: it protects only of GC */ static DEFINE_SPINLOCK(ip6_fl_lock); /* Big socket sock */ static DEFINE_SPINLOCK(ip6_sk_fl_lock); DEFINE_STATIC_KEY_DEFERRED_FALSE(ipv6_flowlabel_exclusive, HZ); EXPORT_SYMBOL(ipv6_flowlabel_exclusive); #define for_each_fl_rcu(hash, fl) \ for (fl = rcu_dereference_bh(fl_ht[(hash)]); \ fl != NULL; \ fl = rcu_dereference_bh(fl->next)) #define for_each_fl_continue_rcu(fl) \ for (fl = rcu_dereference_bh(fl->next); \ fl != NULL; \ fl = rcu_dereference_bh(fl->next)) #define for_each_sk_fl_rcu(np, sfl) \ for (sfl = rcu_dereference_bh(np->ipv6_fl_list); \ sfl != NULL; \ sfl = rcu_dereference_bh(sfl->next)) static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; for_each_fl_rcu(FL_HASH(label), fl) { if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; } static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; rcu_read_lock_bh(); fl = __fl_lookup(net, label); if (fl && !atomic_inc_not_zero(&fl->users)) fl = NULL; rcu_read_unlock_bh(); return fl; } static bool fl_shared_exclusive(struct ip6_flowlabel *fl) { return fl->share == IPV6_FL_S_EXCL || fl->share == IPV6_FL_S_PROCESS || fl->share == IPV6_FL_S_USER; } static void fl_free_rcu(struct rcu_head *head) { struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu); if (fl->share == IPV6_FL_S_PROCESS) put_pid(fl->owner.pid); kfree(fl->opt); kfree(fl); } static void fl_free(struct ip6_flowlabel *fl) { if (!fl) return; if (fl_shared_exclusive(fl) || fl->opt) static_branch_slow_dec_deferred(&ipv6_flowlabel_exclusive); call_rcu(&fl->rcu, fl_free_rcu); } static void fl_release(struct ip6_flowlabel *fl) { spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (atomic_dec_and_test(&fl->users)) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) fl->expires = ttd; ttd = fl->expires; if (fl->opt && fl->share == IPV6_FL_S_EXCL) { struct ipv6_txoptions *opt = fl->opt; fl->opt = NULL; kfree(opt); } if (!timer_pending(&ip6_fl_gc_timer) || time_after(ip6_fl_gc_timer.expires, ttd)) mod_timer(&ip6_fl_gc_timer, ttd); } spin_unlock_bh(&ip6_fl_lock); } static void ip6_fl_gc(struct timer_list *unused) { int i; unsigned long now = jiffies; unsigned long sched = 0; spin_lock(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl; struct ip6_flowlabel __rcu **flp; flp = &fl_ht[i]; while ((fl = rcu_dereference_protected(*flp, lockdep_is_held(&ip6_fl_lock))) != NULL) { if (atomic_read(&fl->users) == 0) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) fl->expires = ttd; ttd = fl->expires; if (time_after_eq(now, ttd)) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); continue; } if (!sched || time_before(ttd, sched)) sched = ttd; } flp = &fl->next; } } if (!sched && atomic_read(&fl_size)) sched = now + FL_MAX_LINGER; if (sched) { mod_timer(&ip6_fl_gc_timer, sched); } spin_unlock(&ip6_fl_lock); } static void __net_exit ip6_fl_purge(struct net *net) { int i; spin_lock_bh(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl; struct ip6_flowlabel __rcu **flp; flp = &fl_ht[i]; while ((fl = rcu_dereference_protected(*flp, lockdep_is_held(&ip6_fl_lock))) != NULL) { if (net_eq(fl->fl_net, net) && atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); continue; } flp = &fl->next; } } spin_unlock_bh(&ip6_fl_lock); } static struct ip6_flowlabel *fl_intern(struct net *net, struct ip6_flowlabel *fl, __be32 label) { struct ip6_flowlabel *lfl; fl->label = label & IPV6_FLOWLABEL_MASK; spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (!lfl) break; } } } else { /* * we dropper the ip6_fl_lock, so this entry could reappear * and we need to recheck with it. * * OTOH no need to search the active socket first, like it is * done in ipv6_flowlabel_opt - sock is locked, so new entry * with the same label can only appear on another sock */ lfl = __fl_lookup(net, fl->label); if (lfl) { atomic_inc(&lfl->users); spin_unlock_bh(&ip6_fl_lock); return lfl; } } fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); atomic_inc(&fl_size); spin_unlock_bh(&ip6_fl_lock); return NULL; } /* Socket flowlabel lists */ struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label) { struct ipv6_fl_socklist *sfl; struct ipv6_pinfo *np = inet6_sk(sk); label &= IPV6_FLOWLABEL_MASK; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label && atomic_inc_not_zero(&fl->users)) { fl->lastuse = jiffies; rcu_read_unlock_bh(); return fl; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(__fl6_sock_lookup); void fl6_free_socklist(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; if (!rcu_access_pointer(np->ipv6_fl_list)) return; spin_lock_bh(&ip6_sk_fl_lock); while ((sfl = rcu_dereference_protected(np->ipv6_fl_list, lockdep_is_held(&ip6_sk_fl_lock))) != NULL) { np->ipv6_fl_list = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); spin_lock_bh(&ip6_sk_fl_lock); } spin_unlock_bh(&ip6_sk_fl_lock); } /* Service routines */ /* It is the only difficult place. flowlabel enforces equal headers before and including routing header, however user may supply options following rthdr. */ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt) { struct ipv6_txoptions *fl_opt = fl->opt; if (!fopt || fopt->opt_flen == 0) return fl_opt; if (fl_opt) { opt_space->hopopt = fl_opt->hopopt; opt_space->dst0opt = fl_opt->dst0opt; opt_space->srcrt = fl_opt->srcrt; opt_space->opt_nflen = fl_opt->opt_nflen; } else { if (fopt->opt_nflen == 0) return fopt; opt_space->hopopt = NULL; opt_space->dst0opt = NULL; opt_space->srcrt = NULL; opt_space->opt_nflen = 0; } opt_space->dst1opt = fopt->dst1opt; opt_space->opt_flen = fopt->opt_flen; opt_space->tot_len = fopt->tot_len; return opt_space; } EXPORT_SYMBOL_GPL(fl6_merge_options); static unsigned long check_linger(unsigned long ttl) { if (ttl < FL_MIN_LINGER) return FL_MIN_LINGER*HZ; if (ttl > FL_MAX_LINGER && !capable(CAP_NET_ADMIN)) return 0; return ttl*HZ; } static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned long expires) { linger = check_linger(linger); if (!linger) return -EPERM; expires = check_linger(expires); if (!expires) return -EPERM; spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (time_before(fl->linger, linger)) fl->linger = linger; if (time_before(expires, fl->linger)) expires = fl->linger; if (time_before(fl->expires, fl->lastuse + expires)) fl->expires = fl->lastuse + expires; spin_unlock_bh(&ip6_fl_lock); return 0; } static struct ip6_flowlabel * fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, sockptr_t optval, int optlen, int *err_p) { struct ip6_flowlabel *fl = NULL; int olen; int addr_type; int err; olen = optlen - CMSG_ALIGN(sizeof(*freq)); err = -EINVAL; if (olen > 64 * 1024) goto done; err = -ENOMEM; fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (!fl) goto done; if (olen > 0) { struct msghdr msg; struct flowi6 flowi6; struct ipcm6_cookie ipc6; err = -ENOMEM; fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL); if (!fl->opt) goto done; memset(fl->opt, 0, sizeof(*fl->opt)); fl->opt->tot_len = sizeof(*fl->opt) + olen; err = -EFAULT; if (copy_from_sockptr_offset(fl->opt + 1, optval, CMSG_ALIGN(sizeof(*freq)), olen)) goto done; msg.msg_controllen = olen; msg.msg_control = (void *)(fl->opt+1); memset(&flowi6, 0, sizeof(flowi6)); ipc6.opt = fl->opt; err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6); if (err) goto done; err = -EINVAL; if (fl->opt->opt_flen) goto done; if (fl->opt->opt_nflen == 0) { kfree(fl->opt); fl->opt = NULL; } } fl->fl_net = net; fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) goto done; fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); if ((addr_type & IPV6_ADDR_MAPPED) || addr_type == IPV6_ADDR_ANY) { err = -EINVAL; goto done; } fl->dst = freq->flr_dst; atomic_set(&fl->users, 1); switch (fl->share) { case IPV6_FL_S_EXCL: case IPV6_FL_S_ANY: break; case IPV6_FL_S_PROCESS: fl->owner.pid = get_task_pid(current, PIDTYPE_PID); break; case IPV6_FL_S_USER: fl->owner.uid = current_euid(); break; default: err = -EINVAL; goto done; } if (fl_shared_exclusive(fl) || fl->opt) { WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1); static_branch_deferred_inc(&ipv6_flowlabel_exclusive); } return fl; done: if (fl) { kfree(fl->opt); kfree(fl); } *err_p = err; return NULL; } static int mem_check(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; int room = FL_MAX_SIZE - atomic_read(&fl_size); int count = 0; if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && !capable(CAP_NET_ADMIN))) return -ENOBUFS; return 0; } static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, struct ip6_flowlabel *fl) { spin_lock_bh(&ip6_sk_fl_lock); sfl->fl = fl; sfl->next = np->ipv6_fl_list; rcu_assign_pointer(np->ipv6_fl_list, sfl); spin_unlock_bh(&ip6_sk_fl_lock); } int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; if (flags & IPV6_FL_F_REMOTE) { freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK; return 0; } if (np->repflow) { freq->flr_label = np->flow_label; return 0; } rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) { spin_lock_bh(&ip6_fl_lock); freq->flr_label = sfl->fl->label; freq->flr_dst = sfl->fl->dst; freq->flr_share = sfl->fl->share; freq->flr_expires = (sfl->fl->expires - jiffies) / HZ; freq->flr_linger = sfl->fl->linger / HZ; spin_unlock_bh(&ip6_fl_lock); rcu_read_unlock_bh(); return 0; } } rcu_read_unlock_bh(); return -ENOENT; } #define socklist_dereference(__sflp) \ rcu_dereference_protected(__sflp, lockdep_is_held(&ip6_sk_fl_lock)) static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist __rcu **sflp; struct ipv6_fl_socklist *sfl; if (freq->flr_flags & IPV6_FL_F_REFLECT) { if (sk->sk_protocol != IPPROTO_TCP) return -ENOPROTOOPT; if (!np->repflow) return -ESRCH; np->flow_label = 0; np->repflow = 0; return 0; } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; (sfl = socklist_dereference(*sflp)) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq->flr_label) goto found; } spin_unlock_bh(&ip6_sk_fl_lock); return -ESRCH; found: if (freq->flr_label == (np->flow_label & IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); return 0; } static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6_fl_socklist *sfl; int err; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq->flr_label) { err = fl6_renew(sfl->fl, freq->flr_linger, freq->flr_expires); rcu_read_unlock_bh(); return err; } } rcu_read_unlock_bh(); if (freq->flr_share == IPV6_FL_S_NONE && ns_capable(net->user_ns, CAP_NET_ADMIN)) { struct ip6_flowlabel *fl = fl_lookup(net, freq->flr_label); if (fl) { err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); fl_release(fl); return err; } } return -ESRCH; } static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, sockptr_t optval, int optlen) { struct ipv6_fl_socklist *sfl, *sfl1 = NULL; struct ip6_flowlabel *fl, *fl1 = NULL; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; if (freq->flr_flags & IPV6_FL_F_REFLECT) { if (net->ipv6.sysctl.flowlabel_consistency) { net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); return -EPERM; } if (sk->sk_protocol != IPPROTO_TCP) return -ENOPROTOOPT; np->repflow = 1; return 0; } if (freq->flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; if (net->ipv6.sysctl.flowlabel_state_ranges && (freq->flr_label & IPV6_FLOWLABEL_STATELESS_FLAG)) return -ERANGE; fl = fl_create(net, sk, freq, optval, optlen, &err); if (!fl) return err; sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); if (freq->flr_label) { err = -EEXIST; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq->flr_label) { if (freq->flr_flags & IPV6_FL_F_EXCL) { rcu_read_unlock_bh(); goto done; } fl1 = sfl->fl; if (!atomic_inc_not_zero(&fl1->users)) fl1 = NULL; break; } } rcu_read_unlock_bh(); if (!fl1) fl1 = fl_lookup(net, freq->flr_label); if (fl1) { recheck: err = -EEXIST; if (freq->flr_flags&IPV6_FL_F_EXCL) goto release; err = -EPERM; if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || ((fl1->share == IPV6_FL_S_PROCESS) && (fl1->owner.pid != fl->owner.pid)) || ((fl1->share == IPV6_FL_S_USER) && !uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -ENOMEM; if (!sfl1) goto release; if (fl->linger > fl1->linger) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) fl1->expires = fl->expires; fl_link(np, sfl1, fl1); fl_free(fl); return 0; release: fl_release(fl1); goto done; } } err = -ENOENT; if (!(freq->flr_flags & IPV6_FL_F_CREATE)) goto done; err = -ENOMEM; if (!sfl1) goto done; err = mem_check(sk); if (err != 0) goto done; fl1 = fl_intern(net, fl, freq->flr_label); if (fl1) goto recheck; if (!freq->flr_label) { size_t offset = offsetof(struct in6_flowlabel_req, flr_label); if (copy_to_sockptr_offset(optval, offset, &fl->label, sizeof(fl->label))) { /* Intentionally ignore fault. */ } } fl_link(np, sfl1, fl); return 0; done: fl_free(fl); kfree(sfl1); return err; } int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen) { struct in6_flowlabel_req freq; if (optlen < sizeof(freq)) return -EINVAL; if (copy_from_sockptr(&freq, optval, sizeof(freq))) return -EFAULT; switch (freq.flr_action) { case IPV6_FL_A_PUT: return ipv6_flowlabel_put(sk, &freq); case IPV6_FL_A_RENEW: return ipv6_flowlabel_renew(sk, &freq); case IPV6_FL_A_GET: return ipv6_flowlabel_get(sk, &freq, optval, optlen); default: return -EINVAL; } } #ifdef CONFIG_PROC_FS struct ip6fl_iter_state { struct seq_net_private p; struct pid_namespace *pid_ns; int bucket; }; #define ip6fl_seq_private(seq) ((struct ip6fl_iter_state *)(seq)->private) static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) { struct ip6_flowlabel *fl = NULL; struct ip6fl_iter_state *state = ip6fl_seq_private(seq); struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { for_each_fl_rcu(state->bucket, fl) { if (net_eq(fl->fl_net, net)) goto out; } } fl = NULL; out: return fl; } static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flowlabel *fl) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); struct net *net = seq_file_net(seq); for_each_fl_continue_rcu(fl) { if (net_eq(fl->fl_net, net)) goto out; } try_again: if (++state->bucket <= FL_HASH_MASK) { for_each_fl_rcu(state->bucket, fl) { if (net_eq(fl->fl_net, net)) goto out; } goto try_again; } fl = NULL; out: return fl; } static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_flowlabel *fl = ip6fl_get_first(seq); if (fl) while (pos && (fl = ip6fl_get_next(seq, fl)) != NULL) --pos; return pos ? NULL : fl; } static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); state->pid_ns = proc_pid_ns(file_inode(seq->file)->i_sb); rcu_read_lock_bh(); return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ip6fl_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_flowlabel *fl; if (v == SEQ_START_TOKEN) fl = ip6fl_get_first(seq); else fl = ip6fl_get_next(seq, v); ++*pos; return fl; } static void ip6fl_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock_bh(); } static int ip6fl_seq_show(struct seq_file *seq, void *v) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Label S Owner Users Linger Expires Dst Opt\n"); } else { struct ip6_flowlabel *fl = v; seq_printf(seq, "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", (unsigned int)ntohl(fl->label), fl->share, ((fl->share == IPV6_FL_S_PROCESS) ? pid_nr_ns(fl->owner.pid, state->pid_ns) : ((fl->share == IPV6_FL_S_USER) ? from_kuid_munged(seq_user_ns(seq), fl->owner.uid) : 0)), atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, &fl->dst, fl->opt ? fl->opt->opt_nflen : 0); } return 0; } static const struct seq_operations ip6fl_seq_ops = { .start = ip6fl_seq_start, .next = ip6fl_seq_next, .stop = ip6fl_seq_stop, .show = ip6fl_seq_show, }; static int __net_init ip6_flowlabel_proc_init(struct net *net) { if (!proc_create_net("ip6_flowlabel", 0444, net->proc_net, &ip6fl_seq_ops, sizeof(struct ip6fl_iter_state))) return -ENOMEM; return 0; } static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { remove_proc_entry("ip6_flowlabel", net->proc_net); } #else static inline int ip6_flowlabel_proc_init(struct net *net) { return 0; } static inline void ip6_flowlabel_proc_fini(struct net *net) { } #endif static void __net_exit ip6_flowlabel_net_exit(struct net *net) { ip6_fl_purge(net); ip6_flowlabel_proc_fini(net); } static struct pernet_operations ip6_flowlabel_net_ops = { .init = ip6_flowlabel_proc_init, .exit = ip6_flowlabel_net_exit, }; int ip6_flowlabel_init(void) { return register_pernet_subsys(&ip6_flowlabel_net_ops); } void ip6_flowlabel_cleanup(void) { static_key_deferred_flush(&ipv6_flowlabel_exclusive); del_timer(&ip6_fl_gc_timer); unregister_pernet_subsys(&ip6_flowlabel_net_ops); } |
| 326 325 1050 18 18 263 263 262 263 281 63 63 62 9 9 5 5 828 3788 261 | 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 | #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H #include <linux/lockdep.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/rwsem.h> #include <linux/tracepoint-defs.h> #include <linux/types.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), DECLARE_TRACEPOINT(mmap_lock_start_locking); DECLARE_TRACEPOINT(mmap_lock_acquire_returned); DECLARE_TRACEPOINT(mmap_lock_released); #ifdef CONFIG_TRACING void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write); static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_start_locking)) __mmap_lock_do_trace_start_locking(mm, write); } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { if (tracepoint_enabled(mmap_lock_acquire_returned)) __mmap_lock_do_trace_acquire_returned(mm, write, success); } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_released)) __mmap_lock_do_trace_released(mm, write); } #else /* !CONFIG_TRACING */ static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { } #endif /* CONFIG_TRACING */ static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); } static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } static inline bool mmap_write_trylock(struct mm_struct *mm) { bool ret; __mmap_lock_trace_start_locking(mm, true); ret = down_write_trylock(&mm->mmap_lock) != 0; __mmap_lock_trace_acquire_returned(mm, true, ret); return ret; } static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, false); down_read(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, true); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_killable(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, ret == 0); return ret; } static inline bool mmap_read_trylock(struct mm_struct *mm) { bool ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_trylock(&mm->mmap_lock) != 0; __mmap_lock_trace_acquire_returned(mm, false, ret); return ret; } static inline void mmap_read_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read(&mm->mmap_lock); } static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) { lockdep_assert_held(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline void mmap_assert_write_locked(struct mm_struct *mm) { lockdep_assert_held_write(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 36 | 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 /* Multipath TCP * * Copyright (c) 2019, Intel Corporation. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" #include "mib.h" /* path manager command handlers */ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo) { u8 add_addr = READ_ONCE(msk->pm.addr_signal); pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo); lockdep_assert_held(&msk->pm.lock); if (add_addr & (echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) { pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo); return -EINVAL; } if (echo) { msk->pm.remote = *addr; add_addr |= BIT(MPTCP_ADD_ADDR_ECHO); } else { msk->pm.local = *addr; add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL); } WRITE_ONCE(msk->pm.addr_signal, add_addr); return 0; } int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { u8 rm_addr = READ_ONCE(msk->pm.addr_signal); pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr); if (rm_addr) { pr_warn("addr_signal error, rm_addr=%d", rm_addr); return -EINVAL; } msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); mptcp_pm_nl_addr_send_ack(msk); return 0; } int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr); spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, rm_list); spin_unlock_bh(&msk->pm.lock); return 0; } /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) { struct mptcp_pm_data *pm = &msk->pm; pr_debug("msk=%p, token=%u side=%d\n", msk, msk->token, server_side); WRITE_ONCE(pm->server_side, server_side); mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); } bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; unsigned int subflows_max; int ret = 0; subflows_max = mptcp_pm_get_subflows_max(msk); pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows, subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ if (!READ_ONCE(pm->accept_subflow)) return false; spin_lock_bh(&pm->lock); if (READ_ONCE(pm->accept_subflow)) { ret = pm->subflows < subflows_max; if (ret && ++pm->subflows == subflows_max) WRITE_ONCE(pm->accept_subflow, false); } spin_unlock_bh(&pm->lock); return ret; } /* return true if the new status bit is currently cleared, that is, this event * can be server, eventually by an already scheduled work */ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, enum mptcp_pm_status new_status) { pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status, BIT(new_status)); if (msk->pm.status & BIT(new_status)) return false; msk->pm.status |= BIT(new_status); mptcp_schedule_work((struct sock *)msk); return true; } void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct mptcp_pm_data *pm = &msk->pm; bool announce = false; pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); /* mptcp_pm_fully_established() can be invoked by multiple * racing paths - accept() and check_fully_established() * be sure to serve this event only once. */ if (READ_ONCE(pm->work_pending) && !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED))) mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED); if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0) announce = true; msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED); spin_unlock_bh(&pm->lock); if (announce) mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, gfp); } void mptcp_pm_connection_closed(struct mptcp_sock *msk) { pr_debug("msk=%p\n", msk); } void mptcp_pm_subflow_established(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; pr_debug("msk=%p\n", msk); if (!READ_ONCE(pm->work_pending)) return; spin_lock_bh(&pm->lock); if (READ_ONCE(pm->work_pending)) mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED); spin_unlock_bh(&pm->lock); } void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id) { pr_debug("msk=%p\n", msk); } void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { struct mptcp_pm_data *pm = &msk->pm; pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id, READ_ONCE(pm->accept_addr)); mptcp_event_addr_announced(msk, addr); spin_lock_bh(&pm->lock); /* id0 should not have a different address */ if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) || (addr->id > 0 && !READ_ONCE(pm->accept_addr))) { mptcp_pm_announce_addr(msk, addr, true); mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->remote = *addr; } else { __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } spin_unlock_bh(&pm->lock); } void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { struct mptcp_pm_data *pm = &msk->pm; pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); if (mptcp_lookup_anno_list_by_saddr(msk, addr) && READ_ONCE(pm->work_pending)) mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED); spin_unlock_bh(&pm->lock); } void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk) { if (!mptcp_pm_should_add_signal(msk)) return; mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK); } void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { struct mptcp_pm_data *pm = &msk->pm; u8 i; pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr); for (i = 0; i < rm_list->nr; i++) mptcp_event_addr_removed(msk, rm_list->ids[i]); spin_lock_bh(&pm->lock); if (mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED)) pm->rm_list_rx = *rm_list; else __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_RMADDRDROP); spin_unlock_bh(&pm->lock); } void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup); subflow->backup = bkup; mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC); } void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) { pr_debug("fail_seq=%llu\n", fail_seq); } /* path manager helpers */ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, unsigned int opt_size, unsigned int remaining, struct mptcp_addr_info *addr, bool *echo, bool *port, bool *drop_other_suboptions) { int ret = false; u8 add_addr; u8 family; spin_lock_bh(&msk->pm.lock); /* double check after the lock is acquired */ if (!mptcp_pm_should_add_signal(msk)) goto out_unlock; /* always drop every other options for pure ack ADD_ADDR; this is a * plain dup-ack from TCP perspective. The other MPTCP-relevant info, * if any, will be carried by the 'original' TCP ack */ if (skb && skb_is_tcp_pure_ack(skb)) { remaining += opt_size; *drop_other_suboptions = true; } *echo = mptcp_pm_should_add_signal_echo(msk); *port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); family = *echo ? msk->pm.remote.family : msk->pm.local.family; if (remaining < mptcp_add_addr_len(family, *echo, *port)) goto out_unlock; if (*echo) { *addr = msk->pm.remote; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO); } else { *addr = msk->pm.local; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL); } WRITE_ONCE(msk->pm.addr_signal, add_addr); ret = true; out_unlock: spin_unlock_bh(&msk->pm.lock); return ret; } bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list) { int ret = false, len; u8 rm_addr; spin_lock_bh(&msk->pm.lock); /* double check after the lock is acquired */ if (!mptcp_pm_should_rm_signal(msk)) goto out_unlock; rm_addr = msk->pm.addr_signal & ~BIT(MPTCP_RM_ADDR_SIGNAL); len = mptcp_rm_addr_len(&msk->pm.rm_list_tx); if (len < 0) { WRITE_ONCE(msk->pm.addr_signal, rm_addr); goto out_unlock; } if (remaining < len) goto out_unlock; *rm_list = msk->pm.rm_list_tx; WRITE_ONCE(msk->pm.addr_signal, rm_addr); ret = true; out_unlock: spin_unlock_bh(&msk->pm.lock); return ret; } int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) { return mptcp_pm_nl_get_local_id(msk, skc); } bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) { struct mptcp_addr_info skc_local; mptcp_local_address((struct sock_common *)skc, &skc_local); return mptcp_pm_nl_is_backup(msk, &skc_local); } void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp); /* keep track of rtx periods with no progress */ if (!subflow->stale_count) { subflow->stale_rcv_tstamp = rcv_tstamp; subflow->stale_count++; } else if (subflow->stale_rcv_tstamp == rcv_tstamp) { if (subflow->stale_count < U8_MAX) subflow->stale_count++; mptcp_pm_nl_subflow_chk_stale(msk, ssk); } else { subflow->stale_count = 0; mptcp_subflow_set_active(subflow); } } void mptcp_pm_data_init(struct mptcp_sock *msk) { msk->pm.add_addr_signaled = 0; msk->pm.add_addr_accepted = 0; msk->pm.local_addr_used = 0; msk->pm.subflows = 0; msk->pm.rm_list_tx.nr = 0; msk->pm.rm_list_rx.nr = 0; WRITE_ONCE(msk->pm.work_pending, false); WRITE_ONCE(msk->pm.addr_signal, 0); WRITE_ONCE(msk->pm.accept_addr, false); WRITE_ONCE(msk->pm.accept_subflow, false); WRITE_ONCE(msk->pm.remote_deny_join_id0, false); msk->pm.status = 0; spin_lock_init(&msk->pm.lock); INIT_LIST_HEAD(&msk->pm.anno_list); mptcp_pm_nl_data_init(msk); } void __init mptcp_pm_init(void) { mptcp_pm_nl_init(); } |
| 10 6 9 653 633 351 350 63 8 181 182 1 6 3 135 177 136 22 2 216 6 212 182 3 177 179 217 216 217 218 217 218 2 218 5 9 5 1 3 8 8 8 2 2 1 3 3 3 3 2 2 14 14 13 10 10 10 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules * * Copyright (C)2003-2006 Helsinki University of Technology * Copyright (C)2003-2006 USAGI/WIDE Project * * Authors * Thomas Graf <tgraf@suug.ch> * Ville Nuorvala <vnuorval@tcs.hut.fi> */ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/export.h> #include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/netlink.h> struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; u8 tclass; }; static bool fib6_rule_matchall(const struct fib_rule *rule) { struct fib6_rule *r = container_of(rule, struct fib6_rule, common); if (r->dst.plen || r->src.plen || r->tclass) return false; return fib_rule_matchall(rule); } bool fib6_rule_default(const struct fib_rule *rule) { if (!fib6_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || rule->l3mdev) return false; if (rule->table != RT6_TABLE_LOCAL && rule->table != RT6_TABLE_MAIN) return false; return true; } EXPORT_SYMBOL_GPL(fib6_rule_default); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, AF_INET6, extack); } unsigned int fib6_rules_seq_read(struct net *net) { return fib_rules_seq_read(net, AF_INET6); } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { int err; if (net->ipv6.fib6_has_custom_rules) { struct fib_lookup_arg arg = { .lookup_ptr = fib6_table_lookup, .lookup_data = &oif, .result = res, .flags = FIB_LOOKUP_NOREF, }; l3mdev_update_flow(net, flowi6_to_flowi(fl6)); err = fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); } else { err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif, fl6, res, flags); if (err || res->f6i == net->ipv6.fib6_null_entry) err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } return err; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { if (net->ipv6.fib6_has_custom_rules) { struct fib6_result res = {}; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .lookup_data = skb, .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi6_to_flowi(fl6)); fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); if (res.rt6) return &res.rt6->dst; } else { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_local_tbl, fl6, skb, flags); if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); } if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&net->ipv6.ip6_null_entry->dst); return &net->ipv6.ip6_null_entry->dst; } static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags, struct flowi6 *flp6, const struct net_device *dev) { struct fib6_rule *r = (struct fib6_rule *)rule; /* If we need to find a source address for this traffic, * we check the result if it meets requirement of the rule. */ if ((rule->flags & FIB_RULE_FIND_SADDR) && r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { struct in6_addr saddr; if (ipv6_dev_get_saddr(net, dev, &flp6->daddr, rt6_flags2srcprefs(flags), &saddr)) return -EAGAIN; if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) return -EAGAIN; flp6->saddr = saddr; } return 0; } static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct flowi6 *flp6 = &flp->u.ip6; struct net *net = rule->fr_net; struct fib6_table *table; int err, *oif; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } tb_id = fib_rule_get_table(rule, arg); table = fib6_get_table(net, tb_id); if (!table) return -EAGAIN; oif = (int *)arg->lookup_data; err = fib6_table_lookup(net, table, *oif, flp6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) err = fib6_rule_saddr(net, rule, flags, flp6, res->nh->fib_nh_dev); else err = -EAGAIN; return err; } static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct flowi6 *flp6 = &flp->u.ip6; struct rt6_info *rt = NULL; struct fib6_table *table; struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; int err = 0; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: err = -ENETUNREACH; rt = net->ipv6.ip6_null_entry; goto discard_pkt; default: case FR_ACT_BLACKHOLE: err = -EINVAL; rt = net->ipv6.ip6_blk_hole_entry; goto discard_pkt; case FR_ACT_PROHIBIT: err = -EACCES; rt = net->ipv6.ip6_prohibit_entry; goto discard_pkt; } tb_id = fib_rule_get_table(rule, arg); table = fib6_get_table(net, tb_id); if (!table) { err = -EAGAIN; goto out; } rt = pol_lookup_func(lookup, net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { struct inet6_dev *idev = ip6_dst_idev(&rt->dst); if (!idev) goto again; err = fib6_rule_saddr(net, rule, flags, flp6, idev->dev); if (err == -EAGAIN) goto again; err = rt->dst.error; if (err != -EAGAIN) goto out; } again: ip6_rt_put_flags(rt, flags); err = -EAGAIN; rt = NULL; goto out; discard_pkt: if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); out: res->rt6 = rt; return err; } INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { if (arg->lookup_ptr == fib6_table_lookup) return fib6_rule_action_alt(rule, flp, flags, arg); return __fib6_rule_action(rule, flp, flags, arg); } INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct rt6_info *rt = res->rt6; struct net_device *dev = NULL; if (!rt) return false; if (rt->rt6i_idev) dev = rt->rt6i_idev->dev; /* do not accept result if the route does * not meet the required prefix length */ if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) goto suppress_route; /* do not accept result if the route uses a device * belonging to a forbidden interface group */ if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) goto suppress_route; return false; suppress_route: ip6_rt_put_flags(rt, flags); return true; } INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; struct flowi6 *fl6 = &fl->u.ip6; if (r->dst.plen && !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen)) return 0; /* * If FIB_RULE_FIND_SADDR is set and we do not have a * source address for the traffic, we defer check for * source address. */ if (r->src.plen) { if (flags & RT6_LOOKUP_F_HAS_SADDR) { if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr, r->src.plen)) return 0; } else if (!(r->common.flags & FIB_RULE_FIND_SADDR)) return 0; } if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) return 0; if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) return 0; if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport)) return 0; if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport)) return 0; return 1; } static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { FRA_GENERIC_POLICY, }; static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { int err = -EINVAL; struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); goto errout; } if (fib6_new_table(net, rule->table) == NULL) { err = -ENOBUFS; goto errout; } } if (frh->src_len) rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]); if (frh->dst_len) rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]); rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; rule6->tclass = frh->tos; if (fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect++; net->ipv6.fib6_has_custom_rules = true; err = 0; errout: return err; } static int fib6_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; if (net->ipv6.fib6_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect--; return 0; } static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (frh->src_len && (rule6->src.plen != frh->src_len)) return 0; if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) return 0; if (frh->tos && (rule6->tclass != frh->tos)) return 0; if (frh->src_len && nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) return 0; if (frh->dst_len && nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) return 0; return 1; } static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { struct fib6_rule *rule6 = (struct fib6_rule *) rule; frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; frh->tos = rule6->tclass; if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || (rule6->src.plen && nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr))) goto nla_put_failure; return 0; nla_put_failure: return -ENOBUFS; } static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ + nla_total_size(16); /* src */ } static void fib6_rule_flush_cache(struct fib_rules_ops *ops) { rt_genid_bump_ipv6(ops->fro_net); } static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, .match = fib6_rule_match, .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, .delete = fib6_rule_delete, .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .policy = fib6_rule_policy, .owner = THIS_MODULE, .fro_net = &init_net, }; static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; int err; ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) goto out_fib6_rules_ops; net->ipv6.fib6_rules_ops = ops; net->ipv6.fib6_rules_require_fldissect = 0; out: return err; out_fib6_rules_ops: fib_rules_unregister(ops); goto out; } static void __net_exit fib6_rules_net_exit(struct net *net) { rtnl_lock(); fib_rules_unregister(net->ipv6.fib6_rules_ops); rtnl_unlock(); } static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, .exit = fib6_rules_net_exit, }; int __init fib6_rules_init(void) { return register_pernet_subsys(&fib6_rules_net_ops); } void fib6_rules_cleanup(void) { unregister_pernet_subsys(&fib6_rules_net_ops); } |
| 4 487 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* linux/net/inet/arp.h */ #ifndef _ARP_H #define _ARP_H #include <linux/if_arp.h> #include <linux/hash.h> #include <net/neighbour.h> extern struct neigh_table arp_tbl; static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); return val * hash_rnd[0]; } #ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) key = INADDR_ANY; return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } #else static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { return NULL; } #endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } void arp_init(void); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw); void arp_xmit(struct sk_buff *skb); #endif /* _ARP_H */ |
| 231 230 39 4284 4294 11 11 11 4 212 216 216 75 70 1469 6131 424 427 427 4275 21 4259 4296 256 52 53 11 11 11 11 216 215 216 70 70 70 70 2 84 87 86 87 86 87 48 2 19 38 66 65 62 62 162 162 3 3430 2 4797 1654 3359 91 3434 2 3 4806 5 4799 3426 2 1 3392 4801 4799 4807 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <crypto/hash.h> #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <net/checksum.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #define PIPE_PARANOIA /* for now */ /* covers iovec and kvec alike */ #define iterate_iovec(i, n, base, len, off, __p, STEP) { \ size_t off = 0; \ size_t skip = i->iov_offset; \ do { \ len = min(n, __p->iov_len - skip); \ if (likely(len)) { \ base = __p->iov_base + skip; \ len -= (STEP); \ off += len; \ skip += len; \ n -= len; \ if (skip < __p->iov_len) \ break; \ } \ __p++; \ skip = 0; \ } while (n); \ i->iov_offset = skip; \ n = off; \ } #define iterate_bvec(i, n, base, len, off, p, STEP) { \ size_t off = 0; \ unsigned skip = i->iov_offset; \ while (n) { \ unsigned offset = p->bv_offset + skip; \ unsigned left; \ void *kaddr = kmap_local_page(p->bv_page + \ offset / PAGE_SIZE); \ base = kaddr + offset % PAGE_SIZE; \ len = min(min(n, (size_t)(p->bv_len - skip)), \ (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); \ left = (STEP); \ kunmap_local(kaddr); \ len -= left; \ off += len; \ skip += len; \ if (skip == p->bv_len) { \ skip = 0; \ p++; \ } \ n -= len; \ if (left) \ break; \ } \ i->iov_offset = skip; \ n = off; \ } #define iterate_xarray(i, n, base, len, __off, STEP) { \ __label__ __out; \ size_t __off = 0; \ struct page *head = NULL; \ loff_t start = i->xarray_start + i->iov_offset; \ unsigned offset = start % PAGE_SIZE; \ pgoff_t index = start / PAGE_SIZE; \ int j; \ \ XA_STATE(xas, i->xarray, index); \ \ rcu_read_lock(); \ xas_for_each(&xas, head, ULONG_MAX) { \ unsigned left; \ if (xas_retry(&xas, head)) \ continue; \ if (WARN_ON(xa_is_value(head))) \ break; \ if (WARN_ON(PageHuge(head))) \ break; \ for (j = (head->index < index) ? index - head->index : 0; \ j < thp_nr_pages(head); j++) { \ void *kaddr = kmap_local_page(head + j); \ base = kaddr + offset; \ len = PAGE_SIZE - offset; \ len = min(n, len); \ left = (STEP); \ kunmap_local(kaddr); \ len -= left; \ __off += len; \ n -= len; \ if (left || n == 0) \ goto __out; \ offset = 0; \ } \ } \ __out: \ rcu_read_unlock(); \ i->iov_offset += __off; \ n = __off; \ } #define __iterate_and_advance(i, n, base, len, off, I, K) { \ if (unlikely(i->count < n)) \ n = i->count; \ if (likely(n)) { \ if (likely(iter_is_iovec(i))) { \ const struct iovec *iov = i->iov; \ void __user *base; \ size_t len; \ iterate_iovec(i, n, base, len, off, \ iov, (I)) \ i->nr_segs -= iov - i->iov; \ i->iov = iov; \ } else if (iov_iter_is_bvec(i)) { \ const struct bio_vec *bvec = i->bvec; \ void *base; \ size_t len; \ iterate_bvec(i, n, base, len, off, \ bvec, (K)) \ i->nr_segs -= bvec - i->bvec; \ i->bvec = bvec; \ } else if (iov_iter_is_kvec(i)) { \ const struct kvec *kvec = i->kvec; \ void *base; \ size_t len; \ iterate_iovec(i, n, base, len, off, \ kvec, (K)) \ i->nr_segs -= kvec - i->kvec; \ i->kvec = kvec; \ } else if (iov_iter_is_xarray(i)) { \ void *base; \ size_t len; \ iterate_xarray(i, n, base, len, off, \ (K)) \ } \ i->count -= n; \ } \ } #define iterate_and_advance(i, n, base, len, off, I, K) \ __iterate_and_advance(i, n, base, len, off, I, ((void)(K),0)) static int copyout(void __user *to, const void *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } static int copyin(void *to, const void __user *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(from, n)) { instrument_copy_from_user(to, from, n); n = raw_copy_from_user(to, from, n); } return n; } static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *from; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_writeable(buf, copy)) { kaddr = kmap_atomic(page); from = kaddr + offset; /* first chunk, usually the only one */ left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = from - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); from = kaddr + offset; left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *to; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_readable(buf, copy)) { kaddr = kmap_atomic(page); to = kaddr + offset; /* first chunk, usually the only one */ left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = to - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); to = kaddr + offset; left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } #ifdef PIPE_PARANOIA static bool sanity(const struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_head = pipe->head; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int p_occupancy = pipe_occupancy(p_head, p_tail); unsigned int i_head = i->head; unsigned int idx; if (i->iov_offset) { struct pipe_buffer *p; if (unlikely(p_occupancy == 0)) goto Bad; // pipe must be non-empty if (unlikely(i_head != p_head - 1)) goto Bad; // must be at the last buffer... p = &pipe->bufs[i_head & p_mask]; if (unlikely(p->offset + p->len != i->iov_offset)) goto Bad; // ... at the end of segment } else { if (i_head != p_head) goto Bad; // must be right after the last buffer } return true; Bad: printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset); printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n", p_head, p_tail, pipe->ring_size); for (idx = 0; idx < pipe->ring_size; idx++) printk(KERN_ERR "[%p %p %d %d]\n", pipe->bufs[idx].ops, pipe->bufs[idx].page, pipe->bufs[idx].offset, pipe->bufs[idx].len); WARN_ON(1); return false; } #else #define sanity(i) true #endif static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; struct pipe_buffer *buf; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; if (!sanity(i)) return 0; off = i->iov_offset; buf = &pipe->bufs[i_head & p_mask]; if (off) { if (offset == off && buf->page == page) { /* merge with the last one */ buf->len += bytes; i->iov_offset += bytes; goto out; } i_head++; buf = &pipe->bufs[i_head & p_mask]; } if (pipe_full(i_head, p_tail, pipe->max_usage)) return 0; buf->ops = &page_cache_pipe_buf_ops; buf->flags = 0; get_page(page); buf->page = page; buf->offset = offset; buf->len = bytes; pipe->head = i_head + 1; i->iov_offset = offset + bytes; i->head = i_head; out: i->count -= bytes; return bytes; } /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator * @size: maximum length * * Fault in one or more iovecs of the given iov_iter, to a maximum length of * @size. For each iovec, fault in each page that constitutes the iovec. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). * * Always returns 0 for non-userspace iterators. */ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) { if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_readable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_readable); /* * fault_in_iov_iter_writeable - fault in iov iterator for writing * @i: iterator * @size: maximum length * * Faults in the iterator using get_user_pages(), i.e., without triggering * hardware page faults. This is primarily useful when we already know that * some or all of the pages in @i aren't in memory. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). * * Always returns 0 for non-user-space iterators. */ size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size) { if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_safe_writeable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_writeable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, .nofault = false, .data_source = direction, .iov = iov, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_init); static inline bool allocated(struct pipe_buffer *buf) { return buf->ops == &default_pipe_buf_ops; } static inline void data_start(const struct iov_iter *i, unsigned int *iter_headp, size_t *offp) { unsigned int p_mask = i->pipe->ring_size - 1; unsigned int iter_head = i->head; size_t off = i->iov_offset; if (off && (!allocated(&i->pipe->bufs[iter_head & p_mask]) || off == PAGE_SIZE)) { iter_head++; off = 0; } *iter_headp = iter_head; *offp = off; } static size_t push_pipe(struct iov_iter *i, size_t size, int *iter_headp, size_t *offp) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int iter_head; size_t off; ssize_t left; if (unlikely(size > i->count)) size = i->count; if (unlikely(!size)) return 0; left = size; data_start(i, &iter_head, &off); *iter_headp = iter_head; *offp = off; if (off) { left -= PAGE_SIZE - off; if (left <= 0) { pipe->bufs[iter_head & p_mask].len += size; return size; } pipe->bufs[iter_head & p_mask].len = PAGE_SIZE; iter_head++; } while (!pipe_full(iter_head, p_tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask]; struct page *page = alloc_page(GFP_USER); if (!page) break; buf->ops = &default_pipe_buf_ops; buf->flags = 0; buf->page = page; buf->offset = 0; buf->len = min_t(ssize_t, left, PAGE_SIZE); left -= buf->len; iter_head++; pipe->head = iter_head; if (left == 0) return size; } return size - left; } static size_t copy_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); memcpy_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; addr += chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } static __wsum csum_and_memcpy(void *to, const void *from, size_t len, __wsum sum, size_t off) { __wsum next = csum_partial_copy_nocheck(from, to, len); return csum_block_add(sum, next, off); } static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, struct iov_iter *i, __wsum *sump) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; __wsum sum = *sump; size_t off = 0; unsigned int i_head; size_t r; if (!sanity(i)) return 0; bytes = push_pipe(i, bytes, &i_head, &r); while (bytes) { size_t chunk = min_t(size_t, bytes, PAGE_SIZE - r); char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page); sum = csum_and_memcpy(p + r, addr + off, chunk, sum, off); kunmap_local(p); i->head = i_head; i->iov_offset = r + chunk; bytes -= chunk; off += chunk; r = 0; i_head++; } *sump = sum; i->count -= off; return off; } size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, base, len, off, copyout(base, addr + off, len), memcpy(base, addr + off, len) ) return bytes; } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static int copyout_mc(void __user *to, const void *from, size_t n) { if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = copy_mc_to_user((__force void *) to, from, n); } return n; } static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; unsigned int valid = pipe->head; size_t n, off, xfer = 0; if (!sanity(i)) return 0; n = push_pipe(i, bytes, &i_head, &off); while (n) { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page); unsigned long rem; rem = copy_mc_to_kernel(p + off, addr + xfer, chunk); chunk -= rem; kunmap_local(p); if (chunk) { i->head = i_head; i->iov_offset = off + chunk; xfer += chunk; valid = i_head + 1; } if (rem) { pipe->bufs[i_head & p_mask].len -= rem; pipe_discard_from(pipe, valid); break; } n -= chunk; off = 0; i_head++; } i->count -= xfer; return xfer; } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @i: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. * Compare to copy_to_iter() where only ITER_IOVEC attempts might return * a short copy. * * Return: number of bytes copied (may be %0) */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return copy_mc_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); __iterate_and_advance(i, bytes, base, len, off, copyout_mc(base, addr + off, len), copy_mc_to_kernel(base, addr + off, len) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, base, len, off, copyin(addr + off, base, len), memcpy(addr + off, base, len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, base, len, off, __copy_from_user_inatomic_nocache(addr + off, base, len), memcpy(addr + off, base, len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @i: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. * * Return: number of bytes copied (may be %0) */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, base, len, off, __copy_from_user_flushcache(addr + off, base, len), memcpy_flushcache(addr + off, base, len) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (likely(n <= v && v <= (page_size(head)))) return true; WARN_ON(1); return false; } static size_t __copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (likely(iter_is_iovec(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); if (iov_iter_is_bvec(i) || iov_iter_is_kvec(i) || iov_iter_is_xarray(i)) { void *kaddr = kmap_local_page(page); size_t wanted = _copy_to_iter(kaddr + offset, bytes, i); kunmap_local(kaddr); return wanted; } if (iov_iter_is_pipe(i)) return copy_page_to_iter_pipe(page, offset, bytes, i); if (unlikely(iov_iter_is_discard(i))) { if (unlikely(i->count < bytes)) bytes = i->count; i->count -= bytes; return bytes; } WARN_ON(1); return 0; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { size_t n = __copy_page_to_iter(page, offset, min(bytes, (size_t)PAGE_SIZE - offset), i); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; if (likely(iter_is_iovec(i))) return copy_page_from_iter_iovec(page, offset, bytes, i); if (iov_iter_is_bvec(i) || iov_iter_is_kvec(i) || iov_iter_is_xarray(i)) { void *kaddr = kmap_local_page(page); size_t wanted = _copy_from_iter(kaddr + offset, bytes, i); kunmap_local(kaddr); return wanted; } WARN_ON(1); return 0; } EXPORT_SYMBOL(copy_page_from_iter); static size_t pipe_zero(size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); char *p = kmap_local_page(pipe->bufs[i_head & p_mask].page); memset(p + off, 0, chunk); kunmap_local(p); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, base, len, count, clear_user(base, len), memset(base, 0, len) ) return bytes; } EXPORT_SYMBOL(iov_iter_zero); size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i) { char *kaddr = kmap_atomic(page), *p = kaddr + offset; if (unlikely(!page_copy_sane(page, offset, bytes))) { kunmap_atomic(kaddr); return 0; } if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; } iterate_and_advance(i, bytes, base, len, off, copyin(p + off, base, len), memcpy(p + off, base, len) ) kunmap_atomic(kaddr); return bytes; } EXPORT_SYMBOL(copy_page_from_iter_atomic); static inline void pipe_truncate(struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_head = pipe->head; unsigned int p_mask = pipe->ring_size - 1; if (!pipe_empty(p_head, p_tail)) { struct pipe_buffer *buf; unsigned int i_head = i->head; size_t off = i->iov_offset; if (off) { buf = &pipe->bufs[i_head & p_mask]; buf->len = off - buf->offset; i_head++; } while (p_head != i_head) { p_head--; pipe_buf_release(pipe, &pipe->bufs[p_head & p_mask]); } pipe->head = p_head; } } static void pipe_advance(struct iov_iter *i, size_t size) { struct pipe_inode_info *pipe = i->pipe; if (size) { struct pipe_buffer *buf; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset, left = size; if (off) /* make it relative to the beginning of buffer */ left += off - pipe->bufs[i_head & p_mask].offset; while (1) { buf = &pipe->bufs[i_head & p_mask]; if (left <= buf->len) break; left -= buf->len; i_head++; } i->head = i_head; i->iov_offset = buf->offset + left; } i->count -= size; /* ... and discard everything past that point */ pipe_truncate(i); } static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { struct bvec_iter bi; bi.bi_size = i->count; bi.bi_bvec_done = i->iov_offset; bi.bi_idx = 0; bvec_iter_advance(i->bvec, &bi, size); i->bvec += bi.bi_idx; i->nr_segs -= bi.bi_idx; i->count = bi.bi_size; i->iov_offset = bi.bi_bvec_done; } static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) { const struct iovec *iov, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; // from beginning of current segment for (iov = i->iov, end = iov + i->nr_segs; iov < end; iov++) { if (likely(size < iov->iov_len)) break; size -= iov->iov_len; } i->iov_offset = size; i->nr_segs -= iov - i->iov; i->iov = iov; } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) size = i->count; if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) { /* iovec and kvec have identical layouts */ iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); } else if (iov_iter_is_pipe(i)) { pipe_advance(i, size); } else if (unlikely(iov_iter_is_xarray(i))) { i->iov_offset += size; i->count -= size; } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset; while (1) { struct pipe_buffer *b = &pipe->bufs[i_head & p_mask]; size_t n = off - b->offset; if (unroll < n) { off -= unroll; break; } unroll -= n; if (!unroll && i_head == i->start_head) { off = 0; break; } i_head--; b = &pipe->bufs[i_head & p_mask]; off = b->offset + b->len; } i->iov_offset = off; i->head = i_head; pipe_truncate(i); return; } if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_xarray(i)) { BUG(); /* We should never go beyond the start of the specified * range since we might then be straying into pages that * aren't pinned. */ } else if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else { /* same logics for iovec and kvec */ const struct iovec *iov = i->iov; while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (i->nr_segs > 1) { if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return min(i->count, i->iov->iov_len - i->iov_offset); if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_bvec); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { BUG_ON(direction != READ); WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size)); *i = (struct iov_iter){ .iter_type = ITER_PIPE, .data_source = false, .pipe = pipe, .head = pipe->head, .start_head = pipe->head, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_pipe); /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. * @xarray: The xarray to access. * @start: The start file position. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, .data_source = direction, .xarray = xarray, .xarray_start = start, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_xarray); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, .data_source = false, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_discard); static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; unsigned k; for (k = 0; k < i->nr_segs; k++, skip = 0) { size_t len = i->iov[k].iov_len - skip; if (len) { res |= (unsigned long)i->iov[k].iov_base + skip; if (len > size) len = size; res |= len; size -= len; if (!size) break; } } return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; unsigned k; for (k = 0; k < i->nr_segs; k++, skip = 0) { size_t len = i->bvec[k].bv_len - skip; res |= (unsigned long)i->bvec[k].bv_offset + skip; if (len > size) len = size; res |= len; size -= len; if (!size) break; } return res; } unsigned long iov_iter_alignment(const struct iov_iter *i) { /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_iter_alignment_iovec(i); if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); if (iov_iter_is_pipe(i)) { unsigned int p_mask = i->pipe->ring_size - 1; size_t size = i->count; if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; } if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; return 0; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; unsigned long v = 0; size_t size = i->count; unsigned k; if (WARN_ON(!iter_is_iovec(i))) return ~0U; for (k = 0; k < i->nr_segs; k++) { if (i->iov[k].iov_len) { unsigned long base = (unsigned long)i->iov[k].iov_base; if (v) // if not the first one res |= base | v; // this start | previous end v = base + i->iov[k].iov_len; if (size <= i->iov[k].iov_len) break; size -= i->iov[k].iov_len; } } return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static inline ssize_t __pipe_get_pages(struct iov_iter *i, size_t maxsize, struct page **pages, int iter_head, size_t *start) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; ssize_t n = push_pipe(i, maxsize, &iter_head, start); if (!n) return -EFAULT; maxsize = n; n += *start; while (n > 0) { get_page(*pages++ = pipe->bufs[iter_head & p_mask].page); iter_head++; n -= PAGE_SIZE; } return maxsize; } static ssize_t pipe_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { unsigned int iter_head, npages; size_t capacity; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); capacity = min(npages, maxpages) * PAGE_SIZE - *start; return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start); } static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { XA_STATE(xas, xa, index); struct page *page; unsigned int ret = 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) { xas_reset(&xas); continue; } pages[ret] = find_subpage(page, xas.xa_index); get_page(pages[ret]); if (++ret == nr_pages) break; } rcu_read_unlock(); return ret; } static ssize_t iter_xarray_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { unsigned nr, offset; pgoff_t index, count; size_t size = maxsize; loff_t pos; if (!size || !maxpages) return 0; pos = i->xarray_start + i->iov_offset; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; *_start_offset = offset; count = 1; if (size > PAGE_SIZE - offset) { size -= PAGE_SIZE - offset; count += size >> PAGE_SHIFT; size &= ~PAGE_MASK; if (size) count++; } if (count > maxpages) count = maxpages; nr = iter_xarray_populate_pages(pages, i->xarray, index, count); if (nr == 0) return 0; return min_t(size_t, nr * PAGE_SIZE - offset, maxsize); } /* must be done on non-empty ITER_IOVEC one */ static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size, size_t *start, size_t maxsize, unsigned maxpages) { size_t skip; long k; for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) { unsigned long addr = (unsigned long)i->iov[k].iov_base + skip; size_t len = i->iov[k].iov_len - skip; if (unlikely(!len)) continue; if (len > maxsize) len = maxsize; len += (*start = addr % PAGE_SIZE); if (len > maxpages * PAGE_SIZE) len = maxpages * PAGE_SIZE; *size = len; return addr & PAGE_MASK; } BUG(); // if it had been empty, we wouldn't get called } /* must be done on non-empty ITER_BVEC one */ static struct page *first_bvec_segment(const struct iov_iter *i, size_t *size, size_t *start, size_t maxsize, unsigned maxpages) { struct page *page; size_t skip = i->iov_offset, len; len = i->bvec->bv_len - skip; if (len > maxsize) len = maxsize; skip += i->bvec->bv_offset; page = i->bvec->bv_page + skip / PAGE_SIZE; len += (*start = skip % PAGE_SIZE); if (len > maxpages * PAGE_SIZE) len = maxpages * PAGE_SIZE; *size = len; return page; } ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { size_t len; int n, res; if (maxsize > i->count) maxsize = i->count; if (!maxsize) return 0; if (likely(iter_is_iovec(i))) { unsigned int gup_flags = 0; unsigned long addr; if (iov_iter_rw(i) != WRITE) gup_flags |= FOLL_WRITE; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &len, start, maxsize, maxpages); n = DIV_ROUND_UP(len, PAGE_SIZE); res = get_user_pages_fast(addr, n, gup_flags, pages); if (unlikely(res <= 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; } if (iov_iter_is_bvec(i)) { struct page *page; page = first_bvec_segment(i, &len, start, maxsize, maxpages); n = DIV_ROUND_UP(len, PAGE_SIZE); while (n--) get_page(*pages++ = page++); return len - *start; } if (iov_iter_is_pipe(i)) return pipe_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; } EXPORT_SYMBOL(iov_iter_get_pages); static struct page **get_pages_array(size_t n) { return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL); } static ssize_t pipe_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; unsigned int iter_head, npages; ssize_t n; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); n = npages * PAGE_SIZE - *start; if (maxsize > n) maxsize = n; else npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE); p = get_pages_array(npages); if (!p) return -ENOMEM; n = __pipe_get_pages(i, maxsize, p, iter_head, start); if (n > 0) *pages = p; else kvfree(p); return n; } static ssize_t iter_xarray_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *_start_offset) { struct page **p; unsigned nr, offset; pgoff_t index, count; size_t size = maxsize; loff_t pos; if (!size) return 0; pos = i->xarray_start + i->iov_offset; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; *_start_offset = offset; count = 1; if (size > PAGE_SIZE - offset) { size -= PAGE_SIZE - offset; count += size >> PAGE_SHIFT; size &= ~PAGE_MASK; if (size) count++; } p = get_pages_array(count); if (!p) return -ENOMEM; *pages = p; nr = iter_xarray_populate_pages(p, i->xarray, index, count); if (nr == 0) return 0; return min_t(size_t, nr * PAGE_SIZE - offset, maxsize); } ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; size_t len; int n, res; if (maxsize > i->count) maxsize = i->count; if (!maxsize) return 0; if (likely(iter_is_iovec(i))) { unsigned int gup_flags = 0; unsigned long addr; if (iov_iter_rw(i) != WRITE) gup_flags |= FOLL_WRITE; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &len, start, maxsize, ~0U); n = DIV_ROUND_UP(len, PAGE_SIZE); p = get_pages_array(n); if (!p) return -ENOMEM; res = get_user_pages_fast(addr, n, gup_flags, p); if (unlikely(res <= 0)) { kvfree(p); *pages = NULL; return res; } *pages = p; return (res == n ? len : res * PAGE_SIZE) - *start; } if (iov_iter_is_bvec(i)) { struct page *page; page = first_bvec_segment(i, &len, start, maxsize, ~0U); n = DIV_ROUND_UP(len, PAGE_SIZE); *pages = p = get_pages_array(n); if (!p) return -ENOMEM; while (n--) get_page(*p++ = page++); return len - *start; } if (iov_iter_is_pipe(i)) return pipe_get_pages_alloc(i, pages, maxsize, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages_alloc(i, pages, maxsize, start); return -EFAULT; } EXPORT_SYMBOL(iov_iter_get_pages_alloc); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { __wsum sum, next; sum = *csum; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, base, len, off, ({ next = csum_and_copy_from_user(base, addr + off, len); sum = csum_block_add(sum, next, off); next ? 0 : len; }), ({ sum = csum_and_memcpy(addr + off, base, len, sum, off); }) ) *csum = sum; return bytes; } EXPORT_SYMBOL(csum_and_copy_from_iter); size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, struct iov_iter *i) { struct csum_state *csstate = _csstate; __wsum sum, next; if (unlikely(iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } sum = csum_shift(csstate->csum, csstate->off); if (unlikely(iov_iter_is_pipe(i))) bytes = csum_and_copy_to_pipe_iter(addr, bytes, i, &sum); else iterate_and_advance(i, bytes, base, len, off, ({ next = csum_and_copy_to_user(addr + off, base, len); sum = csum_block_add(sum, next, off); next ? 0 : len; }), ({ sum = csum_and_memcpy(base, addr + off, len, sum, off); }) ) csstate->csum = csum_shift(sum, csstate->off); csstate->off += bytes; return bytes; } EXPORT_SYMBOL(csum_and_copy_to_iter); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i) { #ifdef CONFIG_CRYPTO_HASH struct ahash_request *hash = hashp; struct scatterlist sg; size_t copied; copied = copy_to_iter(addr, bytes, i); sg_init_one(&sg, addr, copied); ahash_request_set_crypt(hash, &sg, NULL, copied); crypto_ahash_update(hash); return copied; #else return 0; #endif } EXPORT_SYMBOL(hash_and_copy_to_iter); static int iov_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct iovec *p; int npages = 0; for (p = i->iov; size; skip = 0, p++) { unsigned offs = offset_in_page(p->iov_base + skip); size_t len = min(p->iov_len - skip, size); if (len) { size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } } return npages; } static int bvec_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct bio_vec *p; int npages = 0; for (p = i->bvec; size; skip = 0, p++) { unsigned offs = (p->bv_offset + skip) % PAGE_SIZE; size_t len = min(p->bv_len - skip, size); size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } return npages; } int iov_iter_npages(const struct iov_iter *i, int maxpages) { if (unlikely(!i->count)) return 0; /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); if (iov_iter_is_pipe(i)) { unsigned int iter_head; int npages; size_t off; if (!sanity(i)) return 0; data_start(i, &iter_head, &off); /* some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); return min(npages, maxpages); } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } return 0; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } if (unlikely(iov_iter_is_discard(new) || iov_iter_is_xarray(new))) return NULL; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else /* iovec and kvec have identical layout */ return new->iov = kmemdup(new->iov, new->nr_segs * sizeof(struct iovec), flags); } EXPORT_SYMBOL(dup_iter); static int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT, i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { unsigned long seg; if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec))) return -EFAULT; for (seg = 0; seg < nr_segs; seg++) { if ((ssize_t)iov[seg].iov_len < 0) return -EINVAL; } return 0; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); if (!iov) return ERR_PTR(-ENOMEM); } if (compat) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_single_range(int rw, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov->iov_base = buf; iov->iov_len = len; iov_iter_init(i, rw, iov, 1, len); return 0; } EXPORT_SYMBOL(import_single_range); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when * iov_iter_save_state() was called. * * @i: &struct iov_iter to restore * @state: state to restore from * * Used after iov_iter_save_state() to bring restore @i, if operations may * have advanced it. * * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC */ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && !iov_iter_is_kvec(i)) return; i->iov_offset = state->iov_offset; i->count = state->count; /* * For the *vec iters, nr_segs + iov is constant - if we increment * the vec, then we also decrement the nr_segs count. Hence we don't * need to track both of these, just one is enough and we can deduct * the other from that. ITER_KVEC and ITER_IOVEC are the same struct * size, so we can just increment the iov pointer as they are unionzed. * ITER_BVEC _may_ be the same size on some archs, but on others it is * not. Be safe and handle it separately. */ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); if (iov_iter_is_bvec(i)) i->bvec -= state->nr_segs - i->nr_segs; else i->iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } |
| 184 184 185 51 38 112 2384 27 2384 5104 2649 4736 3100 4363 3773 744 224 224 225 225 5011 4992 215 6173 5885 2913 6129 154 3444 3471 5019 2387 6161 6 1751 6169 15 581 6127 8 155 8 155 8 6164 2 834 6173 6199 1991 6168 6176 6 4 956 6151 6122 956 6150 6148 5045 4370 6134 6162 12 1 1 12 12 2 2 10 3 3 2 2 10 3 3 3 3 370 373 373 373 338 14 332 275 14 272 325 275 61 273 266 24 58 121 327 14 13 6 7 353 13 339 356 357 359 703 195 920 720 195 2 1 10 6716 3 6749 6570 8 569 1 153 2371 6490 6512 3 6526 4308 5938 2786 6132 920 69 310 941 1441 4305 2 4089 3 6488 6520 5089 6342 3 2783 2798 2781 6134 909 913 67 1433 4303 2 2901 3731 612 6496 2865 2870 5614 2312 735 736 1 29 462 1 1 1 7 3 3 7 20 2 34 705 210 160 210 28 191 151 11 152 9 149 11 11 149 1 149 148 112 22 4 112 18 134 208 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <asm/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); static noinline unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, unsigned int base) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, max_chars - 1, endp, base); return simple_strntoull(cp, max_chars, endp, base); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 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), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ' '); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Needs to run from preemptible context */ static_branch_disable(¬_filled_random_ptr_key); } static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); static int fill_random_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { /* This may be in an interrupt handler. */ queue_work(system_unbound_wq, &enable_ptr_key_work); return 0; } static struct notifier_block random_ready = { .notifier_call = fill_random_ptr_key }; static int __init initialize_ptr_random(void) { int key_size = sizeof(ptr_key); int ret; /* Use hw RNG if available. */ if (get_random_bytes_arch(&ptr_key, key_size) == key_size) { static_branch_disable(¬_filled_random_ptr_key); return 0; } ret = register_random_ready_notifier(&random_ready); if (!ret) { return 0; } else if (ret == -EALREADY) { /* This is in preemptible context */ enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } return ret; } early_initcall(initialize_ptr_random); /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (static_branch_unlikely(¬_filled_random_ptr_key)) return -EAGAIN; #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_irq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev->bd_partno) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev->bd_partno, spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); /* current bit is 'cur', most recently seen range is [rbot, rtop] */ int cur, rbot, rtop; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; rbot = cur = find_first_bit(bitmap, nr_bits); while (cur < nr_bits) { rtop = cur; cur = find_next_bit(bitmap, nr_bits, cur + 1); if (cur < nr_bits && cur <= rtop + 1) continue; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rbot < rtop) { if (buf < end) *buf = '-'; buf++; buf = number(buf, end, rtop, default_dec_spec); } rbot = cur; } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } strcpy(p, orig & BIT(31) ? " big-endian" : " little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; fallthrough; case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; break; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ fallthrough; default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; if (size != 0) return size - 1; return 0; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && (!isdigit(digit) || digit > '7')) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, field_width >= 0 ? field_width : INT_MAX, &next, base); else val.u = simple_strntoull(str, field_width >= 0 ? field_width : INT_MAX, &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0 /* xfrm_hash.c: Common hash table code. * * Copyright (C) 2006 David S. Miller (davem@davemloft.net) */ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/xfrm.h> #include "xfrm_hash.h" struct hlist_head *xfrm_hash_alloc(unsigned int sz) { struct hlist_head *n; if (sz <= PAGE_SIZE) n = kzalloc(sz, GFP_KERNEL); else if (hashdist) n = vzalloc(sz); else n = (struct hlist_head *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); return n; } void xfrm_hash_free(struct hlist_head *n, unsigned int sz) { if (sz <= PAGE_SIZE) kfree(n); else if (hashdist) vfree(n); else free_pages((unsigned long)n, get_order(sz)); } |
| 3 3 3 3 4 2 2 2 1 1 4 | 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 | /* * net/tipc/net.c: TIPC network routing code * * Copyright (c) 1995-2006, 2014, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. 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. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "net.h" #include "name_distr.h" #include "subscr.h" #include "socket.h" #include "node.h" #include "bcast.h" #include "link.h" #include "netlink.h" #include "monitor.h" /* * The TIPC locking policy is designed to ensure a very fine locking * granularity, permitting complete parallel access to individual * port and node/link instances. The code consists of four major * locking domains, each protected with their own disjunct set of locks. * * 1: The bearer level. * RTNL lock is used to serialize the process of configuring bearer * on update side, and RCU lock is applied on read side to make * bearer instance valid on both paths of message transmission and * reception. * * 2: The node and link level. * All node instances are saved into two tipc_node_list and node_htable * lists. The two lists are protected by node_list_lock on write side, * and they are guarded with RCU lock on read side. Especially node * instance is destroyed only when TIPC module is removed, and we can * confirm that there has no any user who is accessing the node at the * moment. Therefore, Except for iterating the two lists within RCU * protection, it's no needed to hold RCU that we access node instance * in other places. * * In addition, all members in node structure including link instances * are protected by node spin lock. * * 3: The transport level of the protocol. * This consists of the structures port, (and its user level * representations, such as user_port and tipc_sock), reference and * tipc_user (port.c, reg.c, socket.c). * * This layer has four different locks: * - The tipc_port spin_lock. This is protecting each port instance * from parallel data access and removal. Since we can not place * this lock in the port itself, it has been placed in the * corresponding reference table entry, which has the same life * cycle as the module. This entry is difficult to access from * outside the TIPC core, however, so a pointer to the lock has * been added in the port instance, -to be used for unlocking * only. * - A read/write lock to protect the reference table itself (teg.c). * (Nobody is using read-only access to this, so it can just as * well be changed to a spin_lock) * - A spin lock to protect the registry of kernel/driver users (reg.c) * - A global spin_lock (tipc_port_lock), which only task is to ensure * consistency where more than one port is involved in an operation, * i.e., when a port is part of a linked list of ports. * There are two such lists; 'port_list', which is used for management, * and 'wait_list', which is used to queue ports during congestion. * * 4: The name table (name_table.c, name_distr.c, subscription.c) * - There is one big read/write-lock (tipc_nametbl_lock) protecting the * overall name table structure. Nothing must be added/removed to * this structure without holding write access to it. * - There is one local spin_lock per sub_sequence, which can be seen * as a sub-domain to the tipc_nametbl_lock domain. It is used only * for translation operations, and is needed because a translation * steps the root of the 'publication' linked list between each lookup. * This is always used within the scope of a tipc_nametbl_lock(read). * - A local spin_lock protecting the queue of subscriber events. */ static void tipc_net_finalize(struct net *net, u32 addr); int tipc_net_init(struct net *net, u8 *node_id, u32 addr) { if (tipc_own_id(net)) { pr_info("Cannot configure node identity twice\n"); return -1; } pr_info("Started in network mode\n"); if (node_id) tipc_set_node_id(net, node_id); if (addr) tipc_net_finalize(net, addr); return 0; } static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); struct tipc_socket_addr sk = {0, addr}; struct tipc_uaddr ua; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, TIPC_NODE_STATE, addr, addr); if (cmpxchg(&tn->node_addr, 0, addr)) return; tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); tipc_mon_reinit_self(net); tipc_nametbl_publish(net, &ua, &sk, addr); } void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net *tn = container_of(work, struct tipc_net, work); tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) { if (!tipc_own_id(net)) return; rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); rtnl_unlock(); pr_info("Left network mode\n"); } static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = net_generic(net, tipc_net_id); u64 *w0 = (u64 *)&tn->node_id[0]; u64 *w1 = (u64 *)&tn->node_id[8]; struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_NET_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID, *w0, 0)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID_W1, *w1, 0)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int err; int done = cb->args[0]; struct tipc_nl_msg msg; if (done) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; err = __tipc_nl_add_net(net, &msg); if (err) goto out; done = 1; out: cb->args[0] = done; return skb->len; } int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; struct net *net = sock_net(skb->sk); struct tipc_net *tn = tipc_net(net); int err; if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, info->attrs[TIPC_NLA_NET], tipc_nl_net_policy, info->extack); if (err) return err; /* Can't change net id once TIPC has joined a network */ if (tipc_own_addr(net)) return -EPERM; if (attrs[TIPC_NLA_NET_ID]) { u32 val; val = nla_get_u32(attrs[TIPC_NLA_NET_ID]); if (val < 1 || val > 9999) return -EINVAL; tn->net_id = val; } if (attrs[TIPC_NLA_NET_ADDR]) { u32 addr; addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); if (!addr) return -EINVAL; tn->legacy_addr_format = true; tipc_net_init(net, NULL, addr); } if (attrs[TIPC_NLA_NET_NODEID]) { u8 node_id[NODE_ID_LEN]; u64 *w0 = (u64 *)&node_id[0]; u64 *w1 = (u64 *)&node_id[8]; if (!attrs[TIPC_NLA_NET_NODEID_W1]) return -EINVAL; *w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]); *w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]); tipc_net_init(net, node_id, 0); } return 0; } int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_net_set(skb, info); rtnl_unlock(); return err; } static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = tipc_net(net); struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, 0, TIPC_NL_ADDR_LEGACY_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (tn->legacy_addr_format) if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct tipc_nl_msg msg; struct sk_buff *rep; int err; rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; err = __tipc_nl_addr_legacy_get(net, &msg); if (err) { nlmsg_free(msg.skb); return err; } return genlmsg_reply(msg.skb, info); } |
| 4 5 18 988 979 15 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(struct device *d) { struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .owner = THIS_MODULE, .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 6 4 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <linux/in6.h> #include <net/ip.h> int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack) { *ip_proto = nla_get_u8(attr); switch (*ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: return 0; case IPPROTO_ICMP: if (family != AF_INET) break; return 0; #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ICMPV6: if (family != AF_INET6) break; return 0; #endif } NL_SET_ERR_MSG(extack, "Unsupported ip proto"); return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); |
| 93 93 44 124 3002 3 94 48 48 48 12 48 1323 1323 1321 1323 1323 2999 2999 3001 3104 2998 84 663 65 56 | 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 | /* 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 <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/bpfptr.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; 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; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; 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); 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, 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); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); int (*map_pop_elem)(struct bpf_map *map, void *value); int (*map_peek_elem)(struct bpf_map *map, void *value); /* 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); /* 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.*/ int (*map_redirect)(struct bpf_map *map, u32 ifindex, 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); int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags); /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). */ const struct bpf_map_ops *ops ____cacheline_aligned; 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; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; struct mutex freeze_mutex; atomic64_t writecnt; bool free_after_mult_rcu_gp; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) { return map->spin_lock_off >= 0; } static inline bool map_value_has_timer(const struct bpf_map *map) { return map->timer_off >= 0; } static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; if (unlikely(map_value_has_spin_lock(map))) { s_off = map->spin_lock_off; s_sz = sizeof(struct bpf_spin_lock); } if (unlikely(map_value_has_timer(map))) { t_off = map->timer_off; t_sz = sizeof(struct bpf_timer); } if (unlikely(s_sz || t_sz)) { if (s_off < t_off || !s_sz) { swap(s_off, t_off); swap(s_sz, t_sz); } memcpy(dst, src, t_off); memcpy(dst + t_off + t_sz, src + t_off + t_sz, s_off - t_off - t_sz); memcpy(dst + s_off + s_sz, src + s_off + s_sz, map->value_size - s_off - s_sz); } else { memcpy(dst, src, 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); 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 was "allocated" from a different helper, and cannot be mixed * with regular non-MEM_ALLOC'ed MEM types. */ MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), __BPF_TYPE_LAST_FLAG = MEM_ALLOC, }; /* 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 */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints 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_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. */ 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_ALLOC_MEM, /* pointer to dynamically allocated 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 */ __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_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, /* 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_ALLOC_MEM, /* returns a pointer to dynamically allocated 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_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | 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; 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]; }; 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_BUF, /* reg points to a read/write buffer */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ __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 inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && 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_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 btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); bool (*check_kfunc_call)(u32 kfunc_btf_id); }; 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 struct btf_func_model { u8 ret_size; u8 nr_args; u8 arg_size[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) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ #define BPF_MAX_TRAMP_PROGS 38 struct bpf_tramp_progs { struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; int nr_progs; }; /* 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 *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); 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; 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; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; 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; u64 selector; struct module *mod; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; 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; u32 image_off; struct bpf_ksym ksym; }; static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)) { return bpf_func(ctx, insnsi); } #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_prog *prog, 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, s64 *funcs, int num_funcs); #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), \ }, \ } #define DEFINE_BPF_DISPATCHER(name) \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)) \ { \ return bpf_func(ctx, insnsi); \ } \ 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, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)); \ 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_jit_alloc_exec_page(void); void bpf_image_ksym_add(void *data, 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 pages); void bpf_jit_uncharge_modmem(u32 pages); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, 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; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; }; 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; 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 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 offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; struct hlist_node tramp_hlist; /* 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; u32 size_poke_tab; 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 */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; #endif 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; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; }; struct bpf_array_aux { /* 'Ownership' of prog array 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 and JITed flag. */ struct { spinlock_t lock; enum bpf_prog_type type; bool jited; } owner; /* 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; struct work_struct work; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(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); }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 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); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); 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); 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); } #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } static inline void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { } 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; } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); void __percpu *pptrs[0] __aligned(8); }; }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 32 #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) 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; }; bool bpf_prog_array_compatible(struct bpf_array *array, 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); 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(&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_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(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; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; }; 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_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, 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 ret = 1; u32 func_ret; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); 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); ret &= (func_ret & 1); *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return ret; } static __always_inline u32 BPF_PROG_RUN_ARRAY_CG(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_cg_run_ctx run_ctx; u32 ret = 1; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); 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; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return ret; } static __always_inline u32 BPF_PROG_RUN_ARRAY(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; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); 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))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); out: rcu_read_unlock(); migrate_enable(); return ret; } /* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs * so BPF programs can request cwr for TCP packets. * * Current cgroup skb programs can only return 0 or 1 (0 to drop the * packet. This macro changes the behavior so the low order bit * indicates whether the packet should be dropped (0) or not (1) * and the next bit is a congestion notification bit. This could be * used by TCP to call tcp_enter_cwr() * * Hence, new allowed return values of CGROUP EGRESS BPF programs are: * 0: drop packet * 1: keep packet * 2: drop packet and cn * 3: keep packet and cn * * This macro then converts it 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: -EPERM skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ _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 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, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); 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 * __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, 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); #ifdef CONFIG_MEMCG_KMEM 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 __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else static inline void * bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags, node); } static inline void * bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { return kzalloc(size, flags); } static inline void __percpu * bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { return __alloc_percpu_gfp(size, align, flags); } #endif extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); } static inline bool bpf_allow_uninit_stack(void) { return perfmon_capable(); } static inline bool bpf_allow_ptr_to_map_access(void) { return perfmon_capable(); } static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { return perfmon_capable(); } 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); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); #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; } struct bpf_iter_aux_info { struct bpf_map *map; }; 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); /* 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--) *ldst++ = *lsrc++; } /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #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(void); 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(void); 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); bool bpf_prog_test_check_kfunc_call(u32 kfunc_id); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); 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); 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_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); 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); void bpf_task_storage_free(struct task_struct *task); 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); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } #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 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 dev_map_can_have_prog(struct bpf_map *map) { return false; } static inline void __dev_flush(void) { } 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(void) { } 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 bool cpu_map_prog_allowed(struct bpf_map *map) { return false; } 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 bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) { return false; } 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 const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { 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 bool unprivileged_ebpf_enabled(void) { return false; } #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, 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_offload_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_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->offload_requested; } static inline bool bpf_map_is_dev_bound(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); 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); 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_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_map_is_dev_bound(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 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; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #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_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_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_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_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_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_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; 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); #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; } #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); 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); #endif /* _LINUX_BPF_H */ |
| 39 2 19 32 31 32 17 32 19 10 9 9 39 31 9 37 19 19 3 39 39 39 39 37 39 3 3 16 16 16 21 21 12 2 6 21 16 16 14 14 37 31 31 2 2 2 40 30 39 16 37 16 49 6 4 39 39 19 19 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * uprobes-based tracing events * * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ #define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/security.h> #include <linux/ctype.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/uprobes.h> #include <linux/namei.h> #include <linux/string.h> #include <linux/rculist.h> #include "trace_dynevent.h" #include "trace_probe.h" #include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" struct uprobe_trace_entry_head { struct trace_entry ent; unsigned long vaddr[]; }; #define SIZEOF_TRACE_ENTRY(is_return) \ (sizeof(struct uprobe_trace_entry_head) + \ sizeof(unsigned long) * (is_return ? 2 : 1)) #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) static int trace_uprobe_create(const char *raw_command); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); static bool trace_uprobe_is_busy(struct dyn_event *ev); static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_uprobe_ops = { .create = trace_uprobe_create, .show = trace_uprobe_show, .is_busy = trace_uprobe_is_busy, .free = trace_uprobe_release, .match = trace_uprobe_match, }; /* * uprobe event core functions */ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; struct inode *inode; char *filename; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; struct trace_probe tp; }; static bool is_trace_uprobe(struct dyn_event *ev) { return ev->ops == &trace_uprobe_ops; } static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) { return container_of(ev, struct trace_uprobe, devent); } /** * for_each_trace_uprobe - iterate over the trace_uprobe list * @pos: the struct trace_uprobe * for each entry * @dpos: the struct dyn_event * to use as a loop cursor */ #define for_each_trace_uprobe(pos, dpos) \ for_each_dyn_event(dpos) \ if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); struct uprobe_dispatch_data { struct trace_uprobe *tu; unsigned long bp_addr; }; static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs); #ifdef CONFIG_STACK_GROWSUP static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr - (n * sizeof(long)); } #else static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr + (n * sizeof(long)); } #endif static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long ret; unsigned long addr = user_stack_pointer(regs); addr = adjust_stack_addr(addr, n); if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) return 0; return ret; } /* * Uprobes-specific fetch functions */ static nokprobe_inline int probe_mem_read(void *dest, void *src, size_t size) { void __user *vaddr = (void __force __user *)src; return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } static nokprobe_inline int probe_mem_read_user(void *dest, void *src, size_t size) { return probe_mem_read(dest, src, size); } /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ static nokprobe_inline int fetch_store_string(unsigned long addr, void *dest, void *base) { long ret; u32 loc = *(u32 *)dest; int maxlen = get_loc_len(loc); u8 *dst = get_loc_data(dest, base); void __user *src = (void __force __user *) addr; if (unlikely(!maxlen)) return -ENOMEM; if (addr == FETCH_TOKEN_COMM) ret = strlcpy(dst, current->comm, maxlen); else ret = strncpy_from_user(dst, src, maxlen); if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; else /* * Include the terminating null byte. In this case it * was copied by strncpy_from_user but not accounted * for in ret. */ ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } else *(u32 *)dest = make_data_loc(0, (void *)dst - base); return ret; } static nokprobe_inline int fetch_store_string_user(unsigned long addr, void *dest, void *base) { return fetch_store_string(addr, dest, base); } /* Return the length of string -- including null terminal byte */ static nokprobe_inline int fetch_store_strlen(unsigned long addr) { int len; void __user *vaddr = (void __force __user *) addr; if (addr == FETCH_TOKEN_COMM) len = strlen(current->comm) + 1; else len = strnlen_user(vaddr, MAX_STRING_SIZE); return (len > MAX_STRING_SIZE) ? 0 : len; } static nokprobe_inline int fetch_store_strlen_user(unsigned long addr) { return fetch_store_strlen(addr); } static unsigned long translate_user_vaddr(unsigned long file_offset) { unsigned long base_addr; struct uprobe_dispatch_data *udd; udd = (void *) current->utask->vaddr; base_addr = udd->bp_addr - udd->tu->offset; return base_addr + file_offset; } /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_REG: val = regs_get_register(regs, code->param); break; case FETCH_OP_STACK: val = get_user_stack_nth(regs, code->param); break; case FETCH_OP_STACKP: val = user_stack_pointer(regs); break; case FETCH_OP_RETVAL: val = regs_return_value(regs); break; case FETCH_OP_IMM: val = code->immediate; break; case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; case FETCH_OP_DATA: val = (unsigned long)code->data; break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; default: return -EILSEQ; } code++; return process_fetch_insn_bottom(code, val, dest, base); } NOKPROBE_SYMBOL(process_fetch_insn) static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { rwlock_init(&filter->rwlock); filter->nr_systemwide = 0; INIT_LIST_HEAD(&filter->perf_events); } static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) { return !filter->nr_systemwide && list_empty(&filter->perf_events); } static inline bool is_ret_probe(struct trace_uprobe *tu) { return tu->consumer.ret_handler != NULL; } static bool trace_uprobe_is_busy(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return trace_probe_is_enabled(&tu->tp); } static bool trace_uprobe_match_command_head(struct trace_uprobe *tu, int argc, const char **argv) { char buf[MAX_ARGSTR_LEN + 1]; int len; if (!argc) return true; len = strlen(tu->filename); if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':') return false; if (tu->ref_ctr_offset == 0) snprintf(buf, sizeof(buf), "0x%0*lx", (int)(sizeof(void *) * 2), tu->offset); else snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)", (int)(sizeof(void *) * 2), tu->offset, tu->ref_ctr_offset); if (strcmp(buf, &argv[0][len + 1])) return false; argc--; argv++; return trace_probe_match_command_args(&tu->tp, argc, argv); } static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return strcmp(trace_probe_name(&tu->tp), event) == 0 && (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) && trace_uprobe_match_command_head(tu, argc, argv); } static nokprobe_inline struct trace_uprobe * trace_uprobe_primary_from_call(struct trace_event_call *call) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return NULL; return container_of(tp, struct trace_uprobe, tp); } /* * Allocate new trace_uprobe and initialize it (including uprobes). */ static struct trace_uprobe * alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; int ret; tu = kzalloc(struct_size(tu, tp.args, nargs), GFP_KERNEL); if (!tu) return ERR_PTR(-ENOMEM); ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; dyn_event_init(&tu->devent, &trace_uprobe_ops); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: kfree(tu); return ERR_PTR(ret); } static void free_trace_uprobe(struct trace_uprobe *tu) { if (!tu) return; path_put(&tu->path); trace_probe_cleanup(&tu->tp); kfree(tu->filename); kfree(tu); } static struct trace_uprobe *find_probe_event(const char *event, const char *group) { struct dyn_event *pos; struct trace_uprobe *tu; for_each_trace_uprobe(tu, pos) if (strcmp(trace_probe_name(&tu->tp), event) == 0 && strcmp(trace_probe_group_name(&tu->tp), group) == 0) return tu; return NULL; } /* Unregister a trace_uprobe and probe_event */ static int unregister_trace_uprobe(struct trace_uprobe *tu) { int ret; if (trace_probe_has_sibling(&tu->tp)) goto unreg; /* If there's a reference to the dynamic event */ if (trace_event_dyn_busy(trace_probe_event_call(&tu->tp))) return -EBUSY; ret = unregister_uprobe_event(tu); if (ret) return ret; unreg: dyn_event_remove(&tu->devent); trace_probe_unlink(&tu->tp); free_trace_uprobe(tu); return 0; } static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, struct trace_uprobe *comp) { struct trace_probe_event *tpe = orig->tp.event; struct trace_probe *pos; struct inode *comp_inode = d_real_inode(comp->path.dentry); int i; list_for_each_entry(pos, &tpe->probes, list) { orig = container_of(pos, struct trace_uprobe, tp); if (comp_inode != d_real_inode(orig->path.dentry) || comp->offset != orig->offset) continue; /* * trace_probe_compare_arg_type() ensured that nr_args and * each argument name and type are same. Let's compare comm. */ for (i = 0; i < orig->tp.nr_args; i++) { if (strcmp(orig->tp.args[i].comm, comp->tp.args[i].comm)) break; } if (i == orig->tp.nr_args) return true; } return false; } static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) { int ret; ret = trace_probe_compare_arg_type(&tu->tp, &to->tp); if (ret) { /* Note that argument starts index = 2 */ trace_probe_log_set_index(ret + 1); trace_probe_log_err(0, DIFF_ARG_TYPE); return -EEXIST; } if (trace_uprobe_has_same_uprobe(to, tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, SAME_PROBE); return -EEXIST; } /* Append to existing event */ ret = trace_probe_append(&tu->tp, &to->tp); if (!ret) dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); return ret; } /* * Uprobe with multiple reference counter is not allowed. i.e. * If inode and offset matches, reference counter offset *must* * match as well. Though, there is one exception: If user is * replacing old trace_uprobe with new one(same group/event), * then we allow same uprobe with new reference counter as far * as the new one does not conflict with any other existing * ones. */ static int validate_ref_ctr_offset(struct trace_uprobe *new) { struct dyn_event *pos; struct trace_uprobe *tmp; struct inode *new_inode = d_real_inode(new->path.dentry); for_each_trace_uprobe(tmp, pos) { if (new_inode == d_real_inode(tmp->path.dentry) && new->offset == tmp->offset && new->ref_ctr_offset != tmp->ref_ctr_offset) { pr_warn("Reference counter offset mismatch."); return -EINVAL; } } return 0; } /* Register a trace_uprobe and probe_event */ static int register_trace_uprobe(struct trace_uprobe *tu) { struct trace_uprobe *old_tu; int ret; mutex_lock(&event_mutex); ret = validate_ref_ctr_offset(tu); if (ret) goto end; /* register as an event */ old_tu = find_probe_event(trace_probe_name(&tu->tp), trace_probe_group_name(&tu->tp)); if (old_tu) { if (is_ret_probe(tu) != is_ret_probe(old_tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); ret = -EEXIST; } else { ret = append_trace_uprobe(tu, old_tu); } goto end; } ret = register_uprobe_event(tu); if (ret) { if (ret == -EEXIST) { trace_probe_log_set_index(0); trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); goto end; } dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); end: mutex_unlock(&event_mutex); return ret; } /* * Argument syntax: * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS] */ static int __trace_uprobe_create(int argc, const char **argv) { struct trace_uprobe *tu; const char *event = NULL, *group = UPROBE_EVENT_SYSTEM; char *arg, *filename, *rctr, *rctr_end, *tmp; char buf[MAX_EVENT_NAME_LEN]; enum probe_print_type ptype; struct path path; unsigned long offset, ref_ctr_offset; bool is_return = false; int i, ret; ret = 0; ref_ctr_offset = 0; switch (argv[0][0]) { case 'r': is_return = true; break; case 'p': break; default: return -ECANCELED; } if (argc < 2) return -ECANCELED; if (argv[0][1] == ':') event = &argv[0][2]; if (!strchr(argv[1], '/')) return -ECANCELED; filename = kstrdup(argv[1], GFP_KERNEL); if (!filename) return -ENOMEM; /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(filename, ':'); if (!arg || !isdigit(arg[1])) { kfree(filename); return -ECANCELED; } trace_probe_log_init("trace_uprobe", argc, argv); trace_probe_log_set_index(1); /* filename is the 2nd argument */ *arg++ = '\0'; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) { trace_probe_log_err(0, FILE_NOT_FOUND); kfree(filename); trace_probe_log_clear(); return ret; } if (!d_is_reg(path.dentry)) { trace_probe_log_err(0, NO_REGULAR_FILE); ret = -EINVAL; goto fail_address_parse; } /* Parse reference counter offset if specified. */ rctr = strchr(arg, '('); if (rctr) { rctr_end = strchr(rctr, ')'); if (!rctr_end) { ret = -EINVAL; rctr_end = rctr + strlen(rctr); trace_probe_log_err(rctr_end - filename, REFCNT_OPEN_BRACE); goto fail_address_parse; } else if (rctr_end[1] != '\0') { ret = -EINVAL; trace_probe_log_err(rctr_end + 1 - filename, BAD_REFCNT_SUFFIX); goto fail_address_parse; } *rctr++ = '\0'; *rctr_end = '\0'; ret = kstrtoul(rctr, 0, &ref_ctr_offset); if (ret) { trace_probe_log_err(rctr - filename, BAD_REFCNT); goto fail_address_parse; } } /* Check if there is %return suffix */ tmp = strchr(arg, '%'); if (tmp) { if (!strcmp(tmp, "%return")) { *tmp = '\0'; is_return = true; } else { trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX); ret = -EINVAL; goto fail_address_parse; } } /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) { trace_probe_log_err(arg - filename, BAD_UPROBE_OFFS); goto fail_address_parse; } /* setup a probe */ trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, buf, event - argv[0]); if (ret) goto fail_address_parse; } else { char *tail; char *ptr; tail = kstrdup(kbasename(filename), GFP_KERNEL); if (!tail) { ret = -ENOMEM; goto fail_address_parse; } ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); event = buf; kfree(tail); } argc -= 2; argv += 2; tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { ret = PTR_ERR(tu); /* This must return -ENOMEM otherwise there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); goto fail_address_parse; } tu->offset = offset; tu->ref_ctr_offset = ref_ctr_offset; tu->path = path; tu->filename = filename; /* parse arguments */ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { trace_probe_log_set_index(i + 2); ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i], is_return ? TPARG_FL_RETURN : 0); if (ret) goto error; } ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tu->tp, ptype); if (ret < 0) goto error; ret = register_trace_uprobe(tu); if (!ret) goto out; error: free_trace_uprobe(tu); out: trace_probe_log_clear(); return ret; fail_address_parse: trace_probe_log_clear(); path_put(&path); kfree(filename); return ret; } int trace_uprobe_create(const char *raw_command) { return trace_probe_create(raw_command, __trace_uprobe_create); } static int create_or_delete_trace_uprobe(const char *raw_command) { int ret; if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_uprobe_ops); ret = trace_uprobe_create(raw_command); return ret == -ECANCELED ? -EINVAL : ret; } static int trace_uprobe_release(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return unregister_trace_uprobe(tu); } /* Probes listing interfaces */ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); char c = is_ret_probe(tu) ? 'r' : 'p'; int i; seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, trace_probe_group_name(&tu->tp), trace_probe_name(&tu->tp), tu->filename, (int)(sizeof(void *) * 2), tu->offset); if (tu->ref_ctr_offset) seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); seq_putc(m, '\n'); return 0; } static int probes_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; if (!is_trace_uprobe(ev)) return 0; return trace_uprobe_show(m, ev); } static const struct seq_operations probes_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_seq_show }; static int probes_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) return ret; } return seq_open(file, &probes_seq_op); } static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return trace_parse_run_command(file, buffer, count, ppos, create_or_delete_trace_uprobe); } static const struct file_operations uprobe_events_ops = { .owner = THIS_MODULE, .open = probes_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, .write = probes_write, }; /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; struct trace_uprobe *tu; if (!is_trace_uprobe(ev)) return 0; tu = to_trace_uprobe(ev); seq_printf(m, " %s %-44s %15lu\n", tu->filename, trace_probe_name(&tu->tp), tu->nhit); return 0; } static const struct seq_operations profile_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; static int profile_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; return seq_open(file, &profile_seq_op); } static const struct file_operations uprobe_profile_ops = { .owner = THIS_MODULE, .open = profile_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; struct uprobe_cpu_buffer { struct mutex mutex; void *buf; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; static int uprobe_buffer_init(void) { int cpu, err_cpu; uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer); if (uprobe_cpu_buffer == NULL) return -ENOMEM; for_each_possible_cpu(cpu) { struct page *p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); if (p == NULL) { err_cpu = cpu; goto err; } per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p); mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex); } return 0; err: for_each_possible_cpu(cpu) { if (cpu == err_cpu) break; free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); } free_percpu(uprobe_cpu_buffer); return -ENOMEM; } static int uprobe_buffer_enable(void) { int ret = 0; BUG_ON(!mutex_is_locked(&event_mutex)); if (uprobe_buffer_refcnt++ == 0) { ret = uprobe_buffer_init(); if (ret < 0) uprobe_buffer_refcnt--; } return ret; } static void uprobe_buffer_disable(void) { int cpu; BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { for_each_possible_cpu(cpu) free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } } static struct uprobe_cpu_buffer *uprobe_buffer_get(void) { struct uprobe_cpu_buffer *ucb; int cpu; cpu = raw_smp_processor_id(); ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu); /* * Use per-cpu buffers for fastest access, but we might migrate * so the mutex makes sure we have sole access to it. */ mutex_lock(&ucb->mutex); return ucb; } static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) { mutex_unlock(&ucb->mutex); } static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_buffer *buffer; struct ring_buffer_event *event; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) return; if (trace_trigger_soft_disabled(trace_file)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; event = trace_event_buffer_lock_reserve(&buffer, trace_file, call->event.type, size, 0); if (!event) return; entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, tu->tp.size + dsize); event_trigger_unlock_commit(trace_file, buffer, event, entry, 0); } /* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct event_file_link *link; if (is_ret_probe(tu)) return 0; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); rcu_read_unlock(); return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct event_file_link *link; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); rcu_read_unlock(); } /* Event entry printers */ static enum print_line_t print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { struct uprobe_trace_entry_head *entry; struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; entry = (struct uprobe_trace_entry_head *)iter->ent; tu = trace_uprobe_primary_from_call( container_of(event, struct trace_event_call, event)); if (unlikely(!tu)) goto out; if (is_ret_probe(tu)) { trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[1], entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, true); } else { trace_seq_printf(s, "%s: (0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, false); } if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) goto out; trace_seq_putc(s, '\n'); out: return trace_handle_return(s); } typedef bool (*filter_func_t)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { int ret; tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); if (tu->ref_ctr_offset) ret = uprobe_register_refctr(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); else ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) tu->inode = NULL; return ret; } static void __probe_event_disable(struct trace_probe *tp) { struct trace_probe *pos; struct trace_uprobe *tu; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } } static int probe_event_enable(struct trace_event_call *call, struct trace_event_file *file, filter_func_t filter) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; bool enabled; int ret; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; enabled = trace_probe_is_enabled(tp); /* This may also change "enabled" state */ if (file) { if (trace_probe_test_flag(tp, TP_FLAG_PROFILE)) return -EINTR; ret = trace_probe_add_file(tp, file); if (ret < 0) return ret; } else { if (trace_probe_test_flag(tp, TP_FLAG_TRACE)) return -EINTR; trace_probe_set_flag(tp, TP_FLAG_PROFILE); } tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; ret = uprobe_buffer_enable(); if (ret) goto err_flags; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); ret = trace_uprobe_enable(tu, filter); if (ret) { __probe_event_disable(tp); goto err_buffer; } } return 0; err_buffer: uprobe_buffer_disable(); err_flags: if (file) trace_probe_remove_file(tp, file); else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); return ret; } static void probe_event_disable(struct trace_event_call *call, struct trace_event_file *file) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return; if (!trace_probe_is_enabled(tp)) return; if (file) { if (trace_probe_remove_file(tp, file) < 0) return; if (trace_probe_is_enabled(tp)) return; } else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); __probe_event_disable(tp); uprobe_buffer_disable(); } static int uprobe_event_define_fields(struct trace_event_call *event_call) { int ret, size; struct uprobe_trace_entry_head field; struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); if (unlikely(!tu)) return -ENODEV; if (is_ret_probe(tu)) { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); size = SIZEOF_TRACE_ENTRY(true); } else { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); size = SIZEOF_TRACE_ENTRY(false); } return traceprobe_define_arg_fields(event_call, size, &tu->tp); } #ifdef CONFIG_PERF_EVENTS static bool __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { struct perf_event *event; if (filter->nr_systemwide) return true; list_for_each_entry(event, &filter->perf_events, hw.tp_list) { if (event->hw.target->mm == mm) return true; } return false; } static inline bool trace_uprobe_filter_event(struct trace_uprobe_filter *filter, struct perf_event *event) { return __uprobe_perf_filter(filter, event->hw.target->mm); } static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || trace_uprobe_filter_event(filter, event); } else { filter->nr_systemwide--; done = filter->nr_systemwide; } write_unlock(&filter->rwlock); return done; } /* This returns true if the filter always covers target mm */ static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely * on dup_mmap() which preserves the already installed bp's. * * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || trace_uprobe_filter_event(filter, event); list_add(&event->hw.tp_list, &filter->perf_events); } else { done = filter->nr_systemwide; filter->nr_systemwide++; } write_unlock(&filter->rwlock); return done; } static int uprobe_perf_close(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; int ret = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } static int uprobe_perf_open(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; int err = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_add(tu->tp.event->filter, event)) return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; } } return err; } static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); filter = tu->tp.event->filter; read_lock(&filter->rwlock); ret = __uprobe_perf_filter(filter, mm); read_unlock(&filter->rwlock); return ret; } static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; struct hlist_head *head; void *data; int size, esize; int rctx; if (bpf_prog_array_valid(call)) { u32 ret; preempt_disable(); ret = trace_call_bpf(call, regs); preempt_enable(); if (!ret) return; } esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; preempt_disable(); head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) goto out; entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) goto out; if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, tu->tp.size + dsize); if (size - esize > tu->tp.size + dsize) { int len = tu->tp.size + dsize; memset(data + len, 0, size - esize - len); } perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); out: preempt_enable(); } /* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) __uprobe_perf_func(tu, 0, regs, ucb, dsize); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { __uprobe_perf_func(tu, func, regs, ucb, dsize); } int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, u64 *probe_addr, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; struct trace_uprobe *tu; if (perf_type_tracepoint) tu = find_probe_event(pevent, group); else tu = trace_uprobe_primary_from_call(event->tp_event); if (!tu) return -EINVAL; *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; *probe_addr = 0; return 0; } #endif /* CONFIG_PERF_EVENTS */ static int trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, void *data) { struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: return probe_event_enable(event, file, NULL); case TRACE_REG_UNREGISTER: probe_event_disable(event, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: return probe_event_enable(event, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: probe_event_disable(event, NULL); return 0; case TRACE_REG_PERF_OPEN: return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: return uprobe_perf_close(event, data); #endif default: return 0; } } static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; int dsize, esize; int ret = 0; tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; udd.tu = tu; udd.bp_addr = instruction_pointer(regs); current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); return ret; } static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; int dsize, esize; tu = container_of(con, struct trace_uprobe, consumer); udd.tu = tu; udd.bp_addr = func; current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) uretprobe_trace_func(tu, func, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) uretprobe_perf_func(tu, func, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); return 0; } static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; static struct trace_event_fields uprobe_fields_array[] = { { .type = TRACE_FUNCTION_TYPE, .define_fields = uprobe_event_define_fields }, {} }; static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); call->event.funcs = &uprobe_funcs; call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; } static int register_uprobe_event(struct trace_uprobe *tu) { init_trace_event_call(tu); return trace_probe_register_event_call(&tu->tp); } static int unregister_uprobe_event(struct trace_uprobe *tu) { return trace_probe_unregister_event_call(&tu->tp); } #ifdef CONFIG_PERF_EVENTS struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, unsigned long ref_ctr_offset, bool is_return) { enum probe_print_type ptype; struct trace_uprobe *tu; struct path path; int ret; ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); if (!d_is_reg(path.dentry)) { path_put(&path); return ERR_PTR(-EINVAL); } /* * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of * duplicated name "DUMMY_EVENT" here. */ tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0, is_return); if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); path_put(&path); return ERR_CAST(tu); } tu->offset = offs; tu->path = path; tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); if (!tu->filename) { ret = -ENOMEM; goto error; } init_trace_event_call(tu); ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; if (traceprobe_set_print_fmt(&tu->tp, ptype) < 0) { ret = -ENOMEM; goto error; } return trace_probe_event_call(&tu->tp); error: free_trace_uprobe(tu); return ERR_PTR(ret); } void destroy_local_trace_uprobe(struct trace_event_call *event_call) { struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); free_trace_uprobe(tu); } #endif /* CONFIG_PERF_EVENTS */ /* Make a trace interface for controlling probe points */ static __init int init_uprobe_trace(void) { int ret; ret = dyn_event_register(&trace_uprobe_ops); if (ret) return ret; ret = tracing_init_dentry(); if (ret) return 0; trace_create_file("uprobe_events", TRACE_MODE_WRITE, NULL, NULL, &uprobe_events_ops); /* Profile interface */ trace_create_file("uprobe_profile", TRACE_MODE_READ, NULL, NULL, &uprobe_profile_ops); return 0; } fs_initcall(init_uprobe_trace); |
| 55 107 107 102 102 15 4 11 15 330 30 641 601 603 600 6 51 5 46 51 229 229 769 766 500 280 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/l3mdev.h - L3 master device API * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ #include <net/dst.h> #include <net/fib_rules.h> enum l3mdev_type { L3MDEV_TYPE_UNSPEC, L3MDEV_TYPE_VRF, __L3MDEV_TYPE_MAX }; #define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1) typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d); /** * struct l3mdev_ops - l3mdev operations * * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_l3_rcv: Hook in L3 receive path * * @l3mdev_l3_out: Hook in L3 output path * * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, struct sock *sk, struct sk_buff *skb, u16 proto); /* IPv6 ops */ struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id); int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; rcu_read_lock(); ifindex = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); return ifindex; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { struct net_device *dev; int rc = 0; if (likely(ifindex)) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); } return rc; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; struct net_device *master; if (!dev) return NULL; if (netif_is_l3_master(dev)) master = dev; else if (netif_is_l3_slave(dev)) master = netdev_master_upper_dev_get_rcu(dev); else master = NULL; return master; } int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { rcu_read_lock(); ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); rcu_read_unlock(); return ifindex; } u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) { u32 tb_id; rcu_read_lock(); tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; bool rc = false; if (ifindex == 0) return false; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_l3_master(dev); rcu_read_unlock(); return rc; } struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) { struct net_device *master = NULL; if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); else if (netif_is_l3_master(skb->dev) || netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto); return skb; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET6); } static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { struct net_device *dev = skb_dst(skb)->dev; if (netif_is_l3_slave(dev)) { struct net_device *master; master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); } return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET6); } #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex(struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { return 0; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } static inline struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { return NULL; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { return -EOPNOTSUPP; } static inline void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { } static inline int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { return -ENODEV; } static inline int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { return 1; } static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { } #endif #endif /* _NET_L3MDEV_H_ */ |
| 11 2 10 32 32 32 18 18 10 20 10 10 1 19 12 11 11 11 5 24 25 5 20 20 20 10 10 10 10 3 10 5 3 5 20 5 9 6 41 42 42 42 39 5 2 6 31 35 30 32 6 14 32 32 2 28 28 28 14 7 5 19 3 2 19 1 9 11 4 2 2 3 6 1 1 1 3 1 1 2 1 32 31 5 32 15 1 2 9 9 9 9 2 3 15 5 5 5 5 2 3 5 5 4 2 1 2 39 1 20 7 2 1 7 16 16 16 18 18 18 2 16 18 18 18 18 16 4 18 2 18 18 33 24 9 2 25 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel Connection Multiplexor * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/file.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> #include <linux/syscalls.h> #include <linux/sched/signal.h> #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> #include <uapi/linux/kcm.h> unsigned int kcm_net_id; static struct kmem_cache *kcm_psockp __read_mostly; static struct kmem_cache *kcm_muxp __read_mostly; static struct workqueue_struct *kcm_wq; static inline struct kcm_sock *kcm_sk(const struct sock *sk) { return (struct kcm_sock *)sk; } static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) { return (struct kcm_tx_msg *)skb->cb; } static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, bool wakeup_kcm) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; /* Unrecoverable error in transmit */ spin_lock_bh(&mux->lock); if (psock->tx_stopped) { spin_unlock_bh(&mux->lock); return; } psock->tx_stopped = 1; KCM_STATS_INCR(psock->stats.tx_aborts); if (!psock->tx_kcm) { /* Take off psocks_avail list */ list_del(&psock->psock_avail_list); } else if (wakeup_kcm) { /* In this case psock is being aborted while outside of * write_msgs and psock is reserved. Schedule tx_work * to handle the failure there. Need to commit tx_stopped * before queuing work. */ smp_mb(); queue_work(kcm_wq, &psock->tx_kcm->tx_work); } spin_unlock_bh(&mux->lock); /* Report error on lower socket */ report_csk_error(csk, err); } /* RX mux lock held. */ static void kcm_update_rx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { STRP_STATS_ADD(mux->stats.rx_bytes, psock->strp.stats.bytes - psock->saved_rx_bytes); mux->stats.rx_msgs += psock->strp.stats.msgs - psock->saved_rx_msgs; psock->saved_rx_msgs = psock->strp.stats.msgs; psock->saved_rx_bytes = psock->strp.stats.bytes; } static void kcm_update_tx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { KCM_STATS_ADD(mux->stats.tx_bytes, psock->stats.tx_bytes - psock->saved_tx_bytes); mux->stats.tx_msgs += psock->stats.tx_msgs - psock->saved_tx_msgs; psock->saved_tx_msgs = psock->stats.tx_msgs; psock->saved_tx_bytes = psock->stats.tx_bytes; } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); /* KCM is ready to receive messages on its queue-- either the KCM is new or * has become unblocked after being blocked on full socket buffer. Queue any * pending ready messages on a psock. RX mux lock held. */ static void kcm_rcv_ready(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct sk_buff *skb; if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) return; while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Assuming buffer limit has been reached */ skb_queue_head(&mux->rx_hold_queue, skb); WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } } while (!list_empty(&mux->psocks_ready)) { psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, psock_ready_list); if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { /* Assuming buffer limit has been reached */ WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } /* Consumed the ready message on the psock. Schedule rx_work to * get more messages. */ list_del(&psock->psock_ready_list); psock->ready_rx_msg = NULL; /* Commit clearing of ready_rx_msg for queuing work */ smp_mb(); strp_unpause(&psock->strp); strp_check_rcv(&psock->strp); } /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct kcm_sock *kcm = kcm_sk(sk); struct kcm_mux *mux = kcm->mux; unsigned int len = skb->truesize; sk_mem_uncharge(sk, len); atomic_sub(len, &sk->sk_rmem_alloc); /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) return -ENOMEM; if (!sk_rmem_schedule(sk, skb, skb->truesize)) return -ENOBUFS; skb->dev = NULL; skb_orphan(skb); skb->sk = sk; skb->destructor = kcm_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); skb_queue_tail(list, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } /* Requeue received messages for a kcm socket to other kcm sockets. This is * called with a kcm socket is receive disabled. * RX mux lock held. */ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) { struct sk_buff *skb; struct kcm_sock *kcm; while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); try_again: if (list_empty(&mux->kcm_rx_waiters)) { skb_queue_tail(&mux->rx_hold_queue, skb); continue; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); goto try_again; } } } /* Lower sock lock held */ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, struct sk_buff *head) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; WARN_ON(psock->ready_rx_msg); if (psock->rx_kcm) return psock->rx_kcm; spin_lock_bh(&mux->rx_lock); if (psock->rx_kcm) { spin_unlock_bh(&mux->rx_lock); return psock->rx_kcm; } kcm_update_rx_mux_stats(mux, psock); if (list_empty(&mux->kcm_rx_waiters)) { psock->ready_rx_msg = head; strp_pause(&psock->strp); list_add_tail(&psock->psock_ready_list, &mux->psocks_ready); spin_unlock_bh(&mux->rx_lock); return NULL; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); return kcm; } static void kcm_done(struct kcm_sock *kcm); static void kcm_done_work(struct work_struct *w) { kcm_done(container_of(w, struct kcm_sock, done_work)); } /* Lower sock held */ static void unreserve_rx_kcm(struct kcm_psock *psock, bool rcv_ready) { struct kcm_sock *kcm = psock->rx_kcm; struct kcm_mux *mux = psock->mux; if (!kcm) return; spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree */ smp_mb(); if (unlikely(kcm->done)) { spin_unlock_bh(&mux->rx_lock); /* Need to run kcm_done in a task since we need to qcquire * callback locks which may already be held here. */ INIT_WORK(&kcm->done_work, kcm_done_work); schedule_work(&kcm->done_work); return; } if (unlikely(kcm->rx_disabled)) { requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { /* Check for degenerative race with rx_wait that all * data was dequeued (accounted for in kcm_rfree). */ kcm_rcv_ready(kcm); } spin_unlock_bh(&mux->rx_lock); } /* Lower sock lock held */ static void psock_data_ready(struct sock *sk) { struct kcm_psock *psock; read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (likely(psock)) strp_data_ready(&psock->strp); read_unlock_bh(&sk->sk_callback_lock); } /* Called with lower sock held */ static void kcm_rcv_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct kcm_sock *kcm; try_queue: kcm = reserve_rx_kcm(psock, skb); if (!kcm) { /* Unable to reserve a KCM, message is held in psock and strp * is paused. */ return; } if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ unreserve_rx_kcm(psock, false); goto try_queue; } } static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct bpf_prog *prog = psock->bpf_prog; int res; res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } static int kcm_read_sock_done(struct strparser *strp, int err) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); unreserve_rx_kcm(psock, true); return err; } static void psock_state_change(struct sock *sk) { /* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here * since application will normally not poll with EPOLLIN * on the TCP sockets. */ report_csk_error(sk, EPIPE); } static void psock_write_space(struct sock *sk) { struct kcm_psock *psock; struct kcm_mux *mux; struct kcm_sock *kcm; read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (unlikely(!psock)) goto out; mux = psock->mux; spin_lock_bh(&mux->lock); /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; if (kcm && !unlikely(kcm->tx_stopped)) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); out: read_unlock_bh(&sk->sk_callback_lock); } static void unreserve_psock(struct kcm_sock *kcm); /* kcm sock is locked. */ static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; psock = kcm->tx_psock; smp_rmb(); /* Must read tx_psock before tx_wait */ if (psock) { WARN_ON(kcm->tx_wait); if (unlikely(psock->tx_stopped)) unreserve_psock(kcm); else return kcm->tx_psock; } spin_lock_bh(&mux->lock); /* Check again under lock to see if psock was reserved for this * psock via psock_unreserve. */ psock = kcm->tx_psock; if (unlikely(psock)) { WARN_ON(kcm->tx_wait); spin_unlock_bh(&mux->lock); return kcm->tx_psock; } if (!list_empty(&mux->psocks_avail)) { psock = list_first_entry(&mux->psocks_avail, struct kcm_psock, psock_avail_list); list_del(&psock->psock_avail_list); if (kcm->tx_wait) { list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } kcm->tx_psock = psock; psock->tx_kcm = kcm; KCM_STATS_INCR(psock->stats.reserved); } else if (!kcm->tx_wait) { list_add_tail(&kcm->wait_psock_list, &mux->kcm_tx_waiters); kcm->tx_wait = true; } spin_unlock_bh(&mux->lock); return psock; } /* mux lock held */ static void psock_now_avail(struct kcm_psock *psock) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; if (list_empty(&mux->kcm_tx_waiters)) { list_add_tail(&psock->psock_avail_list, &mux->psocks_avail); } else { kcm = list_first_entry(&mux->kcm_tx_waiters, struct kcm_sock, wait_psock_list); list_del(&kcm->wait_psock_list); kcm->tx_wait = false; psock->tx_kcm = kcm; /* Commit before changing tx_psock since that is read in * reserve_psock before queuing work. */ smp_mb(); kcm->tx_psock = psock; KCM_STATS_INCR(psock->stats.reserved); queue_work(kcm_wq, &kcm->tx_work); } } /* kcm sock is locked. */ static void unreserve_psock(struct kcm_sock *kcm) { struct kcm_psock *psock; struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); psock = kcm->tx_psock; if (WARN_ON(!psock)) { spin_unlock_bh(&mux->lock); return; } smp_rmb(); /* Read tx_psock before tx_wait */ kcm_update_tx_mux_stats(mux, psock); WARN_ON(kcm->tx_wait); kcm->tx_psock = NULL; psock->tx_kcm = NULL; KCM_STATS_INCR(psock->stats.unreserved); if (unlikely(psock->tx_stopped)) { if (psock->done) { /* Deferred free */ list_del(&psock->psock_list); mux->psocks_cnt--; sock_put(psock->sk); fput(psock->sk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } /* Don't put back on available list */ spin_unlock_bh(&mux->lock); return; } psock_now_avail(psock); spin_unlock_bh(&mux->lock); } static void kcm_report_tx_retry(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); KCM_STATS_INCR(mux->stats.tx_retries); spin_unlock_bh(&mux->lock); } /* Write any messages ready on the kcm socket. Called with kcm sock lock * held. Return bytes actually sent or error. */ static int kcm_write_msgs(struct kcm_sock *kcm) { struct sock *sk = &kcm->sk; struct kcm_psock *psock; struct sk_buff *skb, *head; struct kcm_tx_msg *txm; unsigned short fragidx, frag_offset; unsigned int sent, total_sent = 0; int ret = 0; kcm->tx_wait_more = false; psock = kcm->tx_psock; if (unlikely(psock && psock->tx_stopped)) { /* A reserved psock was aborted asynchronously. Unreserve * it and we'll retry the message. */ unreserve_psock(kcm); kcm_report_tx_retry(kcm); if (skb_queue_empty(&sk->sk_write_queue)) return 0; kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0; } else if (skb_queue_empty(&sk->sk_write_queue)) { return 0; } head = skb_peek(&sk->sk_write_queue); txm = kcm_tx_msg(head); if (txm->sent) { /* Send of first skbuff in queue already in progress */ if (WARN_ON(!psock)) { ret = -EINVAL; goto out; } sent = txm->sent; frag_offset = txm->frag_offset; fragidx = txm->fragidx; skb = txm->frag_skb; goto do_frag; } try_again: psock = reserve_psock(kcm); if (!psock) goto out; do { skb = head; txm = kcm_tx_msg(head); sent = 0; do_frag_list: if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { ret = -EINVAL; goto out; } for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag; frag_offset = 0; do_frag: frag = &skb_shinfo(skb)->frags[fragidx]; if (WARN_ON(!skb_frag_size(frag))) { ret = -EINVAL; goto out; } ret = kernel_sendpage(psock->sk->sk_socket, skb_frag_page(frag), skb_frag_off(frag) + frag_offset, skb_frag_size(frag) - frag_offset, MSG_DONTWAIT); if (ret <= 0) { if (ret == -EAGAIN) { /* Save state to try again when there's * write space on the socket */ txm->sent = sent; txm->frag_offset = frag_offset; txm->fragidx = fragidx; txm->frag_skb = skb; ret = 0; goto out; } /* Hard failure in sending message, abort this * psock since it has lost framing * synchronization and retry sending the * message from the beginning. */ kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, true); unreserve_psock(kcm); txm->sent = 0; kcm_report_tx_retry(kcm); ret = 0; goto try_again; } sent += ret; frag_offset += ret; KCM_STATS_ADD(psock->stats.tx_bytes, ret); if (frag_offset < skb_frag_size(frag)) { /* Not finished with this frag */ goto do_frag; } } if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } /* Successfully sent the whole packet, account for it. */ skb_dequeue(&sk->sk_write_queue); kfree_skb(head); sk->sk_wmem_queued -= sent; total_sent += sent; KCM_STATS_INCR(psock->stats.tx_msgs); } while ((head = skb_peek(&sk->sk_write_queue))); out: if (!head) { /* Done with all queued messages. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); unreserve_psock(kcm); } /* Check if write space is available */ sk->sk_write_space(sk); return total_sent ? : ret; } static void kcm_tx_work(struct work_struct *w) { struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); struct sock *sk = &kcm->sk; int err; lock_sock(sk); /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx * aborts */ err = kcm_write_msgs(kcm); if (err < 0) { /* Hard failure in write, report error on KCM socket */ pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); report_csk_error(&kcm->sk, -err); goto out; } /* Primarily for SOCK_SEQPACKET sockets */ if (likely(sk->sk_socket) && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_space(sk); } out: release_sock(sk); } static void kcm_push(struct kcm_sock *kcm) { if (kcm->tx_wait_more) kcm_write_msgs(kcm); } static ssize_t kcm_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct sk_buff *skb = NULL, *head = NULL; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); bool eor; int err = 0; int i; if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; /* No MSG_EOR from splice, only look at MSG_MORE */ eor = !(flags & MSG_MORE); lock_sock(sk); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); err = -EPIPE; if (sk->sk_err) goto out_error; if (kcm->seq_skb) { /* Previously opened message */ head = kcm->seq_skb; skb = kcm_tx_msg(head)->last_skb; i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; goto coalesced; } if (i >= MAX_SKB_FRAGS) { struct sk_buff *tskb; tskb = alloc_skb(0, sk->sk_allocation); while (!tskb) { kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (head == skb) skb_shinfo(head)->frag_list = tskb; else skb->next = tskb; skb = tskb; skb->ip_summed = CHECKSUM_UNNECESSARY; i = 0; } } else { /* Call the sk_stream functions to manage the sndbuf mem. */ if (!sk_stream_memory_free(sk)) { kcm_push(kcm); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } head = alloc_skb(0, sk->sk_allocation); while (!head) { kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } skb = head; i = 0; } get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; coalesced: skb->len += size; skb->data_len += size; skb->truesize += size; sk->sk_wmem_queued += size; sk_mem_charge(sk, size); if (head != skb) { head->len += size; head->data_len += size; head->truesize += size; } if (eor) { bool not_busy = skb_queue_empty(&sk->sk_write_queue); /* Message complete, queue it on send buffer */ __skb_queue_tail(&sk->sk_write_queue, head); kcm->seq_skb = NULL; KCM_STATS_INCR(kcm->stats.tx_msgs); if (flags & MSG_BATCH) { kcm->tx_wait_more = true; } else if (kcm->tx_wait_more || not_busy) { err = kcm_write_msgs(kcm); if (err < 0) { /* We got a hard error in write_msgs but have * already queued this message. Report an error * in the socket, but don't affect return value * from sendmsg */ pr_warn("KCM: Hard failure on kcm_write_msgs\n"); report_csk_error(&kcm->sk, -err); } } } else { /* Message not complete, save state */ kcm->seq_skb = head; kcm_tx_msg(head)->last_skb = skb; } KCM_STATS_ADD(kcm->stats.tx_bytes, size); release_sock(sk); return size; out_error: kcm_push(kcm); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) sk->sk_write_space(sk); release_sock(sk); return err; } static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct sk_buff *skb = NULL, *head = NULL; size_t copy, copied = 0; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); int eor = (sock->type == SOCK_DGRAM) ? !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err) goto out_error; if (kcm->seq_skb) { /* Previously opened message */ head = kcm->seq_skb; skb = kcm_tx_msg(head)->last_skb; goto start; } /* Call the sk_stream functions to manage the sndbuf mem. */ if (!sk_stream_memory_free(sk)) { kcm_push(kcm); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (msg_data_left(msg)) { /* New message, alloc head skb */ head = alloc_skb(0, sk->sk_allocation); while (!head) { kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; head = alloc_skb(0, sk->sk_allocation); } skb = head; /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling * csum_and_copy_from_iter from skb_do_copy_data_nocache. */ skb->ip_summed = CHECKSUM_UNNECESSARY; } start: while (msg_data_left(msg)) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_memory; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i == MAX_SKB_FRAGS) { struct sk_buff *tskb; tskb = alloc_skb(0, sk->sk_allocation); if (!tskb) goto wait_for_memory; if (head == skb) skb_shinfo(head)->frag_list = tskb; else skb->next = tskb; skb = tskb; skb->ip_summed = CHECKSUM_UNNECESSARY; continue; } merge = false; } copy = min_t(int, msg_data_left(msg), pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto out_error; /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); get_page(pfrag->page); } pfrag->offset += copy; copied += copy; if (head != skb) { head->len += copy; head->data_len += copy; } continue; wait_for_memory: kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (eor) { bool not_busy = skb_queue_empty(&sk->sk_write_queue); if (head) { /* Message complete, queue it on send buffer */ __skb_queue_tail(&sk->sk_write_queue, head); kcm->seq_skb = NULL; KCM_STATS_INCR(kcm->stats.tx_msgs); } if (msg->msg_flags & MSG_BATCH) { kcm->tx_wait_more = true; } else if (kcm->tx_wait_more || not_busy) { err = kcm_write_msgs(kcm); if (err < 0) { /* We got a hard error in write_msgs but have * already queued this message. Report an error * in the socket, but don't affect return value * from sendmsg */ pr_warn("KCM: Hard failure on kcm_write_msgs\n"); report_csk_error(&kcm->sk, -err); } } } else { /* Message not complete, save state */ partial_message: if (head) { kcm->seq_skb = head; kcm_tx_msg(head)->last_skb = skb; } } KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); mutex_unlock(&kcm->tx_mutex); return copied; out_error: kcm_push(kcm); if (sock->type == SOCK_SEQPACKET) { /* Wrote some bytes before encountering an * error, return partial success. */ if (copied) goto partial_message; if (head != kcm->seq_skb) kfree_skb(head); } else { kfree_skb(head); kcm->seq_skb = NULL; } err = sk_stream_error(sk, msg->msg_flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) sk->sk_write_space(sk); release_sock(sk); mutex_unlock(&kcm->tx_mutex); return err; } static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; err = skb_copy_datagram_msg(skb, stm->offset, msg, len); if (err < 0) goto out; copied = len; if (likely(!(flags & MSG_PEEK))) { KCM_STATS_ADD(kcm->stats.rx_bytes, copied); if (copied < stm->full_len) { if (sock->type == SOCK_DGRAM) { /* Truncated message */ msg->msg_flags |= MSG_TRUNC; goto msg_finished; } stm->offset += copied; stm->full_len -= copied; } else { msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); } } out: skb_free_datagram(sk, skb); return copied ? : err; } static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct strp_msg *stm; int err = 0; ssize_t copied; struct sk_buff *skb; /* Only support splice for SOCKSEQPACKET */ skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto err_out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; copied = skb_splice_bits(skb, sk, stm->offset, pipe, len, flags); if (copied < 0) { err = copied; goto err_out; } KCM_STATS_ADD(kcm->stats.rx_bytes, copied); stm->offset += copied; stm->full_len -= copied; /* We have no way to return MSG_EOR. If all the bytes have been * read we still leave the message in the receive socket buffer. * A subsequent recvmsg needs to be done to return MSG_EOR and * finish reading the message. */ skb_free_datagram(sk, skb); return copied; err_out: skb_free_datagram(sk, skb); return err; } /* kcm sock lock held */ static void kcm_recv_disable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 1; /* If a psock is reserved we'll do cleanup in unreserve */ if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } spin_unlock_bh(&mux->rx_lock); } /* kcm sock lock held */ static void kcm_recv_enable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (!kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 0; kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, valbool; int err = 0; if (level != SOL_KCM) return -ENOPROTOOPT; if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; valbool = val ? 1 : 0; switch (optname) { case KCM_RECV_DISABLE: lock_sock(&kcm->sk); if (valbool) kcm_recv_disable(kcm); else kcm_recv_enable(kcm); release_sock(&kcm->sk); break; default: err = -ENOPROTOOPT; } return err; } static int kcm_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, len; if (level != SOL_KCM) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) { struct kcm_sock *tkcm; struct list_head *head; int index = 0; /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so * we set sk_state, otherwise epoll_wait always returns right away with * EPOLLHUP */ kcm->sk.sk_state = TCP_ESTABLISHED; /* Add to mux's kcm sockets list */ kcm->mux = mux; spin_lock_bh(&mux->lock); head = &mux->kcm_socks; list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { if (tkcm->index != index) break; head = &tkcm->kcm_sock_list; index++; } list_add(&kcm->kcm_sock_list, head); kcm->index = index; mux->kcm_socks_cnt++; spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_attach(struct socket *sock, struct socket *csock, struct bpf_prog *prog) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct sock *csk; struct kcm_psock *psock = NULL, *tpsock; struct list_head *head; int index = 0; static const struct strp_callbacks cb = { .rcv_msg = kcm_rcv_strparser, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; int err = 0; csk = csock->sk; if (!csk) return -EINVAL; lock_sock(csk); /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || csk->sk_protocol != IPPROTO_TCP) { err = -EOPNOTSUPP; goto out; } /* Don't allow listeners or closed sockets */ if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { err = -EOPNOTSUPP; goto out; } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); if (!psock) { err = -ENOMEM; goto out; } psock->mux = mux; psock->sk = csk; psock->bpf_prog = prog; write_lock_bh(&csk->sk_callback_lock); /* Check if sk_user_data is already by KCM or someone else. * Must be done under lock to prevent race conditions. */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); err = -EALREADY; goto out; } err = strp_init(&psock->strp, csk, &cb); if (err) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); goto out; } psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; csk->sk_user_data = psock; csk->sk_data_ready = psock_data_ready; csk->sk_write_space = psock_write_space; csk->sk_state_change = psock_state_change; write_unlock_bh(&csk->sk_callback_lock); sock_hold(csk); /* Finished initialization, now add the psock to the MUX. */ spin_lock_bh(&mux->lock); head = &mux->psocks; list_for_each_entry(tpsock, &mux->psocks, psock_list) { if (tpsock->index != index) break; head = &tpsock->psock_list; index++; } list_add(&psock->psock_list, head); psock->index = index; KCM_STATS_INCR(mux->stats.psock_attach); mux->psocks_cnt++; psock_now_avail(psock); spin_unlock_bh(&mux->lock); /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); out: release_sock(csk); return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) { struct socket *csock; struct bpf_prog *prog; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; prog = bpf_prog_get_type(info->bpf_fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out; } err = kcm_attach(sock, csock, prog); if (err) { bpf_prog_put(prog); goto out; } /* Keep reference on file also */ return 0; out: sockfd_put(csock); return err; } static void kcm_unattach(struct kcm_psock *psock) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; lock_sock(csk); /* Stop getting callbacks from TCP socket. After this there should * be no way to reserve a kcm for this psock. */ write_lock_bh(&csk->sk_callback_lock); csk->sk_user_data = NULL; csk->sk_data_ready = psock->save_data_ready; csk->sk_write_space = psock->save_write_space; csk->sk_state_change = psock->save_state_change; strp_stop(&psock->strp); if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); release_sock(csk); return; } spin_lock_bh(&mux->rx_lock); /* Stop receiver activities. After this point psock should not be * able to get onto ready list either through callbacks or work. */ if (psock->ready_rx_msg) { list_del(&psock->psock_ready_list); kfree_skb(psock->ready_rx_msg); psock->ready_rx_msg = NULL; KCM_STATS_INCR(mux->stats.rx_ready_drops); } spin_unlock_bh(&mux->rx_lock); write_unlock_bh(&csk->sk_callback_lock); /* Call strp_done without sock lock */ release_sock(csk); strp_done(&psock->strp); lock_sock(csk); bpf_prog_put(psock->bpf_prog); spin_lock_bh(&mux->lock); aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); save_strp_stats(&psock->strp, &mux->aggregate_strp_stats); KCM_STATS_INCR(mux->stats.psock_unattach); if (psock->tx_kcm) { /* psock was reserved. Just mark it finished and we will clean * up in the kcm paths, we need kcm lock which can not be * acquired here. */ KCM_STATS_INCR(mux->stats.psock_unattach_rsvd); spin_unlock_bh(&mux->lock); /* We are unattaching a socket that is reserved. Abort the * socket since we may be out of sync in sending on it. We need * to do this without the mux lock. */ kcm_abort_tx_psock(psock, EPIPE, false); spin_lock_bh(&mux->lock); if (!psock->tx_kcm) { /* psock now unreserved in window mux was unlocked */ goto no_reserved; } psock->done = 1; /* Commit done before queuing work to process it */ smp_mb(); /* Queue tx work to make sure psock->done is handled */ queue_work(kcm_wq, &psock->tx_kcm->tx_work); spin_unlock_bh(&mux->lock); } else { no_reserved: if (!psock->tx_stopped) list_del(&psock->psock_avail_list); list_del(&psock->psock_list); mux->psocks_cnt--; spin_unlock_bh(&mux->lock); sock_put(csk); fput(csk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } release_sock(csk); } static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct socket *csock; struct sock *csk; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; csk = csock->sk; if (!csk) { err = -EINVAL; goto out; } err = -ENOENT; spin_lock_bh(&mux->lock); list_for_each_entry(psock, &mux->psocks, psock_list) { if (psock->sk != csk) continue; /* Found the matching psock */ if (psock->unattaching || WARN_ON(psock->done)) { err = -EALREADY; break; } psock->unattaching = 1; spin_unlock_bh(&mux->lock); /* Lower socket lock should already be held */ kcm_unattach(psock); err = 0; goto out; } spin_unlock_bh(&mux->lock); out: sockfd_put(csock); return err; } static struct proto kcm_proto = { .name = "KCM", .owner = THIS_MODULE, .obj_size = sizeof(struct kcm_sock), }; /* Clone a kcm socket. */ static struct file *kcm_clone(struct socket *osock) { struct socket *newsock; struct sock *newsk; newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); newsock->type = osock->type; newsock->ops = osock->ops; __module_get(newsock->ops->owner); newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, &kcm_proto, false); if (!newsk) { sock_release(newsock); return ERR_PTR(-ENOMEM); } sock_init_data(newsock, newsk); init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); } static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int err; switch (cmd) { case SIOCKCMATTACH: { struct kcm_attach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_attach_ioctl(sock, &info); break; } case SIOCKCMUNATTACH: { struct kcm_unattach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_unattach_ioctl(sock, &info); break; } case SIOCKCMCLONE: { struct kcm_clone info; struct file *file; info.fd = get_unused_fd_flags(0); if (unlikely(info.fd < 0)) return info.fd; file = kcm_clone(sock); if (IS_ERR(file)) { put_unused_fd(info.fd); return PTR_ERR(file); } if (copy_to_user((void __user *)arg, &info, sizeof(info))) { put_unused_fd(info.fd); fput(file); return -EFAULT; } fd_install(info.fd, file); err = 0; break; } default: err = -ENOIOCTLCMD; break; } return err; } static void free_mux(struct rcu_head *rcu) { struct kcm_mux *mux = container_of(rcu, struct kcm_mux, rcu); kmem_cache_free(kcm_muxp, mux); } static void release_mux(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; struct kcm_psock *psock, *tmp_psock; /* Release psocks */ list_for_each_entry_safe(psock, tmp_psock, &mux->psocks, psock_list) { if (!WARN_ON(psock->unattaching)) kcm_unattach(psock); } if (WARN_ON(mux->psocks_cnt)) return; __skb_queue_purge(&mux->rx_hold_queue); mutex_lock(&knet->mutex); aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &knet->aggregate_psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &knet->aggregate_strp_stats); list_del_rcu(&mux->kcm_mux_list); knet->count--; mutex_unlock(&knet->mutex); call_rcu(&mux->rcu, free_mux); } static void kcm_done(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct sock *sk = &kcm->sk; int socks_cnt; spin_lock_bh(&mux->rx_lock); if (kcm->rx_psock) { /* Cleanup in unreserve_rx_kcm */ WARN_ON(kcm->done); kcm->rx_disabled = 1; kcm->done = 1; spin_unlock_bh(&mux->rx_lock); return; } if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); spin_unlock_bh(&mux->rx_lock); if (WARN_ON(sk_rmem_alloc_get(sk))) return; /* Detach from MUX */ spin_lock_bh(&mux->lock); list_del(&kcm->kcm_sock_list); mux->kcm_socks_cnt--; socks_cnt = mux->kcm_socks_cnt; spin_unlock_bh(&mux->lock); if (!socks_cnt) { /* We are done with the mux now. */ release_mux(mux); } WARN_ON(kcm->rx_wait); sock_put(&kcm->sk); } /* Called by kcm_release to close a KCM socket. * If this is the last KCM socket on the MUX, destroy the MUX. */ static int kcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct kcm_sock *kcm; struct kcm_mux *mux; struct kcm_psock *psock; if (!sk) return 0; kcm = kcm_sk(sk); mux = kcm->mux; lock_sock(sk); sock_orphan(sk); kfree_skb(kcm->seq_skb); /* Purge queue under lock to avoid race condition with tx_work trying * to act when queue is nonempty. If tx_work runs after this point * it will just return. */ __skb_queue_purge(&sk->sk_write_queue); /* Set tx_stopped. This is checked when psock is bound to a kcm and we * get a writespace callback. This prevents further work being queued * from the callback (unbinding the psock occurs after canceling work. */ kcm->tx_stopped = 1; release_sock(sk); spin_lock_bh(&mux->lock); if (kcm->tx_wait) { /* Take of tx_wait list, after this point there should be no way * that a psock will be assigned to this kcm. */ list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } spin_unlock_bh(&mux->lock); /* Cancel work. After this point there should be no outside references * to the kcm socket. */ cancel_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; if (psock) { /* A psock was reserved, so we need to kill it since it * may already have some bytes queued from a message. We * need to do this after removing kcm from tx_wait list. */ kcm_abort_tx_psock(psock, EPIPE, false); unreserve_psock(kcm); } release_sock(sk); WARN_ON(kcm->tx_wait); WARN_ON(kcm->tx_psock); sock->sk = NULL; kcm_done(kcm); return 0; } static const struct proto_ops kcm_dgram_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .sendpage = kcm_sendpage, }; static const struct proto_ops kcm_seqpacket_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .sendpage = kcm_sendpage, .splice_read = kcm_splice_read, }; /* Create proto operation for kcm sockets */ static int kcm_create(struct net *net, struct socket *sock, int protocol, int kern) { struct kcm_net *knet = net_generic(net, kcm_net_id); struct sock *sk; struct kcm_mux *mux; switch (sock->type) { case SOCK_DGRAM: sock->ops = &kcm_dgram_ops; break; case SOCK_SEQPACKET: sock->ops = &kcm_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } if (protocol != KCMPROTO_CONNECTED) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); if (!sk) return -ENOMEM; /* Allocate a kcm mux, shared between KCM sockets */ mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); if (!mux) { sk_free(sk); return -ENOMEM; } spin_lock_init(&mux->lock); spin_lock_init(&mux->rx_lock); INIT_LIST_HEAD(&mux->kcm_socks); INIT_LIST_HEAD(&mux->kcm_rx_waiters); INIT_LIST_HEAD(&mux->kcm_tx_waiters); INIT_LIST_HEAD(&mux->psocks); INIT_LIST_HEAD(&mux->psocks_ready); INIT_LIST_HEAD(&mux->psocks_avail); mux->knet = knet; /* Add new MUX to list */ mutex_lock(&knet->mutex); list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); knet->count++; mutex_unlock(&knet->mutex); skb_queue_head_init(&mux->rx_hold_queue); /* Init KCM socket */ sock_init_data(sock, sk); init_kcm_sock(kcm_sk(sk), mux); return 0; } static const struct net_proto_family kcm_family_ops = { .family = PF_KCM, .create = kcm_create, .owner = THIS_MODULE, }; static __net_init int kcm_init_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); INIT_LIST_HEAD_RCU(&knet->mux_list); mutex_init(&knet->mutex); return 0; } static __net_exit void kcm_exit_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); /* All KCM sockets should be closed at this point, which should mean * that all multiplexors and psocks have been destroyed. */ WARN_ON(!list_empty(&knet->mux_list)); mutex_destroy(&knet->mutex); } static struct pernet_operations kcm_net_ops = { .init = kcm_init_net, .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), }; static int __init kcm_init(void) { int err = -ENOMEM; kcm_muxp = kmem_cache_create("kcm_mux_cache", sizeof(struct kcm_mux), 0, SLAB_HWCACHE_ALIGN, NULL); if (!kcm_muxp) goto fail; kcm_psockp = kmem_cache_create("kcm_psock_cache", sizeof(struct kcm_psock), 0, SLAB_HWCACHE_ALIGN, NULL); if (!kcm_psockp) goto fail; kcm_wq = create_singlethread_workqueue("kkcmd"); if (!kcm_wq) goto fail; err = proto_register(&kcm_proto, 1); if (err) goto fail; err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail; err = sock_register(&kcm_family_ops); if (err) goto sock_register_fail; err = kcm_proc_init(); if (err) goto proc_init_fail; return 0; proc_init_fail: sock_unregister(PF_KCM); sock_register_fail: unregister_pernet_device(&kcm_net_ops); net_ops_fail: proto_unregister(&kcm_proto); fail: kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); if (kcm_wq) destroy_workqueue(kcm_wq); return err; } static void __exit kcm_exit(void) { kcm_proc_exit(); sock_unregister(PF_KCM); unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq); kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); } module_init(kcm_init); module_exit(kcm_exit); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KCM); |
| 78 8 6380 941 3 7 279 367 63 100 519 31 199 424 486 38 476 137 17 109 12 4 24 24 18 15 165 321 132 23 5 4 2 5 4 89 41 49 24 21 44 44 90 132 82 464 513 517 2 2 118 564 559 363 363 363 363 44 179 178 179 4 4 4 257 256 256 11 18 21 291 44 6 38 331 331 15 50 35 28 7 35 1 363 361 24 3010 3402 160 3007 4 46 21 26 11 23 23 7 17 722 724 3 7 1 713 3 710 3 711 164 521 491 99 46 356 7 798 76 41 784 720 3 5 8 23 15 8 1 18 355 13 113 1 1 3 1 107 5 100 105 71 34 108 378 1 13 1 373 368 356 369 366 364 370 99 1 6 1 6 86 8 83 83 93 150 1 6 2 23 1 122 142 143 57 87 147 14 1 13 1 9 1 10 10 10 5 123 1 122 121 4 113 33 67 34 34 33 2 31 15 30 29 4 5 19 5 16 2 43 2 4 2 33 1 1 7 26 31 31 19 8 17 37 21 1 7 3 2 9 13 3011 3 3012 6 1519 1531 1517 1520 1520 1517 20 1497 1496 2 30 1463 20 20 20 1694 20 1710 1709 15 66 66 65 1519 1519 204 39 345 27 27 10 242 10 89 2300 107 2256 67 119 2876 49 63 2 65 3045 3044 1 2 3046 2436 108 1 185 167 26 74 65 110 2709 1847 3080 2 3081 3060 6 3058 360 2713 2463 10 2 1 3037 6 3045 10 6 16 11 3017 10 9 3 1469 6 1516 2 33 25 2 23 29 4 24 39 17 34 17 17 34 17 17 59 27 34 34 260 264 4 260 260 248 10 12 13 26 12 17 12 1 4 3 2 2 3 1 2 247 3 244 7 234 3 230 4 1 5 221 99 8 50 93 1 1 1 62 3 1 3 56 4 49 41 6 46 52 5 43 54 3 1 50 1856 2 1848 1846 1844 3 1 1835 26 6 14 13 4 2 10 1 6 3 7 2 1 3 1 9 6 4 4 14 14 9 2 9 14 9 77 70 68 85 1 71 6 3 77 66 51 14 14 21 42 52 1 2 3 6 41 6 3 10 39 4 1 9 41 7 48 45 2 3 1 34 3 4 6 37 19 9 2 11 3 8 19 23 1 16 10 155 1 11 87 19 19 5 23 153 489 3 484 16 1 15 16 16 4 3 2 9 39 1 1 38 38 13 24 8 1 1 3 5 199 1 16 156 1 46 17 124 16 44 145 67 1 66 4 59 5 5 50 19 31 49 21 1 1 19 5 16 1 8 2 5 2 10 4 8 14 8 1 7 2 1 4 4 3 9 1 7 1 6 44 46 1 1 44 10 1 1 8 5 1 16 2 1 13 1 10 1 6 2 6 6960 6949 6955 6948 2 724 112 378 98 153 21 3082 25 28 62 53 54 1854 14 2 7 10 7 154 247 488 15 40 42 48 22 127 16 66 21 9 3 46 10 8 16 6949 2 1 1 3 3 13 87 2 3 5 81 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, }; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { const struct bpf_map_ops *ops; u32 type = attr->map_type; struct bpf_map *map; int err; if (type >= ARRAY_SIZE(bpf_map_types)) return ERR_PTR(-EINVAL); type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[type]; if (!ops) return ERR_PTR(-EINVAL); if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return ERR_PTR(err); } if (attr->map_ifindex) ops = &bpf_map_offload_ops; map = ops->map_alloc(attr); if (IS_ERR(map)) return map; map->ops = ops; map->map_type = type; return map; } static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) return sizeof(u32); else return map->value_size; } static void maybe_wait_bpf_programs(struct bpf_map *map) { /* Wait for any running BPF programs to complete so that * userspace, when we return to it, knows that all programs * that could be running use the new map value. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) synchronize_rcu(); } static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_dev_bound(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, f.file, key, value, flags); } bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, flags); rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { rcu_read_lock(); err = bpf_fd_htab_map_update_elem(map, f.file, key, value, flags); rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); } bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; } static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, __u64 flags) { void *ptr; int err; if (bpf_map_is_dev_bound(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) ptr = map->ops->map_lookup_elem_sys_only(map, key); else ptr = map->ops->map_lookup_elem(map, key); if (IS_ERR(ptr)) { err = PTR_ERR(ptr); } else if (!ptr) { err = -ENOENT; } else { err = 0; if (flags & BPF_F_LOCK) /* lock 'ptr' and copy everything but lock */ copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); /* mask lock and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } void bpf_map_area_free(void *area) { kvfree(area); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); map->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } #ifdef CONFIG_MEMCG_KMEM static void bpf_map_save_memcg(struct bpf_map *map) { map->memcg = get_mem_cgroup_from_mm(current->mm); } static void bpf_map_release_memcg(struct bpf_map *map) { mem_cgroup_put(map->memcg); } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *old_memcg; void *ptr; old_memcg = set_active_memcg(map->memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); set_active_memcg(old_memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *old_memcg; void *ptr; old_memcg = set_active_memcg(map->memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *old_memcg; void __percpu *ptr; old_memcg = set_active_memcg(map->memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); bpf_map_release_memcg(map); /* implementation dependent freeing */ map->ops->map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } static void bpf_map_free_in_work(struct bpf_map *map) { INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } static void bpf_map_free_rcu_gp(struct rcu_head *rcu) { bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); } static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_map_free_rcu_gp(rcu); else call_rcu(rcu, bpf_map_free_rcu_gp); } /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); else bpf_map_free_in_work(map); } } void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); } static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; } static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { fmode_t mode = f.file->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. */ if (READ_ONCE(map->frozen)) mode &= ~FMODE_CAN_WRITE; return mode; } #ifdef CONFIG_PROC_FS /* Provides an approximation of the map's memory footprint. * Used only to provide a backward compatibility and display * a reasonable "memlock" info. */ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) { unsigned long size; size = round_up(map->key_size + bpf_map_value_size(map), 8); return round_up(map->max_entries * size, PAGE_SIZE); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; const struct bpf_array *array; u32 type = 0, jited = 0; if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); spin_lock(&array->aux->owner.lock); type = array->aux->owner.type; jited = array->aux->owner.jited; spin_unlock(&array->aux->owner.lock); } seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); if (type) { seq_printf(m, "owner_prog_type:\t%u\n", type); seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; } static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; } /* called for any extra memory-mapped regions (except initial) */ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { .open = bpf_map_mmap_open, .close = bpf_map_mmap_close, }; static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; int err; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || map_value_has_timer(map)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; mutex_lock(&map->freeze_mutex); if (vma->vm_flags & VM_WRITE) { if (map->frozen) { err = -EPERM; goto out; } /* map is meant to be read-only, so do not allow mapping as * writable, because it's possible to leak a writable page * reference and allows user-space to still modify it after * freezing, while verifier will assume contents do not change */ if (map->map_flags & BPF_F_RDONLY_PROG) { err = -EACCES; goto out; } } /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vma->vm_flags &= ~VM_MAYEXEC; if (!(vma->vm_flags & VM_WRITE)) /* disallow re-mapping with PROT_WRITE */ vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); if (err) goto out; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; } static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) { struct bpf_map *map = filp->private_data; if (map->ops->map_poll) return map->ops->map_poll(map, filp, pts); return EPOLLERR; } const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, }; int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL /* dst and src must have at least "size" number of bytes. * Return strlen on success and < 0 on error. */ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { const char *end = src + size; const char *orig_src = src; memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; return src - orig_src; } 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) { return -ENOTSUPP; } static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; int ret = 0; /* Some maps allow key to be unspecified. */ if (btf_key_id) { key_type = btf_type_id_size(btf, &btf_key_id, &key_size); if (!key_type || key_size != map->key_size) return -EINVAL; } else { key_type = btf_type_by_id(btf, 0); if (!map->ops->map_check_btf) return -EINVAL; } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) return -EINVAL; map->spin_lock_off = btf_find_spin_lock(btf, value_type); if (map_value_has_spin_lock(map)) { if (map->map_flags & BPF_F_RDONLY_PROG) return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { WARN_ONCE(1, "verifier bug spin_lock_off %d value_size %d\n", map->spin_lock_off, map->value_size); return -EFAULT; } } map->timer_off = btf_find_timer(btf, value_type); if (map_value_has_timer(map)) { if (map->map_flags & BPF_F_RDONLY_PROG) return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) return -EOPNOTSUPP; } if (map->ops->map_check_btf) ret = map->ops->map_check_btf(map, btf, key_type, value_type); return ret; } #define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) return -EINVAL; } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { return -EINVAL; } f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map = find_and_alloc_map(attr); if (IS_ERR(map)) return PTR_ERR(map); err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); map->spin_lock_off = -EINVAL; map->timer_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with * to figure out the corresponding kernel's * counter part. Thus, attr->btf_fd has * to be valid also. */ attr->btf_vmlinux_value_type_id) { struct btf *btf; btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } if (btf_is_kernel(btf)) { btf_put(btf); err = -EACCES; goto free_map; } map->btf = btf; if (attr->btf_value_type_id) { err = map_check_btf(map, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; } map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; map->btf_vmlinux_value_type_id = attr->btf_vmlinux_value_type_id; } err = security_bpf_map_alloc(map); if (err) goto free_map; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put_with_uref(map); return err; } return err; free_map_sec: security_bpf_map_free(map); free_map: btf_put(map->btf); map->ops->map_free(map); return err; } /* if error is returned, fd is released. * On success caller should complete fd access with matching fdput() */ struct bpf_map *__bpf_map_get(struct fd f) { if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &bpf_map_fops) { fdput(f); return ERR_PTR(-EINVAL); } return f.file->private_data; } void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); void bpf_map_inc_with_uref(struct bpf_map *map) { atomic64_inc(&map->refcnt); atomic64_inc(&map->usercnt); } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; map = __bpf_map_get(f); if (IS_ERR(map)) return map; bpf_map_inc(map); fdput(f); return map; } struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; map = __bpf_map_get(f); if (IS_ERR(map)) return map; bpf_map_inc_with_uref(map); fdput(f); return map; } /* map_idr_lock should have been held */ static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic64_inc(&map->usercnt); return map; } struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { spin_lock_bh(&map_idr_lock); map = __bpf_map_inc_not_zero(map, false); spin_unlock_bh(&map_idr_lock); return map; } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; } static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); return NULL; } static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); return NULL; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: fdput(f); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) { err = -EINVAL; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -EFAULT; if (copy_from_bpfptr(value, uvalue, value_size) != 0) goto free_value; err = bpf_map_update_value(map, f, key, value, attr->flags); free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); fdput(f); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key static int map_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); int ufd = attr->map_fd; struct bpf_map *map; struct fd f; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); fdput(f); return err; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); int ufd = attr->map_fd; struct bpf_map *map; void *key, *next_key; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (ukey) { key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } } else { key = NULL; } err = -ENOMEM; next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); out: if (err) goto free_next_key; err = -EFAULT; if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; err = 0; free_next_key: kvfree(next_key); free_key: kvfree(key); err_put: fdput(f); return err; } int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 cp, max_count; int err = 0; void *key; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) { return -EINVAL; } max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size)) break; if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_delete_elem(map, key); break; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(key); return err; } int generic_map_update_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; int ufd = attr->batch.map_fd; void *key, *value; struct fd f; int err = 0; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) { return -EINVAL; } value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { kvfree(key); return -ENOMEM; } f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size) || copy_from_user(value, values + cp * value_size, value_size)) break; err = bpf_map_update_value(map, f, key, value, attr->batch.elem_flags); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(value); kvfree(key); fdput(f); return err; } #define MAP_LOOKUP_RETRIES 3 int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) return -EINVAL; value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; } err = -EFAULT; prev_key = NULL; if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) goto free_buf; key = buf; value = key + map->key_size; if (ubatch) prev_key = buf_prevkey; for (cp = 0; cp < max_count;) { rcu_read_lock(); err = map->ops->map_get_next_key(map, prev_key, key); rcu_read_unlock(); if (err) break; err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); if (err == -ENOENT) { if (retry) { retry--; continue; } err = -EINTR; break; } if (err) goto free_buf; if (copy_to_user(keys + cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } if (copy_to_user(values + cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); retry = MAP_LOOKUP_RETRIES; cp++; cond_resched(); } if (err == -EFAULT) goto free_buf; if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || (cp && copy_to_user(uobatch, prev_key, map->key_size)))) err = -EFAULT; free_buf: kvfree(buf_prevkey); kvfree(buf); return err; } #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (attr->flags && (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK)) { err = -EINVAL; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { if (!bpf_map_is_dev_bound(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); rcu_read_unlock(); bpf_enable_instrumentation(); } } if (err) goto free_value; if (copy_to_user(uvalue, value, value_size) != 0) { err = -EFAULT; goto free_value; } err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); fdput(f); return err; } #define BPF_MAP_FREEZE_LAST_FIELD map_fd static int map_freeze(const union bpf_attr *attr) { int err = 0, ufd = attr->map_fd; struct bpf_map *map; struct fd f; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || map_value_has_timer(map)) { fdput(f); return -ENOTSUPP; } mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; } if (!bpf_capable()) { err = -EPERM; goto err_put; } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); fdput(f); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { const struct bpf_prog_ops *ops; if (type >= ARRAY_SIZE(bpf_prog_types)) return -EINVAL; type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); ops = bpf_prog_types[type]; if (!ops) return -EINVAL; if (!bpf_prog_is_dev_bound(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } enum bpf_audit { BPF_AUDIT_LOAD, BPF_AUDIT_UNLOAD, BPF_AUDIT_MAX, }; static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { [BPF_AUDIT_LOAD] = "LOAD", [BPF_AUDIT_UNLOAD] = "UNLOAD", }; static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) { struct audit_context *ctx = NULL; struct audit_buffer *ab; if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) return; if (audit_enabled == AUDIT_OFF) return; if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) return; audit_log_format(ab, "prog-id=%u op=%s", prog->aux->id, bpf_audit_str[op]); audit_log_end(ab); } static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&prog_idr_lock); id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); if (id > 0) prog->aux->id = id; spin_unlock_bh(&prog_idr_lock); idr_preload_end(); /* id is in [1, INT_MAX) */ if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) { unsigned long flags; /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, * simply waiting for refcnt to drop to be freed. */ if (!prog->aux->id) return; if (do_idr_lock) spin_lock_irqsave(&prog_idr_lock, flags); else __acquire(&prog_idr_lock); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&prog_idr_lock, flags); else __release(&prog_idr_lock); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { if (prog->aux->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } else { __bpf_prog_put_rcu(&prog->aux->rcu); } } static void bpf_prog_put_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; struct bpf_prog *prog; aux = container_of(work, struct bpf_prog_aux, work); prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); bpf_prog_free_id(prog, true); __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { if (in_irq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { bpf_prog_put_deferred(&aux->work); } } } void bpf_prog_put(struct bpf_prog *prog) { __bpf_prog_put(prog, true); } EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; bpf_prog_put(prog); return 0; } struct bpf_prog_kstats { u64 nsecs; u64 cnt; u64 misses; }; static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); tnsecs = u64_stats_read(&st->nsecs); tcnt = u64_stats_read(&st->cnt); tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; stats->misses = misses; } #ifdef CONFIG_PROC_FS static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" "recursion_misses:\t%llu\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, stats.cnt, stats.misses); } #endif const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { int ret; ret = security_bpf_prog(prog); if (ret < 0) return ret; return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } static struct bpf_prog *____bpf_prog_get(struct fd f) { if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &bpf_prog_fops) { fdput(f); return ERR_PTR(-EINVAL); } return f.file->private_data; } void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); void bpf_prog_sub(struct bpf_prog *prog, int i) { /* Only to be used for undoing previous bpf_prog_add() in some * error path. We still know that another entity in our call * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); void bpf_prog_inc(struct bpf_prog *prog) { atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); return prog; } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ if (!attach_type) return true; if (prog->type != *attach_type) return false; if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { struct fd f = fdget(ufd); struct bpf_prog *prog; prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) { prog = ERR_PTR(-EINVAL); goto out; } bpf_prog_inc(prog); out: fdput(f); return prog; } struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* Initially all BPF programs could be loaded w/o specifying * expected_attach_type. Later for some of them specifying expected_attach_type * at load time became required so that program could be validated properly. * Programs of types that are allowed to be loaded both w/ and w/o (for * backward compatibility) expected_attach_type, should have the default attach * type assigned to expected_attach_type for the latter case, so that it can be * validated later at attach time. * * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if * prog type requires it but has some attach types that have to be backward * compatible. */ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) { switch (attr->prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't * exist so checking for non-zero is the way to go here. */ if (!attr->expected_attach_type) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; case BPF_PROG_TYPE_SK_REUSEPORT: if (!attr->expected_attach_type) attr->expected_attach_type = BPF_SK_REUSEPORT_SELECT; break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; if (!attach_btf && !dst_prog) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; default: return -EINVAL; } } if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SKB: switch (expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCKOPT: switch (expected_attach_type) { case BPF_CGROUP_SETSOCKOPT: case BPF_CGROUP_GETSOCKOPT: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SK_LOOKUP: if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; case BPF_PROG_TYPE_SK_REUSEPORT: switch (expected_attach_type) { case BPF_SK_REUSEPORT_SELECT: case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; fallthrough; default: return 0; } } static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ case BPF_PROG_TYPE_SK_REUSEPORT: /* equivalent to SOCKET_FILTER. need CAP_BPF only */ default: return false; } } static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; default: return false; } } /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD fd_array static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; int err; char license[128]; bool is_gpl; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && !bpf_capable()) return -EPERM; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) return -EFAULT; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ is_gpl = license_is_gpl_compatible(license); if (attr->insn_cnt == 0 || attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) return -E2BIG; if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !bpf_capable()) return -EPERM; if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ if (attr->attach_prog_fd) { dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); if (IS_ERR(attach_btf)) return -EINVAL; if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); return -ENOTSUPP; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) return PTR_ERR(attach_btf); if (!attach_btf) return -EINVAL; btf_get(attach_btf); } bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); return -EINVAL; } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); return -ENOMEM; } prog->expected_attach_type = attr->expected_attach_type; prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) goto free_prog_sec; prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_init(prog, attr); if (err) goto free_prog_sec; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog_sec; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr); if (err < 0) goto free_used_maps; prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; /* Upon success of bpf_prog_alloc_id(), the BPF prog is * effectively publicly exposed. However, retrieving via * bpf_prog_get_fd_by_id() will take another reference, * therefore it cannot be gone underneath us. * * Only for the time /after/ successful bpf_prog_new_fd() * and before returning to userspace, we might just hold * one reference and any parallel close on that fd could * rip everything out. Hence, below notifications must * happen before bpf_prog_new_fd(). * * Also, any failure handling from this point onwards must * be using bpf_prog_put() given the program is exposed. */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) bpf_prog_put(prog); return err; free_used_maps: /* In case we have subprogs, we need to wait for a grace * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ __bpf_prog_put_noref(prog, prog->aux->func_cnt); return err; free_prog_sec: free_uid(prog->aux->user); security_bpf_prog_free(prog->aux); free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); return err; } #define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), attr->file_flags); } void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { atomic64_set(&link->refcnt, 1); link->type = type; link->id = 0; link->ops = ops; link->prog = prog; } static void bpf_link_free_id(int id) { if (!id) return; spin_lock_bh(&link_idr_lock); idr_remove(&link_idr, id); spin_unlock_bh(&link_idr_lock); } /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred * anon_inode's release() call. This helper marksbpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { primer->link->prog = NULL; bpf_link_free_id(primer->id); fput(primer->file); put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) { atomic64_inc(&link->refcnt); } /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { bpf_link_free_id(link->id); if (link->prog) { /* detach BPF program, clean up used resources */ link->ops->release(link); bpf_prog_put(link->prog); } /* free bpf_link and its containing memory */ link->ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) { struct bpf_link *link = container_of(work, struct bpf_link, work); bpf_link_free(link); } /* bpf_link_put can be called from atomic context, but ensures that resources * are freed from process context */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; if (in_atomic()) { INIT_WORK(&link->work, bpf_link_put_deferred); schedule_work(&link->work); } else { bpf_link_free(link); } } static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; bpf_link_put(link); return 0; } #ifdef CONFIG_PROC_FS #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, static const char *bpf_link_type_strs[] = { [BPF_LINK_TYPE_UNSPEC] = "<invalid>", #include <linux/bpf_types.h> }; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "link_type:\t%s\n" "link_id:\t%u\n" "prog_tag:\t%s\n" "prog_id:\t%u\n", bpf_link_type_strs[link->type], link->id, prog_tag, prog->aux->id); if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; static int bpf_link_alloc_id(struct bpf_link *link) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&link_idr_lock); id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); spin_unlock_bh(&link_idr_lock); idr_preload_end(); return id; } /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, * reserving unused FD and allocating ID from link_idr. This is to be paired * with bpf_link_settle() to install FD and ID and expose bpf_link to * user-space, if bpf_link is successfully attached. If not, bpf_link and * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when * there are complicated and expensive operations inbetween creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case * that file, FD, or ID can't be allocated. */ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; id = bpf_link_alloc_id(link); if (id < 0) { put_unused_fd(fd); return id; } file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); return PTR_ERR(file); } primer->link = link; primer->file = file; primer->fd = fd; primer->id = id; return 0; } int bpf_link_settle(struct bpf_link_primer *primer) { /* make bpf_link fetchable by ID */ spin_lock_bh(&link_idr_lock); primer->link->id = primer->id; spin_unlock_bh(&link_idr_lock); /* make bpf_link fetchable by FD */ fd_install(primer->fd, primer->file); /* pass through installed FD */ return primer->fd; } int bpf_link_new_fd(struct bpf_link *link) { return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { struct fd f = fdget(ufd); struct bpf_link *link; if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &bpf_link_fops) { fdput(f); return ERR_PTR(-EINVAL); } link = f.file->private_data; bpf_link_inc(link); fdput(f); return link; } struct bpf_tracing_link { struct bpf_link link; enum bpf_attach_type attach_type; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog, tr_link->trampoline)); bpf_trampoline_put(tr_link->trampoline); /* tgt_prog is NULL if target is a kernel function */ if (tr_link->tgt_prog) bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link); kfree(tr_link); } static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link); seq_printf(seq, "attach_type:\t%d\n", tr_link->attach_type); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link); info->tracing.attach_type = tr_link->attach_type; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); return 0; } static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, .show_fdinfo = bpf_tracing_link_show_fdinfo, .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; u64 key = 0; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && prog->expected_attach_type != BPF_MODIFY_RETURN) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_EXT: if (prog->expected_attach_type != 0) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type != BPF_LSM_MAC) { err = -EINVAL; goto out_put_prog; } break; default: err = -EINVAL; goto out_put_prog; } if (!!tgt_prog_fd != !!btf_id) { err = -EINVAL; goto out_put_prog; } if (tgt_prog_fd) { /* For now we only allow new targets for BPF_PROG_TYPE_EXT */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } tgt_prog = bpf_prog_get(tgt_prog_fd); if (IS_ERR(tgt_prog)) { err = PTR_ERR(tgt_prog); tgt_prog = NULL; goto out_put_prog; } key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_prog; } bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog); link->attach_type = prog->expected_attach_type; mutex_lock(&prog->aux->dst_mutex); /* There are a few possible cases here: * * - if prog->aux->dst_trampoline is set, the program was just loaded * and not yet attached to anything, so we can use the values stored * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. * * - if tgt_prog == NULL when this function was called using the old * raw_tracepoint_open API, and we need a target from prog->aux * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. * * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf * are NULL, then program was already attached and user did not provide * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* * Allow re-attach for TRACING and LSM programs. If it's * currently linked, bpf_trampoline_link_prog will fail. * EXT programs need to specify tgt_prog_fd, so they * re-attach in separate code path. */ if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { err = -EINVAL; goto out_unlock; } /* We can allow re-attach only if we have valid attach_btf. */ if (!prog->aux->attach_btf) { err = -EINVAL; goto out_unlock; } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } if (!prog->aux->dst_trampoline || (key && key != prog->aux->dst_trampoline->key)) { /* If there is no saved target, or the specified target is * different from the destination specified at load time, we * need a new trampoline and a check for compatibility */ struct bpf_attach_target_info tgt_info = {}; err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, &tgt_info); if (err) goto out_unlock; tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; goto out_unlock; } } else { /* The caller didn't specify a target, or the target was the * same as the destination supplied during program load. This * means we can reuse the trampoline and reference from program * load time, and there is no need to allocate a new one. This * can only happen once for any program, as the saved values in * prog->aux are cleared below. */ tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } err = bpf_link_prime(&link->link, &link_primer); if (err) goto out_unlock; err = bpf_trampoline_link_prog(prog, tr); if (err) { bpf_link_cleanup(&link_primer); link = NULL; goto out_unlock; } link->tgt_prog = tgt_prog; link->trampoline = tr; /* Always clear the trampoline and target prog from prog->aux to make * sure the original attach destination is not kept alive after a * program is (re-)attached to another target. */ if (prog->aux->dst_prog && (tgt_prog_fd || tr != prog->aux->dst_trampoline)) /* got extra prog ref from syscall, or attaching to different prog */ bpf_prog_put(prog->aux->dst_prog); if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) /* we allocated a new trampoline, so free the old one */ bpf_trampoline_put(prog->aux->dst_trampoline); prog->aux->dst_prog = NULL; prog->aux->dst_trampoline = NULL; mutex_unlock(&prog->aux->dst_mutex); return bpf_link_settle(&link_primer); out_unlock: if (tr && tr != prog->aux->dst_trampoline) bpf_trampoline_put(tr); mutex_unlock(&prog->aux->dst_mutex); kfree(link); out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); return err; } struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; }; static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); bpf_put_raw_tracepoint(raw_tp->btp); } static void bpf_raw_tp_link_dealloc(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); kfree(raw_tp); } static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, "tp_name:\t%s\n", raw_tp_link->btp->tp->name); } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); const char *tp_name = raw_tp_link->btp->tp->name; u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; if (!ubuf) return 0; if (ulen >= tp_len + 1) { if (copy_to_user(ubuf, tp_name, tp_len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, tp_name, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } return 0; } static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #ifdef CONFIG_PERF_EVENTS struct bpf_perf_link { struct bpf_link link; struct file *perf_file; }; static void bpf_perf_link_release(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); struct perf_event *event = perf_link->perf_file->private_data; perf_event_free_bpf_prog(event); fput(perf_link->perf_file); } static void bpf_perf_link_dealloc(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); kfree(perf_link); } static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_perf_link *link; struct perf_event *event; struct file *perf_file; int err; if (attr->link_create.flags) return -EINVAL; perf_file = perf_event_get(attr->link_create.target_fd); if (IS_ERR(perf_file)) return PTR_ERR(perf_file); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_file; } bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_file; } event = perf_file->private_data; err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; } /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out_put_file: fput(perf_file); return err; } #endif /* CONFIG_PERF_EVENTS */ #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; struct bpf_prog *prog; const char *tp_name; char buf[128]; int err; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. */ err = -EINVAL; goto out_put_prog; } if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } err = bpf_tracing_prog_attach(prog, 0, 0); if (err >= 0) return err; goto out_put_prog; case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), sizeof(buf) - 1) < 0) { err = -EFAULT; goto out_put_prog; } buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: err = -EINVAL; goto out_put_prog; } btp = bpf_get_raw_tracepoint(tp_name); if (!btp) { err = -ENOENT; goto out_put_prog; } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_btp; } bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog); link->btp = btp; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_btp; } err = bpf_probe_register(link->btp, prog); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; } return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); out_put_prog: bpf_prog_put(prog); return err; } static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: if (!capable(CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ return -EPERM; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; default: return 0; } } static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: return BPF_PROG_TYPE_TRACING; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; default: return BPF_PROG_TYPE_UNSPEC; } } #define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd #define BPF_F_ATTACH_MASK \ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; if (attr->attach_flags & ~BPF_F_ATTACH_MASK) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) { bpf_prog_put(prog); return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; default: ret = -EINVAL; } if (ret) bpf_prog_put(prog); return ret; } #define BPF_PROG_DETACH_LAST_FIELD attach_type static int bpf_prog_detach(const union bpf_attr *attr) { enum bpf_prog_type ptype; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: return sock_map_prog_detach(attr, ptype); case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_PROG_TYPE_FLOW_DISSECTOR: return netns_bpf_prog_detach(attr, ptype); case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: return cgroup_bpf_prog_detach(attr, ptype); default: return -EINVAL; } } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) return -EINVAL; switch (attr->query.attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); default: return -EINVAL; } } #define BPF_PROG_TEST_RUN_LAST_FIELD test.cpu static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog *prog; int ret = -ENOTSUPP; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; if ((attr->test.ctx_size_in && !attr->test.ctx_in) || (!attr->test.ctx_size_in && attr->test.ctx_in)) return -EINVAL; if ((attr->test.ctx_size_out && !attr->test.ctx_out) || (!attr->test.ctx_size_out && attr->test.ctx_out)) return -EINVAL; prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->aux->ops->test_run) ret = prog->aux->ops->test_run(prog, attr, uattr); bpf_prog_put(prog); return ret; } #define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id static int bpf_obj_get_next_id(const union bpf_attr *attr, union bpf_attr __user *uattr, struct idr *idr, spinlock_t *lock) { u32 next_id = attr->start_id; int err = 0; if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; next_id++; spin_lock_bh(lock); if (!idr_get_next(idr, &next_id)) err = -ENOENT; spin_unlock_bh(lock); if (!err) err = put_user(next_id, &uattr->next_id); return err; } struct bpf_map *bpf_map_get_curr_or_next(u32 *id) { struct bpf_map *map; spin_lock_bh(&map_idr_lock); again: map = idr_get_next(&map_idr, id); if (map) { map = __bpf_map_inc_not_zero(map, false); if (IS_ERR(map)) { (*id)++; goto again; } } spin_unlock_bh(&map_idr_lock); return map; } struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) { struct bpf_prog *prog; spin_lock_bh(&prog_idr_lock); again: prog = idr_get_next(&prog_idr, id); if (prog) { prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { (*id)++; goto again; } } spin_unlock_bh(&prog_idr_lock); return prog; } #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); if (prog) prog = bpf_prog_inc_not_zero(prog); else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); return prog; } static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) { struct bpf_prog *prog; u32 id = attr->prog_id; int fd; if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); fd = bpf_prog_new_fd(prog); if (fd < 0) bpf_prog_put(prog); return fd; } #define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; int f_flags; int fd; if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; f_flags = bpf_get_file_flag(attr->open_flags); if (f_flags < 0) return f_flags; spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); if (IS_ERR(map)) return PTR_ERR(map); fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); return fd; } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, unsigned long addr, u32 *off, u32 *type) { const struct bpf_map *map; int i; mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; goto out; } } map = NULL; out: mutex_unlock(&prog->aux->used_maps_mutex); return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), GFP_USER); if (!insns) return insns; for (i = 0; i < prog->len; i++) { code = insns[i].code; if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; continue; } if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { insns[i].src_reg = type; insns[i].imm = map->id; insns[i + 1].imm = off; continue; } } return insns; } static int set_info_rec_size(struct bpf_prog_info *info) { /* * Ensure info.*_rec_size is the same as kernel expected size * * or * * Only allow zero *_rec_size if both _rec_size and _cnt are * zero. In this case, the kernel will set the expected * _rec_size back to the info. */ if ((info->nr_func_info || info->func_info_rec_size) && info->func_info_rec_size != sizeof(struct bpf_func_info)) return -EINVAL; if ((info->nr_line_info || info->line_info_rec_size) && info->line_info_rec_size != sizeof(struct bpf_line_info)) return -EINVAL; if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && info->jited_line_info_rec_size != sizeof(__u64)) return -EINVAL; info->func_info_rec_size = sizeof(struct bpf_func_info); info->line_info_rec_size = sizeof(struct bpf_line_info); info->jited_line_info_rec_size = sizeof(__u64); return 0; } static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_prog_info info; u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = prog->type; info.id = prog->aux->id; info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, &user_map_ids[i])) { mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; } } mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) return err; bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; info.nr_func_info = 0; info.nr_line_info = 0; info.nr_jited_line_info = 0; goto done; } ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { struct bpf_insn *insns_sanitized; bool fault; if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); fault = copy_to_user(uinsns, insns_sanitized, ulen); kfree(insns_sanitized); if (fault) return -EFAULT; } if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; goto done; } /* NOTE: the following code is supposed to be skipped for offload. * bpf_prog_offload_info_fill() is the place to fill similar fields * for offload. */ ulen = info.jited_prog_len; if (prog->aux->func_cnt) { u32 i; info.jited_prog_len = 0; for (i = 0; i < prog->aux->func_cnt; i++) info.jited_prog_len += prog->aux->func[i]->jited_len; } else { info.jited_prog_len = prog->jited_len; } if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); /* for multi-function programs, copy the JITed * instructions for all the functions */ if (prog->aux->func_cnt) { u32 len, free, i; u8 *img; free = ulen; for (i = 0; i < prog->aux->func_cnt; i++) { len = prog->aux->func[i]->jited_len; len = min_t(u32, len, free); img = (u8 *) prog->aux->func[i]->bpf_func; if (copy_to_user(uinsns, img, len)) return -EFAULT; uinsns += len; free -= len; if (!free) break; } } else { if (copy_to_user(uinsns, prog->bpf_func, ulen)) return -EFAULT; } } else { info.jited_prog_insns = 0; } } ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; /* copy the address of the kernel symbol * corresponding to each function */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { ksym_addr = (unsigned long) prog->aux->func[i]->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } } else { ksym_addr = (unsigned long) prog->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { info.jited_ksyms = 0; } } ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { func_len = prog->aux->func[i]->jited_len; if (put_user(func_len, &user_lens[i])) return -EFAULT; } } else { func_len = prog->jited_len; if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { info.jited_func_lens = 0; } } if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; if (info.nr_func_info && ulen) { char __user *user_finfo; user_finfo = u64_to_user_ptr(info.func_info); ulen = min_t(u32, info.nr_func_info, ulen); if (copy_to_user(user_finfo, prog->aux->func_info, info.func_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_line_info; info.nr_line_info = prog->aux->nr_linfo; if (info.nr_line_info && ulen) { __u8 __user *user_linfo; user_linfo = u64_to_user_ptr(info.line_info); ulen = min_t(u32, info.nr_line_info, ulen); if (copy_to_user(user_linfo, prog->aux->linfo, info.line_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_jited_line_info; if (prog->aux->jited_linfo) info.nr_jited_line_info = prog->aux->nr_linfo; else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { if (put_user((__u64)(long)prog->aux->jited_linfo[i], &user_linfo[i])) return -EFAULT; } } else { info.jited_line_info = 0; } } ulen = info.nr_prog_tags; info.nr_prog_tags = prog->aux->func_cnt ? : 1; if (ulen) { __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; u32 i; user_prog_tags = u64_to_user_ptr(info.prog_tags); ulen = min_t(u32, info.nr_prog_tags, ulen); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { if (copy_to_user(user_prog_tags[i], prog->aux->func[i]->tag, BPF_TAG_SIZE)) return -EFAULT; } } else { if (copy_to_user(user_prog_tags[0], prog->tag, BPF_TAG_SIZE)) return -EFAULT; } } done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_map_get_info_by_fd(struct file *file, struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_btf_get_info_by_fd(struct file *file, struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } static int bpf_link_get_info_by_fd(struct file *file, struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_link_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = link->type; info.id = link->id; info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { int ufd = attr->info.bpf_fd; struct fd f; int err; if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; f = fdget(ufd); if (!f.file) return -EBADFD; if (f.file->f_op == &bpf_prog_fops) err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_map_fops) err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &btf_fops) err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_link_fops) err = bpf_link_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else err = -EINVAL; fdput(f); return err; } #define BPF_BTF_LOAD_LAST_FIELD btf_log_level static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) { if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; if (!bpf_capable()) return -EPERM; return btf_new_fd(attr, uattr); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; return btf_get_fd_by_id(attr->btf_id); } static int bpf_task_fd_query_copy(const union bpf_attr *attr, union bpf_attr __user *uattr, u32 prog_id, u32 fd_type, const char *buf, u64 probe_offset, u64 probe_addr) { char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); u32 len = buf ? strlen(buf) : 0, input_len; int err = 0; if (put_user(len, &uattr->task_fd_query.buf_len)) return -EFAULT; input_len = attr->task_fd_query.buf_len; if (input_len && ubuf) { if (!len) { /* nothing to copy, just make ubuf NULL terminated */ char zero = '\0'; if (put_user(zero, ubuf)) return -EFAULT; } else if (input_len >= len + 1) { /* ubuf can hold the string with NULL terminator */ if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { /* ubuf cannot hold the string with NULL terminator, * do a partial copy with NULL terminator. */ char zero = '\0'; err = -ENOSPC; if (copy_to_user(ubuf, buf, input_len - 1)) return -EFAULT; if (put_user(zero, ubuf + input_len - 1)) return -EFAULT; } } if (put_user(prog_id, &uattr->task_fd_query.prog_id) || put_user(fd_type, &uattr->task_fd_query.fd_type) || put_user(probe_offset, &uattr->task_fd_query.probe_offset) || put_user(probe_addr, &uattr->task_fd_query.probe_addr)) return -EFAULT; return err; } #define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr static int bpf_task_fd_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; struct task_struct *task; struct file *file; int err; if (CHECK_ATTR(BPF_TASK_FD_QUERY)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (attr->task_fd_query.flags != 0) return -EINVAL; rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); if (!task) return -ENOENT; err = 0; file = fget_task(task, fd); put_task_struct(task); if (!file) return -EBADF; if (file->f_op == &bpf_link_fops) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; err = bpf_task_fd_query_copy(attr, uattr, raw_tp->link.prog->aux->id, BPF_FD_TYPE_RAW_TRACEPOINT, btp->tp->name, 0, 0); goto put_file; } goto out_not_supp; } event = perf_get_event(file); if (!IS_ERR(event)) { u64 probe_offset, probe_addr; u32 prog_id, fd_type; const char *buf; err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, &probe_addr); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, probe_offset, probe_addr); goto put_file; } out_not_supp: err = -ENOTSUPP; put_file: fput(file); return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags #define BPF_DO_BATCH(fn) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ err = fn(map, attr, uattr); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; ufd = attr->batch.map_fd; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (has_write) bpf_map_write_active_inc(map); if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); err_put: if (has_write) bpf_map_write_active_dec(map); fdput(f); return err; } static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog) { if (attr->link_create.attach_type != prog->expected_attach_type) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_ITER) return bpf_iter_link_attach(attr, uattr, prog); else if (prog->type == BPF_PROG_TYPE_EXT) return bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id); return -EINVAL; } #define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len static int link_create(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) goto out; switch (prog->type) { case BPF_PROG_TYPE_EXT: ret = tracing_bpf_link_attach(attr, uattr, prog); goto out; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: if (attr->link_create.attach_type != BPF_PERF_EVENT) { ret = -EINVAL; goto out; } ptype = prog->type; break; default: ptype = attach_type_to_prog_type(attr->link_create.attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { ret = -EINVAL; goto out; } break; } switch (ptype) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_TRACING: ret = tracing_bpf_link_attach(attr, uattr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; #endif #ifdef CONFIG_PERF_EVENTS case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_KPROBE: ret = bpf_perf_link_attach(attr, prog); break; #endif default: ret = -EINVAL; } out: if (ret < 0) bpf_prog_put(prog); return ret; } #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) { struct bpf_prog *old_prog = NULL, *new_prog; struct bpf_link *link; u32 flags; int ret; if (CHECK_ATTR(BPF_LINK_UPDATE)) return -EINVAL; flags = attr->link_update.flags; if (flags & ~BPF_F_REPLACE) return -EINVAL; link = bpf_link_get_from_fd(attr->link_update.link_fd); if (IS_ERR(link)) return PTR_ERR(link); new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); goto out_put_link; } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); if (IS_ERR(old_prog)) { ret = PTR_ERR(old_prog); old_prog = NULL; goto out_put_progs; } } else if (attr->link_update.old_prog_fd) { ret = -EINVAL; goto out_put_progs; } if (link->ops->update_prog) ret = link->ops->update_prog(link, new_prog, old_prog); else ret = -EINVAL; out_put_progs: if (old_prog) bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); out_put_link: bpf_link_put(link); return ret; } #define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd static int link_detach(union bpf_attr *attr) { struct bpf_link *link; int ret; if (CHECK_ATTR(BPF_LINK_DETACH)) return -EINVAL; link = bpf_link_get_from_fd(attr->link_detach.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->detach) ret = link->ops->detach(link); else ret = -EOPNOTSUPP; bpf_link_put(link); return ret; } static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ link = idr_find(&link_idr, id); if (link) { if (link->id) link = bpf_link_inc_not_zero(link); else link = ERR_PTR(-EAGAIN); } else { link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); return link; } #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) { struct bpf_link *link; u32 id = attr->link_id; int fd; if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; link = bpf_link_by_id(id); if (IS_ERR(link)) return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) bpf_link_put(link); return fd; } DEFINE_MUTEX(bpf_stats_enabled_mutex); static int bpf_stats_release(struct inode *inode, struct file *file) { mutex_lock(&bpf_stats_enabled_mutex); static_key_slow_dec(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return 0; } static const struct file_operations bpf_stats_fops = { .release = bpf_stats_release, }; static int bpf_enable_runtime_stats(void) { int fd; mutex_lock(&bpf_stats_enabled_mutex); /* Set a very high limit to avoid overflow */ if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { mutex_unlock(&bpf_stats_enabled_mutex); return -EBUSY; } fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); if (fd >= 0) static_key_slow_inc(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return fd; } #define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type static int bpf_enable_stats(union bpf_attr *attr) { if (CHECK_ATTR(BPF_ENABLE_STATS)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; switch (attr->enable_stats.type) { case BPF_STATS_RUN_TIME: return bpf_enable_runtime_stats(); default: break; } return -EINVAL; } #define BPF_ITER_CREATE_LAST_FIELD iter_create.flags static int bpf_iter_create(union bpf_attr *attr) { struct bpf_link *link; int err; if (CHECK_ATTR(BPF_ITER_CREATE)) return -EINVAL; if (attr->iter_create.flags) return -EINVAL; link = bpf_link_get_from_fd(attr->iter_create.link_fd); if (IS_ERR(link)) return PTR_ERR(link); err = bpf_iter_new_fd(link); bpf_link_put(link); return err; } #define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags static int bpf_prog_bind_map(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; struct bpf_map **used_maps_old, **used_maps_new; int i, ret = 0; if (CHECK_ATTR(BPF_PROG_BIND_MAP)) return -EINVAL; if (attr->prog_bind_map.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_bind_map.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); map = bpf_map_get(attr->prog_bind_map.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto out_prog_put; } mutex_lock(&prog->aux->used_maps_mutex); used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) if (used_maps_old[i] == map) { bpf_map_put(map); goto out_unlock; } used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, sizeof(used_maps_new[0]), GFP_KERNEL); if (!used_maps_new) { ret = -ENOMEM; goto out_unlock; } memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; prog->aux->used_map_cnt++; prog->aux->used_maps = used_maps_new; kfree(used_maps_old); out_unlock: mutex_unlock(&prog->aux->used_maps_mutex); if (ret) bpf_map_put(map); out_prog_put: bpf_prog_put(prog); return ret; } static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) return -EPERM; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; case BPF_MAP_FREEZE: err = map_freeze(&attr); break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; case BPF_MAP_GET_FD_BY_ID: err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: err = bpf_btf_load(&attr, uattr); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); break; case BPF_LINK_GET_FD_BY_ID: err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; case BPF_LINK_DETACH: err = link_detach(&attr); break; case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; default: err = -EINVAL; break; } return err; } SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { return __sys_bpf(cmd, USER_BPFPTR(uattr), size); } static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= U16_MAX) return false; if (off % size != 0) return false; return true; } BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size) { switch (cmd) { case BPF_MAP_CREATE: case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_PROG_LOAD: case BPF_BTF_LOAD: break; /* case BPF_PROG_TEST_RUN: * is not part of this list to prevent recursive test_run */ default: return -EINVAL; } return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id); } BPF_CALL_1(bpf_sys_close, u32, fd) { /* When bpf program calls this helper there should not be * an fdget() without matching completed fdput(). * This helper is allowed in the following callchain only: * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close */ return close_fd(fd); } static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; default: return tracing_prog_func_proto(func_id, prog); } } const struct bpf_verifier_ops bpf_syscall_verifier_ops = { .get_func_proto = syscall_prog_func_proto, .is_valid_access = syscall_prog_is_valid_access, }; const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; |
| 263 293 402 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ u32 nr_extents; union { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, UCOUNT_COUNTS, }; #define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; } __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; }; extern struct user_namespace init_user_ns; extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type) { return atomic_long_read(&ucounts->ucount[type]); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type); bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); static inline void set_rlimit_ucount_max(struct user_namespace *ns, enum ucount_type type, unsigned long max) { ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) refcount_inc(&ns->ns.count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && refcount_dec_and_test(&ns->ns.count)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_H */ |
| 918 920 920 916 1 1 921 925 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return false; return fsnotify_inode_watches_children(fsnotify_conn_inode(conn)); } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return; fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn)); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { bool update_children; if (!conn) return; spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); __fsnotify_recalc_mask(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* * Set children's PARENT_WATCHED flags only if parent started watching. * When parent stops watching, we clear false positive PARENT_WATCHED * flags lazily in __fsnotify_parent(). */ if (update_children) fsnotify_conn_set_children_dentry_flags(conn); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void fsnotify_put_inode_ref(struct inode *inode) { struct super_block *sb = inode->i_sb; iput(inode); if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb) atomic_long_inc(&sb->s_fsnotify_connectors); } static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } fsnotify_put_sb_connectors(conn); rcu_assign_pointer(*(conn->obj), NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, unsigned int obj_type, __kernel_fsid_t *fsid) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { conn->fsid = *fsid; conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID; } else { conn->fsid.val[0] = conn->fsid.val[1] = 0; conn->flags = 0; } fsnotify_get_sb_connectors(conn); /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1])) return -ENODEV; restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj_type, fsid); if (err) return err; goto restart; } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) { conn->fsid = *fsid; /* Pairs with smp_rmb() in fanotify_get_fsid() */ smp_wmb(); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID; } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) && (fsid->val[0] != conn->fsid.val[0] || fsid->val[1] != conn->fsid.val[1])) { /* * Backend is expected to check for non uniform fsid * (e.g. btrfs), but maybe we missed something? * Only allow setting conn->fsid once to non zero fsid. * inotify and non-fid fanotify groups do not set nor test * conn->fsid. */ pr_warn_ratelimited("%s: fsid mismatch on object of type %u: " "%x.%x != %x.%x\n", __func__, conn->type, fsid->val[0], fsid->val[1], conn->fsid.val[0], conn->fsid.val[1]); err = -EXDEV; goto out_err; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | // SPDX-License-Identifier: GPL-2.0 /* net/atm/svc.c - ATM SVC sockets */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ #include <linux/string.h> #include <linux/net.h> /* struct socket, struct proto_ops */ #include <linux/errno.h> /* error codes */ #include <linux/kernel.h> /* printk */ #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/fcntl.h> /* O_NONBLOCK */ #include <linux/init.h> #include <linux/atm.h> /* ATM stuff */ #include <linux/atmsap.h> #include <linux/atmsvc.h> #include <linux/atmdev.h> #include <linux/bitops.h> #include <net/sock.h> /* for sock_no_* */ #include <linux/uaccess.h> #include <linux/export.h> #include "resources.h" #include "common.h" /* common for PVCs and SVCs */ #include "signaling.h" #include "addr.h" static int svc_create(struct net *net, struct socket *sock, int protocol, int kern); /* * Note: since all this is still nicely synchronized with the signaling demon, * there's no need to protect sleep loops with clis. If signaling is * moved into the kernel, that would change. */ static int svc_shutdown(struct socket *sock, int how) { return 0; } static void svc_disconnect(struct atm_vcc *vcc) { DEFINE_WAIT(wait); struct sk_buff *skb; struct sock *sk = sk_atm(vcc); pr_debug("%p\n", vcc); if (test_bit(ATM_VF_REGIS, &vcc->flags)) { sigd_enq(vcc, as_close, NULL, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); } /* beware - socket is still in use by atmsigd until the last as_indicate has been answered */ while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { atm_return(vcc, skb->truesize); pr_debug("LISTEN REL\n"); sigd_enq2(NULL, as_reject, vcc, NULL, NULL, &vcc->qos, 0); dev_kfree_skb(skb); } clear_bit(ATM_VF_REGIS, &vcc->flags); /* ... may retry later */ } static int svc_release(struct socket *sock) { struct sock *sk = sock->sk; struct atm_vcc *vcc; if (sk) { vcc = ATM_SD(sock); pr_debug("%p\n", vcc); clear_bit(ATM_VF_READY, &vcc->flags); /* * VCC pointer is used as a reference, * so we must not free it (thereby subjecting it to re-use) * before all pending connections are closed */ svc_disconnect(vcc); vcc_release(sock); } return 0; } static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc; int error; if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTED) { error = -EISCONN; goto out; } if (sock->state != SS_UNCONNECTED) { error = -EINVAL; goto out; } vcc = ATM_SD(sock); addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } clear_bit(ATM_VF_BOUND, &vcc->flags); /* failing rebind will kill old binding */ /* @@@ check memory (de)allocation on rebind */ if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } vcc->local = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */ if (!sigd) { error = -EUNATCH; goto out; } if (!sk->sk_err) set_bit(ATM_VF_BOUND, &vcc->flags); error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) { error = -EINVAL; goto out; } switch (sock->state) { default: error = -EINVAL; goto out; case SS_CONNECTED: error = -EISCONN; goto out; case SS_CONNECTING: if (test_bit(ATM_VF_WAITING, &vcc->flags)) { error = -EALREADY; goto out; } sock->state = SS_UNCONNECTED; if (sk->sk_err) { error = -sk->sk_err; goto out; } break; case SS_UNCONNECTED: addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } if (vcc->qos.txtp.traffic_class == ATM_ANYCLASS || vcc->qos.rxtp.traffic_class == ATM_ANYCLASS) { error = -EINVAL; goto out; } if (!vcc->qos.txtp.traffic_class && !vcc->qos.rxtp.traffic_class) { error = -EINVAL; goto out; } vcc->remote = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote); if (flags & O_NONBLOCK) { sock->state = SS_CONNECTING; error = -EINPROGRESS; goto out; } error = 0; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); if (!signal_pending(current)) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); continue; } pr_debug("*ABORT*\n"); /* * This is tricky: * Kernel ---close--> Demon * Kernel <--close--- Demon * or * Kernel ---close--> Demon * Kernel <--error--- Demon * or * Kernel ---close--> Demon * Kernel <--okay---- Demon * Kernel <--close--- Demon */ sigd_enq(vcc, as_close, NULL, NULL, NULL); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } if (!sk->sk_err) while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } clear_bit(ATM_VF_REGIS, &vcc->flags); clear_bit(ATM_VF_RELEASED, &vcc->flags); clear_bit(ATM_VF_CLOSE, &vcc->flags); /* we're gone now but may connect later */ error = -EINTR; break; } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!sigd) { error = -EUNATCH; goto out; } if (sk->sk_err) { error = -sk->sk_err; goto out; } } vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp); vcc->qos.txtp.pcr = 0; vcc->qos.txtp.min_pcr = 0; error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci); if (!error) sock->state = SS_CONNECTED; else (void)svc_disconnect(vcc); out: release_sock(sk); return error; } static int svc_listen(struct socket *sock, int backlog) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); /* let server handle listen on unbound sockets */ if (test_bit(ATM_VF_SESSION, &vcc->flags)) { error = -EINVAL; goto out; } if (test_bit(ATM_VF_LISTEN, &vcc->flags)) { error = -EADDRINUSE; goto out; } set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } set_bit(ATM_VF_LISTEN, &vcc->flags); vcc_insert_socket(sk); sk->sk_max_ack_backlog = backlog > 0 ? backlog : ATM_BACKLOG_DEFAULT; error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; struct atmsvc_msg *msg; struct atm_vcc *old_vcc = ATM_SD(sock); struct atm_vcc *new_vcc; int error; lock_sock(sk); error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; new_vcc = ATM_SD(newsock); pr_debug("%p -> %p\n", old_vcc, new_vcc); while (1) { DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (!(skb = skb_dequeue(&sk->sk_receive_queue)) && sigd) { if (test_bit(ATM_VF_RELEASED, &old_vcc->flags)) break; if (test_bit(ATM_VF_CLOSE, &old_vcc->flags)) { error = -sk->sk_err; break; } if (flags & O_NONBLOCK) { error = -EAGAIN; break; } release_sock(sk); schedule(); lock_sock(sk); if (signal_pending(current)) { error = -ERESTARTSYS; break; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!skb) { error = -EUNATCH; goto out; } msg = (struct atmsvc_msg *)skb->data; new_vcc->qos = msg->qos; set_bit(ATM_VF_HASQOS, &new_vcc->flags); new_vcc->remote = msg->svc; new_vcc->local = msg->local; new_vcc->sap = msg->sap; error = vcc_connect(newsock, msg->pvc.sap_addr.itf, msg->pvc.sap_addr.vpi, msg->pvc.sap_addr.vci); dev_kfree_skb(skb); sk_acceptq_removed(sk); if (error) { sigd_enq2(NULL, as_reject, old_vcc, NULL, NULL, &old_vcc->qos, error); error = error == -EAGAIN ? -EBUSY : error; goto out; } /* wait should be short, so we ignore the non-blocking flag */ set_bit(ATM_VF_WAITING, &new_vcc->flags); sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &new_vcc->flags) || !sigd) break; release_sock(sk); schedule(); lock_sock(sk); } finish_wait(sk_sleep(sk_atm(new_vcc)), &wait); if (!sigd) { error = -EUNATCH; goto out; } if (!sk_atm(new_vcc)->sk_err) break; if (sk_atm(new_vcc)->sk_err != ERESTARTSYS) { error = -sk_atm(new_vcc)->sk_err; goto out; } } newsock->state = SS_CONNECTED; out: release_sock(sk); return error; } static int svc_getname(struct socket *sock, struct sockaddr *sockaddr, int peer) { struct sockaddr_atmsvc *addr; addr = (struct sockaddr_atmsvc *) sockaddr; memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local, sizeof(struct sockaddr_atmsvc)); return sizeof(struct sockaddr_atmsvc); } int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) { struct sock *sk = sk_atm(vcc); DEFINE_WAIT(wait); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) { break; } schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) return -EUNATCH; return -sk->sk_err; } static int svc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int value, error = 0; lock_sock(sk); switch (optname) { case SO_ATMSAP: if (level != SOL_ATM || optlen != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&vcc->sap, optval, optlen)) { error = -EFAULT; goto out; } set_bit(ATM_VF_HASSAP, &vcc->flags); break; case SO_MULTIPOINT: if (level != SOL_ATM || optlen != sizeof(int)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&value, optval, sizeof(int))) { error = -EFAULT; goto out; } if (value == 1) set_bit(ATM_VF_SESSION, &vcc->flags); else if (value == 0) clear_bit(ATM_VF_SESSION, &vcc->flags); else error = -EINVAL; break; default: error = vcc_setsockopt(sock, level, optname, optval, optlen); } out: release_sock(sk); return error; } static int svc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int error = 0, len; lock_sock(sk); if (!__SO_LEVEL_MATCH(optname, level) || optname != SO_ATMSAP) { error = vcc_getsockopt(sock, level, optname, optval, optlen); goto out; } if (get_user(len, optlen)) { error = -EFAULT; goto out; } if (len != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_to_user(optval, &ATM_SD(sock)->sap, sizeof(struct atm_sap))) { error = -EFAULT; goto out; } out: release_sock(sk); return error; } static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_addparty, NULL, NULL, (struct sockaddr_atmsvc *) sockaddr); if (flags & O_NONBLOCK) { error = -EINPROGRESS; goto out; } pr_debug("added wait queue\n"); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_dropparty(struct socket *sock, int ep_ref) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int error, ep_ref; struct sockaddr_atmsvc sa; struct atm_vcc *vcc = ATM_SD(sock); switch (cmd) { case ATM_ADDPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&sa, (void __user *) arg, sizeof(sa))) return -EFAULT; error = svc_addparty(sock, (struct sockaddr *)&sa, sizeof(sa), 0); break; case ATM_DROPPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&ep_ref, (void __user *) arg, sizeof(int))) return -EFAULT; error = svc_dropparty(sock, ep_ref); break; default: error = vcc_ioctl(sock, cmd, arg); } return error; } #ifdef CONFIG_COMPAT static int svc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* The definition of ATM_ADDPARTY uses the size of struct atm_iobuf. But actually it takes a struct sockaddr_atmsvc, which doesn't need compat handling. So all we have to do is fix up cmd... */ if (cmd == COMPAT_ATM_ADDPARTY) cmd = ATM_ADDPARTY; if (cmd == ATM_ADDPARTY || cmd == ATM_DROPPARTY) return svc_ioctl(sock, cmd, arg); else return vcc_compat_ioctl(sock, cmd, arg); } #endif /* CONFIG_COMPAT */ static const struct proto_ops svc_proto_ops = { .family = PF_ATMSVC, .owner = THIS_MODULE, .release = svc_release, .bind = svc_bind, .connect = svc_connect, .socketpair = sock_no_socketpair, .accept = svc_accept, .getname = svc_getname, .poll = vcc_poll, .ioctl = svc_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = svc_compat_ioctl, #endif .gettstamp = sock_gettstamp, .listen = svc_listen, .shutdown = svc_shutdown, .setsockopt = svc_setsockopt, .getsockopt = svc_getsockopt, .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static int svc_create(struct net *net, struct socket *sock, int protocol, int kern) { int error; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; error = vcc_create(net, sock, protocol, AF_ATMSVC, kern); if (error) return error; ATM_SD(sock)->local.sas_family = AF_ATMSVC; ATM_SD(sock)->remote.sas_family = AF_ATMSVC; return 0; } static const struct net_proto_family svc_family_ops = { .family = PF_ATMSVC, .create = svc_create, .owner = THIS_MODULE, }; /* * Initialize the ATM SVC protocol family */ int __init atmsvc_init(void) { return sock_register(&svc_family_ops); } void atmsvc_exit(void) { sock_unregister(PF_ATMSVC); } |
| 7 3 7 7 7 7 7 2 2 2 2 6 2 6 6 7 7 7 7 7 7 7 3 3 6 3 3 2 2 2 2 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright Red Hat Inc. 2017 * * This file is part of the SCTP kernel implementation * * These functions manipulate sctp stream queue/scheduling. * * Please send any bug reports or fixes you make to the * email addresched(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> */ #include <linux/list.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> /* Priority handling * RFC DRAFT ndata section 3.4 */ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p) { p->users++; return p; } static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p) { if (p && --p->users == 0) kfree(p); } static struct sctp_stream_priorities *sctp_sched_prio_new_head( struct sctp_stream *stream, int prio, gfp_t gfp) { struct sctp_stream_priorities *p; p = kmalloc(sizeof(*p), gfp); if (!p) return NULL; INIT_LIST_HEAD(&p->prio_sched); INIT_LIST_HEAD(&p->active); p->next = NULL; p->prio = prio; p->users = 1; return p; } static struct sctp_stream_priorities *sctp_sched_prio_get_head( struct sctp_stream *stream, int prio, gfp_t gfp) { struct sctp_stream_priorities *p; int i; /* Look into scheduled priorities first, as they are sorted and * we can find it fast IF it's scheduled. */ list_for_each_entry(p, &stream->prio_list, prio_sched) { if (p->prio == prio) return sctp_sched_prio_head_get(p); if (p->prio > prio) break; } /* No luck. So we search on all streams now. */ for (i = 0; i < stream->outcnt; i++) { if (!SCTP_SO(stream, i)->ext) continue; p = SCTP_SO(stream, i)->ext->prio_head; if (!p) /* Means all other streams won't be initialized * as well. */ break; if (p->prio == prio) return sctp_sched_prio_head_get(p); } /* If not even there, allocate a new one. */ return sctp_sched_prio_new_head(stream, prio, gfp); } static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p) { struct list_head *pos; pos = p->next->prio_list.next; if (pos == &p->active) pos = pos->next; p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list); } static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute) { bool scheduled = false; if (!list_empty(&soute->prio_list)) { struct sctp_stream_priorities *prio_head = soute->prio_head; /* Scheduled */ scheduled = true; if (prio_head->next == soute) /* Try to move to the next stream */ sctp_sched_prio_next_stream(prio_head); list_del_init(&soute->prio_list); /* Also unsched the priority if this was the last stream */ if (list_empty(&prio_head->active)) { list_del_init(&prio_head->prio_sched); /* If there is no stream left, clear next */ prio_head->next = NULL; } } return scheduled; } static void sctp_sched_prio_sched(struct sctp_stream *stream, struct sctp_stream_out_ext *soute) { struct sctp_stream_priorities *prio, *prio_head; prio_head = soute->prio_head; /* Nothing to do if already scheduled */ if (!list_empty(&soute->prio_list)) return; /* Schedule the stream. If there is a next, we schedule the new * one before it, so it's the last in round robin order. * If there isn't, we also have to schedule the priority. */ if (prio_head->next) { list_add(&soute->prio_list, prio_head->next->prio_list.prev); return; } list_add(&soute->prio_list, &prio_head->active); prio_head->next = soute; list_for_each_entry(prio, &stream->prio_list, prio_sched) { if (prio->prio > prio_head->prio) { list_add(&prio_head->prio_sched, prio->prio_sched.prev); return; } } list_add_tail(&prio_head->prio_sched, &stream->prio_list); } static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, __u16 prio, gfp_t gfp) { struct sctp_stream_out *sout = SCTP_SO(stream, sid); struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; old = soute->prio_head; if (old && old->prio == prio) return 0; prio_head = sctp_sched_prio_get_head(stream, prio, gfp); if (!prio_head) return -ENOMEM; reschedule = sctp_sched_prio_unsched(soute); soute->prio_head = prio_head; if (reschedule) sctp_sched_prio_sched(stream, soute); sctp_sched_prio_head_put(old); return 0; } static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, __u16 *value) { *value = SCTP_SO(stream, sid)->ext->prio_head->prio; return 0; } static int sctp_sched_prio_init(struct sctp_stream *stream) { INIT_LIST_HEAD(&stream->prio_list); return 0; } static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->prio_list); return sctp_sched_prio_set(stream, sid, 0, gfp); } static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) { sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head); SCTP_SO(stream, sid)->ext->prio_head = NULL; } static void sctp_sched_prio_free(struct sctp_stream *stream) { struct sctp_stream_priorities *prio, *n; LIST_HEAD(list); int i; /* As we don't keep a list of priorities, to avoid multiple * frees we have to do it in 3 steps: * 1. unsched everyone, so the lists are free to use in 2. * 2. build the list of the priorities * 3. free the list */ sctp_sched_prio_unsched_all(stream); for (i = 0; i < stream->outcnt; i++) { if (!SCTP_SO(stream, i)->ext) continue; prio = SCTP_SO(stream, i)->ext->prio_head; if (prio && list_empty(&prio->prio_sched)) list_add(&prio->prio_sched, &list); } list_for_each_entry_safe(prio, n, &list, prio_sched) { list_del_init(&prio->prio_sched); kfree(prio); } } static void sctp_sched_prio_enqueue(struct sctp_outq *q, struct sctp_datamsg *msg) { struct sctp_stream *stream; struct sctp_chunk *ch; __u16 sid; ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; sctp_sched_prio_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) { struct sctp_stream *stream = &q->asoc->stream; struct sctp_stream_priorities *prio; struct sctp_stream_out_ext *soute; struct sctp_chunk *ch = NULL; /* Bail out quickly if queue is empty */ if (list_empty(&q->out_chunk_list)) goto out; /* Find which chunk is next. It's easy, it's either the current * one or the first chunk on the next active stream. */ if (stream->out_curr) { soute = stream->out_curr->ext; } else { prio = list_entry(stream->prio_list.next, struct sctp_stream_priorities, prio_sched); soute = prio->next; } ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); sctp_sched_dequeue_common(q, ch); out: return ch; } static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_priorities *prio; struct sctp_stream_out_ext *soute; __u16 sid; /* Last chunk on that msg, move to the next stream on * this priority. */ sid = sctp_chunk_stream_no(ch); soute = SCTP_SO(&q->asoc->stream, sid)->ext; prio = soute->prio_head; sctp_sched_prio_next_stream(prio); if (list_empty(&soute->outq)) sctp_sched_prio_unsched(soute); } static void sctp_sched_prio_sched_all(struct sctp_stream *stream) { struct sctp_association *asoc; struct sctp_stream_out *sout; struct sctp_chunk *ch; asoc = container_of(stream, struct sctp_association, stream); list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { __u16 sid; sid = sctp_chunk_stream_no(ch); sout = SCTP_SO(stream, sid); if (sout->ext) sctp_sched_prio_sched(stream, sout->ext); } } static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) { struct sctp_stream_priorities *p, *tmp; struct sctp_stream_out_ext *soute, *souttmp; list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched) list_for_each_entry_safe(soute, souttmp, &p->active, prio_list) sctp_sched_prio_unsched(soute); } static struct sctp_sched_ops sctp_sched_prio = { .set = sctp_sched_prio_set, .get = sctp_sched_prio_get, .init = sctp_sched_prio_init, .init_sid = sctp_sched_prio_init_sid, .free_sid = sctp_sched_prio_free_sid, .free = sctp_sched_prio_free, .enqueue = sctp_sched_prio_enqueue, .dequeue = sctp_sched_prio_dequeue, .dequeue_done = sctp_sched_prio_dequeue_done, .sched_all = sctp_sched_prio_sched_all, .unsched_all = sctp_sched_prio_unsched_all, }; void sctp_sched_ops_prio_init(void) { sctp_sched_ops_register(SCTP_SS_PRIO, &sctp_sched_prio); } |
| 10 4 6 46 46 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * x_tables core - Backend for {ip,ip6,arp}_tables * * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on existing ip_tables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) struct xt_template { struct list_head list; /* called when table is needed in the given netns */ int (*table_init)(struct net *net); struct module *me; /* A unique name... */ char name[XT_TABLE_MAXNAMELEN]; }; static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; }; struct compat_delta { unsigned int offset; /* offset in kernel */ int delta; /* delta in 32bit user land */ }; struct xt_af { struct mutex mutex; struct list_head match; struct list_head target; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct mutex compat_mutex; struct compat_delta *compat_tab; unsigned int number; /* number of slots in compat_tab[] */ unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; static unsigned int xt_pernet_id __read_mostly; static struct xt_af *xt __read_mostly; static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_UNSPEC] = "x", [NFPROTO_IPV4] = "ip", [NFPROTO_ARP] = "arp", [NFPROTO_BRIDGE] = "eb", [NFPROTO_IPV6] = "ip6", }; /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_add(&target->list, &xt[af].target); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_target); void xt_unregister_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_del(&target->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_target); int xt_register_targets(struct xt_target *target, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_target(&target[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_targets(target, i); return err; } EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { while (n-- > 0) xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); int xt_register_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_add(&match->list, &xt[af].match); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_match); void xt_unregister_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_del(&match->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_match); int xt_register_matches(struct xt_match *match, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_match(&match[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_matches(match, i); return err; } EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { while (n-- > 0) xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision == revision) { if (try_module_get(m->me)) { mutex_unlock(&xt[af].mutex); return m; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_match(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_match); struct xt_match * xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) { struct xt_match *match; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); match = xt_find_match(nfproto, name, revision); if (IS_ERR(match)) { request_module("%st_%s", xt_prefix[nfproto], name); match = xt_find_match(nfproto, name, revision); } return match; } EXPORT_SYMBOL_GPL(xt_request_find_match); /* Find target, grabs ref. Returns ERR_PTR() on error. */ static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision == revision) { if (try_module_get(t->me)) { mutex_unlock(&xt[af].mutex); return t; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_target(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); target = xt_find_target(af, name, revision); if (IS_ERR(target)) { request_module("%st_%s", xt_prefix[af], name); target = xt_find_target(af, name, revision); } return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); static int xt_obj_to_user(u16 __user *psize, u16 size, void __user *pname, const char *name, u8 __user *prev, u8 rev) { if (put_user(size, psize)) return -EFAULT; if (copy_to_user(pname, name, strlen(name) + 1)) return -EFAULT; if (put_user(rev, prev)) return -EFAULT; return 0; } #define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \ U->u.user.name, K->u.kernel.TYPE->name, \ &U->u.user.revision, K->u.kernel.TYPE->revision) int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size) { usersize = usersize ? : size; if (copy_to_user(dst, src, usersize)) return -EFAULT; if (usersize != aligned_size && clear_user(dst + usersize, aligned_size - usersize)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(xt_data_to_user); #define XT_DATA_TO_USER(U, K, TYPE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ K->u.kernel.TYPE->TYPE##size, \ XT_ALIGN(K->u.kernel.TYPE->TYPE##size)) int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u) { return XT_OBJ_TO_USER(u, m, match, 0) || XT_DATA_TO_USER(u, m, match); } EXPORT_SYMBOL_GPL(xt_match_to_user); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u) { return XT_OBJ_TO_USER(u, t, target, 0) || XT_DATA_TO_USER(u, t, target); } EXPORT_SYMBOL_GPL(xt_target_to_user); static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_match *m; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) *bestp = m->revision; if (m->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_target *t; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) *bestp = t->revision; if (t->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } /* Returns true or false (if no such extension at all) */ int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err) { int have_rev, best = -1; if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { *err = -ENOENT; return 0; } *err = best; if (!have_rev) *err = -EPROTONOSUPPORT; return 1; } EXPORT_SYMBOL_GPL(xt_find_revision); static char * textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; static const char *const arp_names[] = { "INPUT", "FORWARD", "OUTPUT", }; const char *const *names; unsigned int i, max; char *p = buf; bool np = false; int res; names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : ARRAY_SIZE(inetbr_names); *p = '\0'; for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); if (res > 0) { size -= res; p += res; } np = true; } return buf; } /** * xt_check_proc_name - check that name is suitable for /proc file creation * * @name: file name candidate * @size: length of buffer * * some x_tables modules wish to create a file in /proc. * This function makes sure that the name is suitable for this * purpose, it checks that name is NUL terminated and isn't a 'special' * name, like "..". * * returns negative number on error or 0 if name is useable. */ int xt_check_proc_name(const char *name, unsigned int size) { if (name[0] == '\0') return -EINVAL; if (strnlen(name, size) == size) return -ENAMETOOLONG; if (strcmp(name, ".") == 0 || strcmp(name, "..") == 0 || strchr(name, '/')) return -EINVAL; return 0; } EXPORT_SYMBOL(xt_check_proc_name); int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ pr_err_ratelimited("%s_tables: %s.%u match: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->match->name, par->match->revision, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s match: only valid in %s table, not %s\n", xt_prefix[par->family], par->match->name, par->match->table, par->table); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s match: used from hooks %s, but only valid from %s\n", xt_prefix[par->family], par->match->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->match->hooks, par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s match: only valid for protocol %u\n", xt_prefix[par->family], par->match->name, par->match->proto); return -EINVAL; } if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target * * @match: beginning of xt_entry_match * @target: beginning of this rules target (alleged end of matches) * @alignment: alignment requirement of match structures * * Validates that all matches add up to the beginning of the target, * and that each match covers at least the base structure size. * * Return: 0 on success, negative errno on failure. */ static int xt_check_entry_match(const char *match, const char *target, const size_t alignment) { const struct xt_entry_match *pos; int length = target - match; if (length == 0) /* no matches */ return 0; pos = (struct xt_entry_match *)match; do { if ((unsigned long)pos % alignment) return -EINVAL; if (length < (int)sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size < sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size > length) return -EINVAL; length -= pos->u.match_size; pos = ((void *)((char *)(pos) + (pos)->u.match_size)); } while (length > 0); return 0; } /** xt_check_table_hooks - check hook entry points are sane * * @info xt_table_info to check * @valid_hooks - hook entry points that we can enter from * * Validates that the hook entry and underflows points are set up. * * Return: 0 on success, negative errno on failure. */ int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks) { const char *err = "unsorted underflow"; unsigned int i, max_uflow, max_entry; bool check_hooks = false; BUILD_BUG_ON(ARRAY_SIZE(info->hook_entry) != ARRAY_SIZE(info->underflow)); max_entry = 0; max_uflow = 0; for (i = 0; i < ARRAY_SIZE(info->hook_entry); i++) { if (!(valid_hooks & (1 << i))) continue; if (info->hook_entry[i] == 0xFFFFFFFF) return -EINVAL; if (info->underflow[i] == 0xFFFFFFFF) return -EINVAL; if (check_hooks) { if (max_uflow > info->underflow[i]) goto error; if (max_uflow == info->underflow[i]) { err = "duplicate underflow"; goto error; } if (max_entry > info->hook_entry[i]) { err = "unsorted entry"; goto error; } if (max_entry == info->hook_entry[i]) { err = "duplicate entry"; goto error; } } max_entry = info->hook_entry[i]; max_uflow = info->underflow[i]; check_hooks = true; } return 0; error: pr_err_ratelimited("%s at hook %d\n", err, i); return -EINVAL; } EXPORT_SYMBOL(xt_check_table_hooks); static bool verdict_ok(int verdict) { if (verdict > 0) return true; if (verdict < 0) { int v = -verdict - 1; if (verdict == XT_RETURN) return true; switch (v) { case NF_ACCEPT: return true; case NF_DROP: return true; case NF_QUEUE: return true; default: break; } return false; } return false; } static bool error_tg_ok(unsigned int usersize, unsigned int kernsize, const char *msg, unsigned int msglen) { return usersize == kernsize && strnlen(msg, msglen) < msglen; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { struct xt_af *xp = &xt[af]; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (WARN_ON(!xp->compat_tab)) return -ENOMEM; if (xp->cur >= xp->number) return -EINVAL; if (xp->cur) delta += xp->compat_tab[xp->cur - 1].delta; xp->compat_tab[xp->cur].offset = offset; xp->compat_tab[xp->cur].delta = delta; xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (xt[af].compat_tab) { vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { struct compat_delta *tmp = xt[af].compat_tab; int mid, left = 0, right = xt[af].cur - 1; while (left <= right) { mid = (left + right) >> 1; if (offset > tmp[mid].offset) left = mid + 1; else if (offset < tmp[mid].offset) right = mid - 1; else return mid ? tmp[mid - 1].delta : 0; } return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); int xt_compat_init_offsets(u8 af, unsigned int number) { size_t mem; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (!number || number > (INT_MAX / sizeof(struct compat_delta))) return -EINVAL; if (WARN_ON(xt[af].compat_tab)) return -EINVAL; mem = sizeof(struct compat_delta) * number; if (mem > XT_MAX_TABLE_SIZE) return -ENOMEM; xt[af].compat_tab = vmalloc(mem); if (!xt[af].compat_tab) return -ENOMEM; xt[af].number = number; xt[af].cur = 0; return 0; } EXPORT_SYMBOL(xt_compat_init_offsets); int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_match_offset); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; m = *dstptr; memcpy(m, cm, sizeof(*cm)); if (match->compat_from_user) match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); msize += off; m->u.user.match_size = msize; strlcpy(name, match->name, sizeof(name)); module_put(match->me); strncpy(m->u.user.name, name, sizeof(m->u.user.name)); *size += off; *dstptr += msize; } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); #define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ C_SIZE, \ COMPAT_XT_ALIGN(C_SIZE)) int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; if (XT_OBJ_TO_USER(cm, m, match, msize)) return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm))) return -EFAULT; } *size -= off; *dstptr += msize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_to_user); /* non-compat version may have padding after verdict */ struct compat_xt_standard_target { struct compat_xt_entry_target t; compat_uint_t verdict; }; struct compat_xt_error_target { struct compat_xt_entry_target t; char errorname[XT_FUNCTION_MAXNAMELEN]; }; int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct compat_xt_entry_target *t; const char *e = base; if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct compat_xt_standard_target *st = (const void *)t; if (COMPAT_XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct compat_xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } /* compat_xt_entry match has less strict alignment requirements, * otherwise they are identical. In case of padding differences * we need to add compat version of xt_check_entry_match. */ BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match)); return xt_check_entry_match(elems, base + target_offset, __alignof__(struct compat_xt_entry_match)); } EXPORT_SYMBOL(xt_compat_check_entry_offsets); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ /** * xt_check_entry_offsets - validate arp/ip/ip6t_entry * * @base: pointer to arp/ip/ip6t_entry * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems * @target_offset: the arp/ip/ip6_t->target_offset * @next_offset: the arp/ip/ip6_t->next_offset * * validates that target_offset and next_offset are sane and that all * match sizes (if any) align with the target offset. * * This function does not validate the targets or matches themselves, it * only tests that all the offsets and sizes are correct, that all * match structures are aligned, and that the last structure ends where * the target structure begins. * * Also see xt_compat_check_entry_offsets for CONFIG_NETFILTER_XTABLES_COMPAT version. * * The arp/ip/ip6t_entry structure @base must have passed following tests: * - it must point to a valid memory location * - base to base + next_offset must be accessible, i.e. not exceed allocated * length. * * A well-formed entry looks like this: * * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry * e->elems[]-----' | | * matchsize | | * matchsize | | * | | * target_offset---------------------------------' | * next_offset---------------------------------------------------' * * elems[]: flexible array member at end of ip(6)/arpt_entry struct. * This is where matches (if any) and the target reside. * target_offset: beginning of target. * next_offset: start of the next rule; also: size of this rule. * Since targets have a minimum size, target_offset + minlen <= next_offset. * * Every match stores its size, sum of sizes must not exceed target_offset. * * Return: 0 on success, negative errno on failure. */ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct xt_entry_target *t; const char *e = base; /* target start is within the ip/ip6/arpt_entry struct */ if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct xt_standard_target *st = (const void *)t; if (XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } return xt_check_entry_match(elems, base + target_offset, __alignof__(struct xt_entry_match)); } EXPORT_SYMBOL(xt_check_entry_offsets); /** * xt_alloc_entry_offsets - allocate array to store rule head offsets * * @size: number of entries * * Return: NULL or zeroed kmalloc'd or vmalloc'd array */ unsigned int *xt_alloc_entry_offsets(unsigned int size) { if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int)) return NULL; return kvcalloc(size, sizeof(unsigned int), GFP_KERNEL); } EXPORT_SYMBOL(xt_alloc_entry_offsets); /** * xt_find_jump_offset - check if target is a valid jump offset * * @offsets: array containing all valid rule start offsets of a rule blob * @target: the jump target to search for * @size: entries in @offset */ bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size) { int m, low = 0, hi = size; while (hi > low) { m = (low + hi) / 2u; if (offsets[m] > target) hi = m; else if (offsets[m] < target) low = m + 1; else return true; } return false; } EXPORT_SYMBOL(xt_find_jump_offset); int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, par->target->revision, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s target: only valid in %s table, not %s\n", xt_prefix[par->family], par->target->name, par->target->table, par->table); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s target: used from hooks %s, but only usable from %s\n", xt_prefix[par->family], par->target->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->target->hooks, par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s target: only valid for protocol %u\n", xt_prefix[par->family], par->target->name, par->target->proto); return -EINVAL; } if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_target); /** * xt_copy_counters - copy counters and metadata from a sockptr_t * * @arg: src sockptr * @len: alleged size of userspace memory * @info: where to store the xt_counters_info metadata * * Copies counter meta data from @user and stores it in @info. * * vmallocs memory to hold the counters, then copies the counter data * from @user to the new memory and returns a pointer to it. * * If called from a compat syscall, @info gets converted automatically to the * 64bit representation. * * The metadata associated with the counters is stored in @info. * * Return: returns pointer that caller has to test via IS_ERR(). * If IS_ERR is false, caller has to vfree the pointer. */ void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info) { size_t offset; void *mem; u64 size; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) { /* structures only differ in size due to alignment */ struct compat_xt_counters_info compat_tmp; if (len <= sizeof(compat_tmp)) return ERR_PTR(-EINVAL); len -= sizeof(compat_tmp); if (copy_from_sockptr(&compat_tmp, arg, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; offset = sizeof(compat_tmp); } else #endif { if (len <= sizeof(*info)) return ERR_PTR(-EINVAL); len -= sizeof(*info); if (copy_from_sockptr(info, arg, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); offset = sizeof(*info); } info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; if (size != (u64)len) return ERR_PTR(-EINVAL); mem = vmalloc(len); if (!mem) return ERR_PTR(-ENOMEM); if (copy_from_sockptr_offset(mem, arg, offset, len) == 0) return mem; vfree(mem); return ERR_PTR(-EFAULT); } EXPORT_SYMBOL_GPL(xt_copy_counters); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; t = *dstptr; memcpy(t, ct, sizeof(*ct)); if (target->compat_from_user) target->compat_from_user(t->data, ct->data); else memcpy(t->data, ct->data, tsize - sizeof(*ct)); tsize += off; t->u.user.target_size = tsize; strlcpy(name, target->name, sizeof(name)); module_put(target->me); strncpy(t->u.user.name, name, sizeof(t->u.user.name)); *size += off; *dstptr += tsize; } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; if (XT_OBJ_TO_USER(ct, t, target, tsize)) return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct))) return -EFAULT; } *size -= off; *dstptr += tsize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_target_to_user); #endif struct xt_table_info *xt_alloc_table_info(unsigned int size) { struct xt_table_info *info = NULL; size_t sz = sizeof(*info) + size; if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE) return NULL; info = kvmalloc(sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; memset(info, 0, sizeof(*info)); info->size = size; return info; } EXPORT_SYMBOL(xt_alloc_table_info); void xt_free_table_info(struct xt_table_info *info) { int cpu; if (info->jumpstack != NULL) { for_each_possible_cpu(cpu) kvfree(info->jumpstack[cpu]); kvfree(info->jumpstack); } kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { mutex_unlock(&xt[af].mutex); return t; } } mutex_unlock(&xt[af].mutex); return NULL; } EXPORT_SYMBOL(xt_find_table); /* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct module *owner = NULL; struct xt_template *tmpl; struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; /* Table doesn't exist in this netns, check larval list */ list_for_each_entry(tmpl, &xt_templates[af], list) { int err; if (strcmp(tmpl->name, name)) continue; if (!try_module_get(tmpl->me)) goto out; owner = tmpl->me; mutex_unlock(&xt[af].mutex); err = tmpl->table_init(net); if (err < 0) { module_put(owner); return ERR_PTR(err); } mutex_lock(&xt[af].mutex); break; } /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0) return t; module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(xt_find_table_lock); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_table *t = xt_find_table_lock(net, af, name); #ifdef CONFIG_MODULES if (IS_ERR(t)) { int err = request_module("%stable_%s", xt_prefix[af], name); if (err < 0) return ERR_PTR(err); t = xt_find_table_lock(net, af, name); } #endif return t; } EXPORT_SYMBOL_GPL(xt_request_find_table_lock); void xt_table_unlock(struct xt_table *table) { mutex_unlock(&xt[table->af].mutex); } EXPORT_SYMBOL_GPL(xt_table_unlock); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_lock); void xt_compat_unlock(u_int8_t af) { mutex_unlock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); struct static_key xt_tee_enabled __read_mostly; EXPORT_SYMBOL_GPL(xt_tee_enabled); static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = kvzalloc(size, GFP_KERNEL); else i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) return -ENOMEM; /* ruleset without jumps -- no stack needed */ if (i->stacksize == 0) return 0; /* Jumpstack needs to be able to record two full callchains, one * from the first rule set traversal, plus one table reentrancy * via -j TEE without clobbering the callchain that brought us to * TEE target. * * This is done by allocating two jumpstacks per cpu, on reentry * the upper half of the stack is used. * * see the jumpstack setup in ipt_do_table() for more details. */ size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (i->jumpstack[cpu] == NULL) /* * Freeing will be done later on by the callers. The * chain is: xt_replace_table -> __do_replace -> * do_replace -> xt_free_table_info. */ return -ENOMEM; } return 0; } struct xt_counters *xt_counters_alloc(unsigned int counters) { struct xt_counters *mem; if (counters == 0 || counters > INT_MAX / sizeof(*mem)) return NULL; counters *= sizeof(*mem); if (counters > XT_MAX_TABLE_SIZE) return NULL; return vzalloc(counters); } EXPORT_SYMBOL(xt_counters_alloc); struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); if (ret < 0) { *error = ret; return NULL; } /* Do the substitution. */ local_bh_disable(); private = table->private; /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; /* * Ensure contents of newinfo are visible before assigning to * private. */ smp_wmb(); table->private = newinfo; /* make sure all cpus see new ->private value */ smp_mb(); /* * Even though table entries have now been swapped, other CPU's * may still be using the old entries... */ local_bh_enable(); /* ... so wait for even xt_recseq on all cpus */ for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); u32 seq = raw_read_seqcount(s); if (seq & 1) { do { cond_resched(); cpu_relax(); } while (seq == raw_read_seqcount(s)); } } audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : AUDIT_XT_OP_REPLACE, GFP_KERNEL); return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table_info *private; struct xt_table *t, *table; int ret; /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; } mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ list_for_each_entry(t, &xt_net->tables[table->af], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; goto unlock; } } /* Simplifies replace_table code. */ table->private = bootstrap; if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ private->initial_entries = private->number; list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); kfree(table); out: return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); void *xt_unregister_table(struct xt_table *table) { struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); private = table->private; list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); kfree(table->ops); kfree(table); return private; } EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); mutex_lock(&xt[af].mutex); return seq_list_start(&xt_net->tables[af], *pos); } static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); return seq_list_next(v, &xt_net->tables[af], pos); } static void xt_table_seq_stop(struct seq_file *seq, void *v) { u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); if (*table->name) seq_printf(seq, "%s\n", table->name); return 0; } static const struct seq_operations xt_table_seq_ops = { .start = xt_table_seq_start, .next = xt_table_seq_next, .stop = xt_table_seq_stop, .show = xt_table_seq_show, }; /* * Traverse state for ip{,6}_{tables,matches} for helping crossing * the multi-AF mutexes. */ struct nf_mttg_trav { struct list_head *head, *curr; uint8_t class; }; enum { MTTG_TRAV_INIT, MTTG_TRAV_NFP_UNSPEC, MTTG_TRAV_NFP_SPEC, MTTG_TRAV_DONE, }; static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, bool is_target) { static const uint8_t next_class[] = { [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) ++(*ppos); switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; mutex_lock(&xt[NFPROTO_UNSPEC].mutex); trav->head = trav->curr = is_target ? &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; break; case MTTG_TRAV_NFP_UNSPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); mutex_lock(&xt[nfproto].mutex); trav->head = trav->curr = is_target ? &xt[nfproto].target : &xt[nfproto].match; trav->class = next_class[trav->class]; break; case MTTG_TRAV_NFP_SPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; fallthrough; default: return NULL; } return trav; } static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, bool is_target) { struct nf_mttg_trav *trav = seq->private; unsigned int j; trav->class = MTTG_TRAV_INIT; for (j = 0; j < *pos; ++j) if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) return NULL; return trav; } static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); break; case MTTG_TRAV_NFP_SPEC: mutex_unlock(&xt[nfproto].mutex); break; } } static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, false); } static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, false); } static int xt_match_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_match *match; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); if (*match->name) seq_printf(seq, "%s\n", match->name); } return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, true); } static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_target *target; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); if (*target->name) seq_printf(seq, "%s\n", target->name); } return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; #define FORMAT_TABLES "_tables_names" #define FORMAT_MATCHES "_tables_matches" #define FORMAT_TARGETS "_tables_targets" #endif /* CONFIG_PROC_FS */ /** * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * * This function will create the nf_hook_ops that the x_table needs * to hand to xt_hook_link_net(). */ struct nf_hook_ops * xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; if (!num_hooks) return ERR_PTR(-EINVAL); ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; hook_mask >>= 1, ++hooknum) { if (!(hook_mask & 1)) continue; ops[i].hook = fn; ops[i].pf = table->af; ops[i].hooknum = hooknum; ops[i].priority = table->priority; ++i; } return ops; } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { int ret = -EEXIST, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) goto out_unlock; } ret = -ENOMEM; t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) goto out_unlock; BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); strscpy(t->name, table->name, sizeof(t->name)); t->table_init = table_init; t->me = table->me; list_add(&t->list, &xt_templates[af]); ret = 0; out_unlock: mutex_unlock(&xt[af].mutex); return ret; } EXPORT_SYMBOL_GPL(xt_register_template); void xt_unregister_template(const struct xt_table *table) { struct xt_template *t; int af = table->af; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (strcmp(table->name, t->name)) continue; list_del(&t->list); mutex_unlock(&xt[af].mutex); kfree(t); return; } mutex_unlock(&xt[af].mutex); WARN_ON_ONCE(1); } EXPORT_SYMBOL_GPL(xt_unregister_template); int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif if (af >= ARRAY_SIZE(xt_prefix)) return -EINVAL; #ifdef CONFIG_PROC_FS root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops, sizeof(struct seq_net_private), (void *)(unsigned long)af); if (!proc) goto out; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_match_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_tables; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_target_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_matches; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; #ifdef CONFIG_PROC_FS out_remove_matches: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out_remove_tables: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out: return -1; #endif } EXPORT_SYMBOL_GPL(xt_proto_init); void xt_proto_fini(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); /** * xt_percpu_counter_alloc - allocate x_tables rule counter * * @state: pointer to xt_percpu allocation state * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct * * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then * contain the address of the real (percpu) counter. * * Rule evaluation needs to use xt_get_this_cpu_counter() helper * to fetch the real percpu counter. * * To speed up allocation and improve data locality, a 4kb block is * allocated. Freeing any counter may free an entire block, so all * counters allocated using the same state must be freed at the same * time. * * xt_percpu_counter_alloc_state contains the base address of the * allocated page and the current sub-offset. * * returns false on error. */ bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter) { BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2)); if (nr_cpu_ids <= 1) return true; if (!state->mem) { state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE, XT_PCPU_BLOCK_SIZE); if (!state->mem) return false; } counter->pcnt = (__force unsigned long)(state->mem + state->off); state->off += sizeof(*counter); if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) { state->mem = NULL; state->off = 0; } return true; } EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc); void xt_percpu_counter_free(struct xt_counters *counters) { unsigned long pcnt = counters->pcnt; if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0) free_percpu((void __percpu *)pcnt); } EXPORT_SYMBOL_GPL(xt_percpu_counter_free); static int __net_init xt_net_init(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) INIT_LIST_HEAD(&xt_net->tables[i]); return 0; } static void __net_exit xt_net_exit(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); } static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, .id = &xt_pernet_id, .size = sizeof(struct xt_pernet), }; static int __init xt_init(void) { unsigned int i; int rv; for_each_possible_cpu(i) { seqcount_init(&per_cpu(xt_recseq, i)); } xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT mutex_init(&xt[i].compat_mutex); xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) kfree(xt); return rv; } static void __exit xt_fini(void) { unregister_pernet_subsys(&xt_net_ops); kfree(xt); } module_init(xt_init); module_exit(xt_fini); |
| 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm4_policy.c * * Changes: * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/err.h> #include <linux/kernel.h> #include <linux/inetdevice.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/l3mdev.h> static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct rtable *rt; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); fl4->flowi4_mark = mark; if (saddr) fl4->saddr = saddr->a4; fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF; rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct flowi4 fl4; return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); } static int xfrm4_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark) { struct dst_entry *dst; struct flowi4 fl4; dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; saddr->a4 = fl4.saddr; dst_release(dst); return 0; } static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; dev_hold(dev); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt.rt_is_input = rt->rt_is_input; xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) xdst->u.rt.rt_gw6 = rt->rt_gw6; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); return 0; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); if (xdst->u.rt.rt_uncached_list) rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { if (!unregister) return; xfrm_dst_ifdown(dst, dev); } static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 32768, }; static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .fill_dst = xfrm4_fill_dst, .blackhole_route = ipv4_blackhole_route, }; #ifdef CONFIG_SYSCTL static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static __net_init int xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = xfrm4_policy_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; } hdr = register_net_sysctl(net, "net/ipv4", table); if (!hdr) goto err_reg; net->ipv4.xfrm4_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else /* CONFIG_SYSCTL */ static inline int xfrm4_net_sysctl_init(struct net *net) { return 0; } static inline void xfrm4_net_sysctl_exit(struct net *net) { } #endif static int __net_init xfrm4_net_init(struct net *net) { int ret; memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, sizeof(xfrm4_dst_ops_template)); ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); if (ret) return ret; ret = xfrm4_net_sysctl_init(net); if (ret) dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); return ret; } static void __net_exit xfrm4_net_exit(struct net *net) { xfrm4_net_sysctl_exit(net); dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); } static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; static void __init xfrm4_policy_init(void) { xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET); } void __init xfrm4_init(void) { xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } |
| 101 17 6 100 22 5 5 15 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); void udp_tunnel_sock_release(struct socket *sock); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif static inline void udp_tunnel_encap_enable(struct socket *sock) { struct udp_sock *up = udp_sk(sock->sk); if (up->encap_enabled) return; up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device callbacks may sleep */ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_size(dev, table); } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_write(dev, table, skb); } #endif |
| 1 1 4 4 3 1 10 10 10 10 10 1 1 3 3 3 10 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vxcan.c - Virtual CAN Tunnel for cross namespace communication * * This code is derived from drivers/net/can/vcan.c for the virtual CAN * specific parts and from drivers/net/veth.c to implement the netlink API * for network interface pairs in a common and established way. * * Copyright (c) 2017 Oliver Hartkopp <socketcan@hartkopp.net> */ #include <linux/module.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/can.h> #include <linux/can/dev.h> #include <linux/can/skb.h> #include <linux/can/vxcan.h> #include <linux/can/can-ml.h> #include <linux/slab.h> #include <net/rtnetlink.h> #define DRV_NAME "vxcan" MODULE_DESCRIPTION("Virtual CAN Tunnel"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); struct vxcan_priv { struct net_device __rcu *peer; }; static netdev_tx_t vxcan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer; struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct net_device_stats *peerstats, *srcstats = &dev->stats; u8 len; if (can_dropped_invalid_skb(dev, skb)) return NETDEV_TX_OK; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (unlikely(!peer)) { kfree_skb(skb); dev->stats.tx_dropped++; goto out_unlock; } skb = can_create_echo_skb(skb); if (!skb) goto out_unlock; /* reset CAN GW hop counter */ skb->csum_start = 0; skb->pkt_type = PACKET_BROADCAST; skb->dev = peer; skb->ip_summed = CHECKSUM_UNNECESSARY; len = cfd->len; if (netif_rx_ni(skb) == NET_RX_SUCCESS) { srcstats->tx_packets++; srcstats->tx_bytes += len; peerstats = &peer->stats; peerstats->rx_packets++; peerstats->rx_bytes += len; } out_unlock: rcu_read_unlock(); return NETDEV_TX_OK; } static int vxcan_open(struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); if (!peer) return -ENOTCONN; if (peer->flags & IFF_UP) { netif_carrier_on(dev); netif_carrier_on(peer); } return 0; } static int vxcan_close(struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); netif_carrier_off(dev); if (peer) netif_carrier_off(peer); return 0; } static int vxcan_get_iflink(const struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer; int iflink; rcu_read_lock(); peer = rcu_dereference(priv->peer); iflink = peer ? peer->ifindex : 0; rcu_read_unlock(); return iflink; } static int vxcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ if (dev->flags & IFF_UP) return -EBUSY; if (new_mtu != CAN_MTU && new_mtu != CANFD_MTU) return -EINVAL; dev->mtu = new_mtu; return 0; } static const struct net_device_ops vxcan_netdev_ops = { .ndo_open = vxcan_open, .ndo_stop = vxcan_close, .ndo_start_xmit = vxcan_xmit, .ndo_get_iflink = vxcan_get_iflink, .ndo_change_mtu = vxcan_change_mtu, }; static void vxcan_setup(struct net_device *dev) { struct can_ml_priv *can_ml; dev->type = ARPHRD_CAN; dev->mtu = CANFD_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 0; dev->flags = IFF_NOARP; dev->netdev_ops = &vxcan_netdev_ops; dev->needs_free_netdev = true; can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); } /* forward declaration for rtnl_create_link() */ static struct rtnl_link_ops vxcan_link_ops; static int vxcan_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxcan_priv *priv; struct net_device *peer; struct net *peer_net; struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb; char ifname[IFNAMSIZ]; unsigned char name_assign_type; struct ifinfomsg *ifmp = NULL; int err; /* register peer device */ if (data && data[VXCAN_INFO_PEER]) { struct nlattr *nla_peer; nla_peer = data[VXCAN_INFO_PEER]; ifmp = nla_data(nla_peer); err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; tbp = peer_tb; } if (ifmp && tbp[IFLA_IFNAME]) { nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d"); name_assign_type = NET_NAME_ENUM; } peer_net = rtnl_link_get_net(net, tbp); if (IS_ERR(peer_net)) return PTR_ERR(peer_net); peer = rtnl_create_link(peer_net, ifname, name_assign_type, &vxcan_link_ops, tbp, extack); if (IS_ERR(peer)) { put_net(peer_net); return PTR_ERR(peer); } if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; err = register_netdevice(peer); put_net(peer_net); peer_net = NULL; if (err < 0) { free_netdev(peer); return err; } netif_carrier_off(peer); err = rtnl_configure_link(peer, ifmp); if (err < 0) goto unregister_network_device; /* register first device */ if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); else snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); err = register_netdevice(dev); if (err < 0) goto unregister_network_device; netif_carrier_off(dev); /* cross link the device pair */ priv = netdev_priv(dev); rcu_assign_pointer(priv->peer, peer); priv = netdev_priv(peer); rcu_assign_pointer(priv->peer, dev); return 0; unregister_network_device: unregister_netdevice(peer); return err; } static void vxcan_dellink(struct net_device *dev, struct list_head *head) { struct vxcan_priv *priv; struct net_device *peer; priv = netdev_priv(dev); peer = rtnl_dereference(priv->peer); /* Note : dellink() is called from default_device_exit_batch(), * before a rcu_synchronize() point. The devices are guaranteed * not being freed before one RCU grace period. */ RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(dev, head); if (peer) { priv = netdev_priv(peer); RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(peer, head); } } static const struct nla_policy vxcan_policy[VXCAN_INFO_MAX + 1] = { [VXCAN_INFO_PEER] = { .len = sizeof(struct ifinfomsg) }, }; static struct net *vxcan_get_link_net(const struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); return peer ? dev_net(peer) : dev_net(dev); } static struct rtnl_link_ops vxcan_link_ops = { .kind = DRV_NAME, .priv_size = ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN) + sizeof(struct can_ml_priv), .setup = vxcan_setup, .newlink = vxcan_newlink, .dellink = vxcan_dellink, .policy = vxcan_policy, .maxtype = VXCAN_INFO_MAX, .get_link_net = vxcan_get_link_net, }; static __init int vxcan_init(void) { pr_info("vxcan: Virtual CAN Tunnel driver\n"); return rtnl_link_register(&vxcan_link_ops); } static __exit void vxcan_exit(void) { rtnl_link_unregister(&vxcan_link_ops); } module_init(vxcan_init); module_exit(vxcan_exit); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { int val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { int val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 3135 566 18 13 668 98 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct list_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x0040 #define PERF_PMU_CAP_NO_EXCLUDE 0x0080 #define PERF_PMU_CAP_AUX_OUTPUT 0x0100 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0200 struct perf_output_handle; /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to: event->hw.idx + 1. */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_context *prev, struct perf_event_context *next); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; #define for_each_sibling_event(sibling, event) \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct callback_head pending_task; unsigned int pending_work; struct rcuwait pending_work_wait; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head active_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; struct list_head pinned_active; struct list_head flexible_active; int nr_events; int nr_active; int is_active; int nr_stat; int nr_freq; int rotate_disable; /* * Set when nr_events != nr_active, except tolerant to events not * necessary to be active due to scheduling constraints, such as cgroups. */ int rotate_necessary; refcount_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; /* * Sum (event->pending_sigtrap + event->pending_work) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_pending; }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; int online; /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); struct perf_sample_data { /* * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ u64 addr; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; union perf_sample_weight weight; u64 txn; union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; u64 aux_size; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 phys_addr; u64 cgroup; u64 data_page_size; u64 code_page_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; data->period = period; data->weight.full = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) { if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } #define is_default_overflow_handler(event) \ __is_default_overflow_handler((event)->overflow_handler) #ifdef CONFIG_BPF_SYSCALL static inline bool uses_default_overflow_handler(struct perf_event *event) { if (likely(is_default_overflow_handler(event))) return true; return __is_default_overflow_handler(event->orig_overflow_handler); } #else #define uses_default_overflow_handler(event) \ is_default_overflow_handler(event) #endif extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) { /* * Callbacks are RCU-protected and must be READ_ONCE to avoid reloading * the callbacks between a !NULL check and dereferences, to ensure * pending stores/changes to the callback pointers are visible before a * non-NULL perf_guest_cbs is visible to readers, and to prevent a * module from unloading callbacks while readers are active. */ return rcu_dereference(perf_guest_cbs); } extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_proc_update_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void __weak arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); #ifdef CONFIG_MMU extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 31 31 31 8 1 2 18 2 8 3 9 18 15 6 6 2 2 10 10 46 | 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 | // 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. * * "Ping" sockets * * Based on ipv4/ping.c code. * * Authors: Lorenzo Colitti (IPv6 support) * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) */ #include <net/addrconf.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/protocol.h> #include <net/udp.h> #include <net/transp_v6.h> #include <linux/proc_fs.h> #include <net/ping.h> /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { return -EAFNOSUPPORT; } static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { } static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) { return -EAFNOSUPPORT; } static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) {} static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { return 0; } static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; struct rt6_info *rt; struct pingfakehdr pfh; struct ipcm6_cookie ipc6; pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, sizeof(user_icmph)); if (err) return err; if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); if (msg->msg_namelen < sizeof(*u)) return -EINVAL; if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } daddr = &(u->sin6_addr); if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } if (!oif) oif = sk->sk_bound_dev_if; if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif && ipv6_addr_is_multicast(daddr)) oif = np->mcast_oif; else if (!oif) oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if && l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; fl6.flowi6_oif = oif; fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); ipcm6_init_sk(&ipc6, np); ipc6.sockc.mark = sk->sk_mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); rt = (struct rt6_info *) dst; if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; pfh.icmph.type = user_icmph.icmp6_type; pfh.icmph.code = user_icmph.icmp6_code; pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET6; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, 0, &ipc6, &fl6, rt, MSG_DONTWAIT); if (err) { ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); dst_release(dst); if (err) return err; return len; } struct proto pingv6_prot = { .name = "PINGv6", .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .sendmsg = ping_v6_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .obj_size = sizeof(struct raw6_sock), }; EXPORT_SYMBOL_GPL(pingv6_prot); static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; #ifdef CONFIG_PROC_FS static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) { return ping_seq_start(seq, pos, AF_INET6); } static int ping_v6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct ping_iter_state *) seq->private)->bucket; struct inet_sock *inet = inet_sk(v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); } return 0; } static const struct seq_operations ping_v6_seq_ops = { .start = ping_v6_seq_start, .show = ping_v6_seq_show, .next = ping_seq_next, .stop = ping_seq_stop, }; static int __net_init ping_v6_proc_init_net(struct net *net) { if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } static void __net_exit ping_v6_proc_exit_net(struct net *net) { remove_proc_entry("icmp6", net->proc_net); } static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, }; #endif int __init pingv6_init(void) { #ifdef CONFIG_PROC_FS int ret = register_pernet_subsys(&ping_v6_net_ops); if (ret) return ret; #endif pingv6_ops.ipv6_recv_error = ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = ip6_datagram_recv_specific_ctl; pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; return inet6_register_protosw(&pingv6_protosw); } /* This never gets called because it's not possible to unload the ipv6 module, * but just in case. */ void pingv6_exit(void) { pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; #ifdef CONFIG_PROC_FS unregister_pernet_subsys(&ping_v6_net_ops); #endif inet6_unregister_protosw(&pingv6_protosw); } |
| 28 28 28 | 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 | /* SPDX-License-Identifier: GPL-2.0 * * IO cost model based controller. * * Copyright (C) 2019 Tejun Heo <tj@kernel.org> * Copyright (C) 2019 Andy Newell <newella@fb.com> * Copyright (C) 2019 Facebook * * One challenge of controlling IO resources is the lack of trivially * observable cost metric. This is distinguished from CPU and memory where * wallclock time and the number of bytes can serve as accurate enough * approximations. * * Bandwidth and iops are the most commonly used metrics for IO devices but * depending on the type and specifics of the device, different IO patterns * easily lead to multiple orders of magnitude variations rendering them * useless for the purpose of IO capacity distribution. While on-device * time, with a lot of clutches, could serve as a useful approximation for * non-queued rotational devices, this is no longer viable with modern * devices, even the rotational ones. * * While there is no cost metric we can trivially observe, it isn't a * complete mystery. For example, on a rotational device, seek cost * dominates while a contiguous transfer contributes a smaller amount * proportional to the size. If we can characterize at least the relative * costs of these different types of IOs, it should be possible to * implement a reasonable work-conserving proportional IO resource * distribution. * * 1. IO Cost Model * * IO cost model estimates the cost of an IO given its basic parameters and * history (e.g. the end sector of the last IO). The cost is measured in * device time. If a given IO is estimated to cost 10ms, the device should * be able to process ~100 of those IOs in a second. * * Currently, there's only one builtin cost model - linear. Each IO is * classified as sequential or random and given a base cost accordingly. * On top of that, a size cost proportional to the length of the IO is * added. While simple, this model captures the operational * characteristics of a wide varienty of devices well enough. Default * parameters for several different classes of devices are provided and the * parameters can be configured from userspace via * /sys/fs/cgroup/io.cost.model. * * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate * device-specific coefficients. * * 2. Control Strategy * * The device virtual time (vtime) is used as the primary control metric. * The control strategy is composed of the following three parts. * * 2-1. Vtime Distribution * * When a cgroup becomes active in terms of IOs, its hierarchical share is * calculated. Please consider the following hierarchy where the numbers * inside parentheses denote the configured weights. * * root * / \ * A (w:100) B (w:300) * / \ * A0 (w:100) A1 (w:100) * * If B is idle and only A0 and A1 are actively issuing IOs, as the two are * of equal weight, each gets 50% share. If then B starts issuing IOs, B * gets 300/(100+300) or 75% share, and A0 and A1 equally splits the rest, * 12.5% each. The distribution mechanism only cares about these flattened * shares. They're called hweights (hierarchical weights) and always add * upto 1 (WEIGHT_ONE). * * A given cgroup's vtime runs slower in inverse proportion to its hweight. * For example, with 12.5% weight, A0's time runs 8 times slower (100/12.5) * against the device vtime - an IO which takes 10ms on the underlying * device is considered to take 80ms on A0. * * This constitutes the basis of IO capacity distribution. Each cgroup's * vtime is running at a rate determined by its hweight. A cgroup tracks * the vtime consumed by past IOs and can issue a new IO if doing so * wouldn't outrun the current device vtime. Otherwise, the IO is * suspended until the vtime has progressed enough to cover it. * * 2-2. Vrate Adjustment * * It's unrealistic to expect the cost model to be perfect. There are too * many devices and even on the same device the overall performance * fluctuates depending on numerous factors such as IO mixture and device * internal garbage collection. The controller needs to adapt dynamically. * * This is achieved by adjusting the overall IO rate according to how busy * the device is. If the device becomes overloaded, we're sending down too * many IOs and should generally slow down. If there are waiting issuers * but the device isn't saturated, we're issuing too few and should * generally speed up. * * To slow down, we lower the vrate - the rate at which the device vtime * passes compared to the wall clock. For example, if the vtime is running * at the vrate of 75%, all cgroups added up would only be able to issue * 750ms worth of IOs per second, and vice-versa for speeding up. * * Device business is determined using two criteria - rq wait and * completion latencies. * * When a device gets saturated, the on-device and then the request queues * fill up and a bio which is ready to be issued has to wait for a request * to become available. When this delay becomes noticeable, it's a clear * indication that the device is saturated and we lower the vrate. This * saturation signal is fairly conservative as it only triggers when both * hardware and software queues are filled up, and is used as the default * busy signal. * * As devices can have deep queues and be unfair in how the queued commands * are executed, soley depending on rq wait may not result in satisfactory * control quality. For a better control quality, completion latency QoS * parameters can be configured so that the device is considered saturated * if N'th percentile completion latency rises above the set point. * * The completion latency requirements are a function of both the * underlying device characteristics and the desired IO latency quality of * service. There is an inherent trade-off - the tighter the latency QoS, * the higher the bandwidth lossage. Latency QoS is disabled by default * and can be set through /sys/fs/cgroup/io.cost.qos. * * 2-3. Work Conservation * * Imagine two cgroups A and B with equal weights. A is issuing a small IO * periodically while B is sending out enough parallel IOs to saturate the * device on its own. Let's say A's usage amounts to 100ms worth of IO * cost per second, i.e., 10% of the device capacity. The naive * distribution of half and half would lead to 60% utilization of the * device, a significant reduction in the total amount of work done * compared to free-for-all competition. This is too high a cost to pay * for IO control. * * To conserve the total amount of work done, we keep track of how much * each active cgroup is actually using and yield part of its weight if * there are other cgroups which can make use of it. In the above case, * A's weight will be lowered so that it hovers above the actual usage and * B would be able to use the rest. * * As we don't want to penalize a cgroup for donating its weight, the * surplus weight adjustment factors in a margin and has an immediate * snapback mechanism in case the cgroup needs more IO vtime for itself. * * Note that adjusting down surplus weights has the same effects as * accelerating vtime for other cgroups and work conservation can also be * implemented by adjusting vrate dynamically. However, squaring who can * donate and should take back how much requires hweight propagations * anyway making it easier to implement and understand as a separate * mechanism. * * 3. Monitoring * * Instead of debugfs or other clumsy monitoring mechanisms, this * controller uses a drgn based monitoring script - * tools/cgroup/iocost_monitor.py. For details on drgn, please see * https://github.com/osandov/drgn. The output looks like the following. * * sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12% * active weight hweight% inflt% dbt delay usages% * test/a * 50/ 50 33.33/ 33.33 27.65 2 0*041 033:033:033 * test/b * 100/ 100 66.67/ 66.67 17.56 0 0*000 066:079:077 * * - per : Timer period * - cur_per : Internal wall and device vtime clock * - vrate : Device virtual time rate against wall clock * - weight : Surplus-adjusted and configured weights * - hweight : Surplus-adjusted and configured hierarchical weights * - inflt : The percentage of in-flight IO cost at the end of last period * - del_ms : Deferred issuer delay induction level and duration * - usages : Usage history */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/time64.h> #include <linux/parser.h> #include <linux/sched/signal.h> #include <linux/blk-cgroup.h> #include <asm/local.h> #include <asm/local64.h> #include "blk-rq-qos.h" #include "blk-stat.h" #include "blk-wbt.h" #ifdef CONFIG_TRACEPOINTS /* copied from TRACE_CGROUP_PATH, see cgroup-internal.h */ #define TRACE_IOCG_PATH_LEN 1024 static DEFINE_SPINLOCK(trace_iocg_path_lock); static char trace_iocg_path[TRACE_IOCG_PATH_LEN]; #define TRACE_IOCG_PATH(type, iocg, ...) \ do { \ unsigned long flags; \ if (trace_iocost_##type##_enabled()) { \ spin_lock_irqsave(&trace_iocg_path_lock, flags); \ cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup, \ trace_iocg_path, TRACE_IOCG_PATH_LEN); \ trace_iocost_##type(iocg, trace_iocg_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_iocg_path_lock, flags); \ } \ } while (0) #else /* CONFIG_TRACE_POINTS */ #define TRACE_IOCG_PATH(type, iocg, ...) do { } while (0) #endif /* CONFIG_TRACE_POINTS */ enum { MILLION = 1000000, /* timer period is calculated from latency requirements, bound it */ MIN_PERIOD = USEC_PER_MSEC, MAX_PERIOD = USEC_PER_SEC, /* * iocg->vtime is targeted at 50% behind the device vtime, which * serves as its IO credit buffer. Surplus weight adjustment is * immediately canceled if the vtime margin runs below 10%. */ MARGIN_MIN_PCT = 10, MARGIN_LOW_PCT = 20, MARGIN_TARGET_PCT = 50, INUSE_ADJ_STEP_PCT = 25, /* Have some play in timer operations */ TIMER_SLACK_PCT = 1, /* 1/64k is granular enough and can easily be handled w/ u32 */ WEIGHT_ONE = 1 << 16, }; enum { /* * As vtime is used to calculate the cost of each IO, it needs to * be fairly high precision. For example, it should be able to * represent the cost of a single page worth of discard with * suffificient accuracy. At the same time, it should be able to * represent reasonably long enough durations to be useful and * convenient during operation. * * 1s worth of vtime is 2^37. This gives us both sub-nanosecond * granularity and days of wrap-around time even at extreme vrates. */ VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC, VTIME_PER_NSEC = VTIME_PER_SEC / NSEC_PER_SEC, /* bound vrate adjustments within two orders of magnitude */ VRATE_MIN_PPM = 10000, /* 1% */ VRATE_MAX_PPM = 100000000, /* 10000% */ VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, /* switch iff the conditions are met for longer than this */ AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, }; enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, /* unbusy hysterisis */ UNBUSY_THR_PCT = 75, /* * The effect of delay is indirect and non-linear and a huge amount of * future debt can accumulate abruptly while unthrottled. Linearly scale * up delay as debt is going up and then let it decay exponentially. * This gives us quick ramp ups while delay is accumulating and long * tails which can help reducing the frequency of debt explosions on * unthrottle. The parameters are experimentally determined. * * The delay mechanism provides adequate protection and behavior in many * cases. However, this is far from ideal and falls shorts on both * fronts. The debtors are often throttled too harshly costing a * significant level of fairness and possibly total work while the * protection against their impacts on the system can be choppy and * unreliable. * * The shortcoming primarily stems from the fact that, unlike for page * cache, the kernel doesn't have well-defined back-pressure propagation * mechanism and policies for anonymous memory. Fully addressing this * issue will likely require substantial improvements in the area. */ MIN_DELAY_THR_PCT = 500, MAX_DELAY_THR_PCT = 25000, MIN_DELAY = 250, MAX_DELAY = 250 * USEC_PER_MSEC, /* halve debts if avg usage over 100ms is under 50% */ DFGV_USAGE_PCT = 50, DFGV_PERIOD = 100 * USEC_PER_MSEC, /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer * numbers of digits to per-IO cost components. */ IOC_PAGE_SHIFT = 12, IOC_PAGE_SIZE = 1 << IOC_PAGE_SHIFT, IOC_SECT_TO_PAGE_SHIFT = IOC_PAGE_SHIFT - SECTOR_SHIFT, /* if apart further than 16M, consider randio for linear model */ LCOEF_RANDIO_PAGES = 4096, }; enum ioc_running { IOC_IDLE, IOC_RUNNING, IOC_STOP, }; /* io.cost.qos controls including per-dev enable of the whole controller */ enum { QOS_ENABLE, QOS_CTRL, NR_QOS_CTRL_PARAMS, }; /* io.cost.qos params */ enum { QOS_RPPM, QOS_RLAT, QOS_WPPM, QOS_WLAT, QOS_MIN, QOS_MAX, NR_QOS_PARAMS, }; /* io.cost.model controls */ enum { COST_CTRL, COST_MODEL, NR_COST_CTRL_PARAMS, }; /* builtin linear cost model coefficients */ enum { I_LCOEF_RBPS, I_LCOEF_RSEQIOPS, I_LCOEF_RRANDIOPS, I_LCOEF_WBPS, I_LCOEF_WSEQIOPS, I_LCOEF_WRANDIOPS, NR_I_LCOEFS, }; enum { LCOEF_RPAGE, LCOEF_RSEQIO, LCOEF_RRANDIO, LCOEF_WPAGE, LCOEF_WSEQIO, LCOEF_WRANDIO, NR_LCOEFS, }; enum { AUTOP_INVALID, AUTOP_HDD, AUTOP_SSD_QD1, AUTOP_SSD_DFL, AUTOP_SSD_FAST, }; struct ioc_params { u32 qos[NR_QOS_PARAMS]; u64 i_lcoefs[NR_I_LCOEFS]; u64 lcoefs[NR_LCOEFS]; u32 too_fast_vrate_pct; u32 too_slow_vrate_pct; }; struct ioc_margins { s64 min; s64 low; s64 target; }; struct ioc_missed { local_t nr_met; local_t nr_missed; u32 last_met; u32 last_missed; }; struct ioc_pcpu_stat { struct ioc_missed missed[2]; local64_t rq_wait_ns; u64 last_rq_wait_ns; }; /* per device */ struct ioc { struct rq_qos rqos; bool enabled; struct ioc_params params; struct ioc_margins margins; u32 period_us; u32 timer_slack_ns; u64 vrate_min; u64 vrate_max; spinlock_t lock; struct timer_list timer; struct list_head active_iocgs; /* active cgroups */ struct ioc_pcpu_stat __percpu *pcpu_stat; enum ioc_running running; atomic64_t vtime_rate; u64 vtime_base_rate; s64 vtime_err; seqcount_spinlock_t period_seqcount; u64 period_at; /* wallclock starttime */ u64 period_at_vtime; /* vtime starttime */ atomic64_t cur_period; /* inc'd each period */ int busy_level; /* saturation history */ bool weights_updated; atomic_t hweight_gen; /* for lazy hweights */ /* debt forgivness */ u64 dfgv_period_at; u64 dfgv_period_rem; u64 dfgv_usage_us_sum; u64 autop_too_fast_at; u64 autop_too_slow_at; int autop_idx; bool user_qos_params:1; bool user_cost_model:1; }; struct iocg_pcpu_stat { local64_t abs_vusage; }; struct iocg_stat { u64 usage_us; u64 wait_us; u64 indebt_us; u64 indelay_us; }; /* per device-cgroup pair */ struct ioc_gq { struct blkg_policy_data pd; struct ioc *ioc; /* * A iocg can get its weight from two sources - an explicit * per-device-cgroup configuration or the default weight of the * cgroup. `cfg_weight` is the explicit per-device-cgroup * configuration. `weight` is the effective considering both * sources. * * When an idle cgroup becomes active its `active` goes from 0 to * `weight`. `inuse` is the surplus adjusted active weight. * `active` and `inuse` are used to calculate `hweight_active` and * `hweight_inuse`. * * `last_inuse` remembers `inuse` while an iocg is idle to persist * surplus adjustments. * * `inuse` may be adjusted dynamically during period. `saved_*` are used * to determine and track adjustments. */ u32 cfg_weight; u32 weight; u32 active; u32 inuse; u32 last_inuse; s64 saved_margin; sector_t cursor; /* to detect randio */ /* * `vtime` is this iocg's vtime cursor which progresses as IOs are * issued. If lagging behind device vtime, the delta represents * the currently available IO budget. If running ahead, the * overage. * * `vtime_done` is the same but progressed on completion rather * than issue. The delta behind `vtime` represents the cost of * currently in-flight IOs. */ atomic64_t vtime; atomic64_t done_vtime; u64 abs_vdebt; /* current delay in effect and when it started */ u64 delay; u64 delay_at; /* * The period this iocg was last active in. Used for deactivation * and invalidating `vtime`. */ atomic64_t active_period; struct list_head active_list; /* see __propagate_weights() and current_hweight() for details */ u64 child_active_sum; u64 child_inuse_sum; u64 child_adjusted_sum; int hweight_gen; u32 hweight_active; u32 hweight_inuse; u32 hweight_donating; u32 hweight_after_donation; struct list_head walk_list; struct list_head surplus_list; struct wait_queue_head waitq; struct hrtimer waitq_timer; /* timestamp at the latest activation */ u64 activated_at; /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; struct iocg_stat local_stat; struct iocg_stat desc_stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; u64 wait_since; u64 indebt_since; u64 indelay_since; /* this iocg's depth in the hierarchy and ancestors including self */ int level; struct ioc_gq *ancestors[]; }; /* per cgroup */ struct ioc_cgrp { struct blkcg_policy_data cpd; unsigned int dfl_weight; }; struct ioc_now { u64 now_ns; u64 now; u64 vnow; u64 vrate; }; struct iocg_wait { struct wait_queue_entry wait; struct bio *bio; u64 abs_cost; bool committed; }; struct iocg_wake_ctx { struct ioc_gq *iocg; u32 hw_inuse; s64 vbudget; }; static const struct ioc_params autop[] = { [AUTOP_HDD] = { .qos = { [QOS_RLAT] = 250000, /* 250ms */ [QOS_WLAT] = 250000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 174019176, [I_LCOEF_RSEQIOPS] = 41708, [I_LCOEF_RRANDIOPS] = 370, [I_LCOEF_WBPS] = 178075866, [I_LCOEF_WSEQIOPS] = 42705, [I_LCOEF_WRANDIOPS] = 378, }, }, [AUTOP_SSD_QD1] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 245855193, [I_LCOEF_RSEQIOPS] = 61575, [I_LCOEF_RRANDIOPS] = 6946, [I_LCOEF_WBPS] = 141365009, [I_LCOEF_WSEQIOPS] = 33716, [I_LCOEF_WRANDIOPS] = 26796, }, }, [AUTOP_SSD_DFL] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 488636629, [I_LCOEF_RSEQIOPS] = 8932, [I_LCOEF_RRANDIOPS] = 8518, [I_LCOEF_WBPS] = 427891549, [I_LCOEF_WSEQIOPS] = 28755, [I_LCOEF_WRANDIOPS] = 21940, }, .too_fast_vrate_pct = 500, }, [AUTOP_SSD_FAST] = { .qos = { [QOS_RLAT] = 5000, /* 5ms */ [QOS_WLAT] = 5000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 3102524156LLU, [I_LCOEF_RSEQIOPS] = 724816, [I_LCOEF_RRANDIOPS] = 778122, [I_LCOEF_WBPS] = 1742780862LLU, [I_LCOEF_WSEQIOPS] = 425702, [I_LCOEF_WRANDIOPS] = 443193, }, .too_slow_vrate_pct = 10, }, }; /* * vrate adjust percentages indexed by ioc->busy_level. We adjust up on * vtime credit shortage and down on device saturation. */ static u32 vrate_adj_pct[] = { 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 }; static struct blkcg_policy blkcg_policy_iocost; /* accessors and helpers */ static struct ioc *rqos_to_ioc(struct rq_qos *rqos) { return container_of(rqos, struct ioc, rqos); } static struct ioc *q_to_ioc(struct request_queue *q) { return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST)); } static const char *q_name(struct request_queue *q) { if (blk_queue_registered(q)) return kobject_name(q->kobj.parent); else return "<unknown>"; } static const char __maybe_unused *ioc_name(struct ioc *ioc) { return q_name(ioc->rqos.q); } static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct ioc_gq, pd) : NULL; } static struct ioc_gq *blkg_to_iocg(struct blkcg_gq *blkg) { return pd_to_iocg(blkg_to_pd(blkg, &blkcg_policy_iocost)); } static struct blkcg_gq *iocg_to_blkg(struct ioc_gq *iocg) { return pd_to_blkg(&iocg->pd); } static struct ioc_cgrp *blkcg_to_iocc(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &blkcg_policy_iocost), struct ioc_cgrp, cpd); } /* * Scale @abs_cost to the inverse of @hw_inuse. The lower the hierarchical * weight, the more expensive each IO. Must round up. */ static u64 abs_cost_to_cost(u64 abs_cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(abs_cost * WEIGHT_ONE, hw_inuse); } /* * The inverse of abs_cost_to_cost(). Must round up. */ static u64 cost_to_abs_cost(u64 cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(cost * hw_inuse, WEIGHT_ONE); } static void iocg_commit_bio(struct ioc_gq *iocg, struct bio *bio, u64 abs_cost, u64 cost) { struct iocg_pcpu_stat *gcs; bio->bi_iocost_cost = cost; atomic64_add(cost, &iocg->vtime); gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_lock(struct ioc_gq *iocg, bool lock_ioc, unsigned long *flags) { if (lock_ioc) { spin_lock_irqsave(&iocg->ioc->lock, *flags); spin_lock(&iocg->waitq.lock); } else { spin_lock_irqsave(&iocg->waitq.lock, *flags); } } static void iocg_unlock(struct ioc_gq *iocg, bool unlock_ioc, unsigned long *flags) { if (unlock_ioc) { spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&iocg->ioc->lock, *flags); } else { spin_unlock_irqrestore(&iocg->waitq.lock, *flags); } } #define CREATE_TRACE_POINTS #include <trace/events/iocost.h> static void ioc_refresh_margins(struct ioc *ioc) { struct ioc_margins *margins = &ioc->margins; u32 period_us = ioc->period_us; u64 vrate = ioc->vtime_base_rate; margins->min = (period_us * MARGIN_MIN_PCT / 100) * vrate; margins->low = (period_us * MARGIN_LOW_PCT / 100) * vrate; margins->target = (period_us * MARGIN_TARGET_PCT / 100) * vrate; } /* latency Qos params changed, update period_us and all the dependent params */ static void ioc_refresh_period_us(struct ioc *ioc) { u32 ppm, lat, multi, period_us; lockdep_assert_held(&ioc->lock); /* pick the higher latency target */ if (ioc->params.qos[QOS_RLAT] >= ioc->params.qos[QOS_WLAT]) { ppm = ioc->params.qos[QOS_RPPM]; lat = ioc->params.qos[QOS_RLAT]; } else { ppm = ioc->params.qos[QOS_WPPM]; lat = ioc->params.qos[QOS_WLAT]; } /* * We want the period to be long enough to contain a healthy number * of IOs while short enough for granular control. Define it as a * multiple of the latency target. Ideally, the multiplier should * be scaled according to the percentile so that it would nominally * contain a certain number of requests. Let's be simpler and * scale it linearly so that it's 2x >= pct(90) and 10x at pct(50). */ if (ppm) multi = max_t(u32, (MILLION - ppm) / 50000, 2); else multi = 2; period_us = multi * lat; period_us = clamp_t(u32, period_us, MIN_PERIOD, MAX_PERIOD); /* calculate dependent params */ ioc->period_us = period_us; ioc->timer_slack_ns = div64_u64( (u64)period_us * NSEC_PER_USEC * TIMER_SLACK_PCT, 100); ioc_refresh_margins(ioc); } static int ioc_autop_idx(struct ioc *ioc) { int idx = ioc->autop_idx; const struct ioc_params *p = &autop[idx]; u32 vrate_pct; u64 now_ns; /* rotational? */ if (!blk_queue_nonrot(ioc->rqos.q)) return AUTOP_HDD; /* handle SATA SSDs w/ broken NCQ */ if (blk_queue_depth(ioc->rqos.q) == 1) return AUTOP_SSD_QD1; /* use one of the normal ssd sets */ if (idx < AUTOP_SSD_DFL) return AUTOP_SSD_DFL; /* if user is overriding anything, maintain what was there */ if (ioc->user_qos_params || ioc->user_cost_model) return idx; /* step up/down based on the vrate */ vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC); now_ns = ktime_get_ns(); if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) { if (!ioc->autop_too_fast_at) ioc->autop_too_fast_at = now_ns; if (now_ns - ioc->autop_too_fast_at >= AUTOP_CYCLE_NSEC) return idx + 1; } else { ioc->autop_too_fast_at = 0; } if (p->too_slow_vrate_pct && p->too_slow_vrate_pct >= vrate_pct) { if (!ioc->autop_too_slow_at) ioc->autop_too_slow_at = now_ns; if (now_ns - ioc->autop_too_slow_at >= AUTOP_CYCLE_NSEC) return idx - 1; } else { ioc->autop_too_slow_at = 0; } return idx; } /* * Take the followings as input * * @bps maximum sequential throughput * @seqiops maximum sequential 4k iops * @randiops maximum random 4k iops * * and calculate the linear model cost coefficients. * * *@page per-page cost 1s / (@bps / 4096) * *@seqio base cost of a seq IO max((1s / @seqiops) - *@page, 0) * @randiops base cost of a rand IO max((1s / @randiops) - *@page, 0) */ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, u64 *page, u64 *seqio, u64 *randio) { u64 v; *page = *seqio = *randio = 0; if (bps) { u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); if (bps_pages) *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); else *page = 1; } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); if (v > *page) *seqio = v - *page; } if (randiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, randiops); if (v > *page) *randio = v - *page; } } static void ioc_refresh_lcoefs(struct ioc *ioc) { u64 *u = ioc->params.i_lcoefs; u64 *c = ioc->params.lcoefs; calc_lcoefs(u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]); calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS], &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]); } static bool ioc_refresh_params(struct ioc *ioc, bool force) { const struct ioc_params *p; int idx; lockdep_assert_held(&ioc->lock); idx = ioc_autop_idx(ioc); p = &autop[idx]; if (idx == ioc->autop_idx && !force) return false; if (idx != ioc->autop_idx) atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); ioc->autop_idx = idx; ioc->autop_too_fast_at = 0; ioc->autop_too_slow_at = 0; if (!ioc->user_qos_params) memcpy(ioc->params.qos, p->qos, sizeof(p->qos)); if (!ioc->user_cost_model) memcpy(ioc->params.i_lcoefs, p->i_lcoefs, sizeof(p->i_lcoefs)); ioc_refresh_period_us(ioc); ioc_refresh_lcoefs(ioc); ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] * VTIME_PER_USEC, MILLION); ioc->vrate_max = div64_u64((u64)ioc->params.qos[QOS_MAX] * VTIME_PER_USEC, MILLION); return true; } /* * When an iocg accumulates too much vtime or gets deactivated, we throw away * some vtime, which lowers the overall device utilization. As the exact amount * which is being thrown away is known, we can compensate by accelerating the * vrate accordingly so that the extra vtime generated in the current period * matches what got lost. */ static void ioc_refresh_vrate(struct ioc *ioc, struct ioc_now *now) { s64 pleft = ioc->period_at + ioc->period_us - now->now; s64 vperiod = ioc->period_us * ioc->vtime_base_rate; s64 vcomp, vcomp_min, vcomp_max; lockdep_assert_held(&ioc->lock); /* we need some time left in this period */ if (pleft <= 0) goto done; /* * Calculate how much vrate should be adjusted to offset the error. * Limit the amount of adjustment and deduct the adjusted amount from * the error. */ vcomp = -div64_s64(ioc->vtime_err, pleft); vcomp_min = -(ioc->vtime_base_rate >> 1); vcomp_max = ioc->vtime_base_rate; vcomp = clamp(vcomp, vcomp_min, vcomp_max); ioc->vtime_err += vcomp * pleft; atomic64_set(&ioc->vtime_rate, ioc->vtime_base_rate + vcomp); done: /* bound how much error can accumulate */ ioc->vtime_err = clamp(ioc->vtime_err, -vperiod, vperiod); } static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct, int nr_lagging, int nr_shortages, int prev_busy_level, u32 *missed_ppm) { u64 vrate = ioc->vtime_base_rate; u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max; if (!ioc->busy_level || (ioc->busy_level < 0 && nr_lagging)) { if (ioc->busy_level != prev_busy_level || nr_lagging) trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate), missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); return; } /* * If vrate is out of bounds, apply clamp gradually as the * bounds can change abruptly. Otherwise, apply busy_level * based adjustment. */ if (vrate < vrate_min) { vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT), 100); vrate = min(vrate, vrate_min); } else if (vrate > vrate_max) { vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT), 100); vrate = max(vrate, vrate_max); } else { int idx = min_t(int, abs(ioc->busy_level), ARRAY_SIZE(vrate_adj_pct) - 1); u32 adj_pct = vrate_adj_pct[idx]; if (ioc->busy_level > 0) adj_pct = 100 - adj_pct; else adj_pct = 100 + adj_pct; vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100), vrate_min, vrate_max); } trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); ioc->vtime_base_rate = vrate; ioc_refresh_margins(ioc); } /* take a snapshot of the current [v]time and vrate */ static void ioc_now(struct ioc *ioc, struct ioc_now *now) { unsigned seq; now->now_ns = ktime_get(); now->now = ktime_to_us(now->now_ns); now->vrate = atomic64_read(&ioc->vtime_rate); /* * The current vtime is * * vtime at period start + (wallclock time since the start) * vrate * * As a consistent snapshot of `period_at_vtime` and `period_at` is * needed, they're seqcount protected. */ do { seq = read_seqcount_begin(&ioc->period_seqcount); now->vnow = ioc->period_at_vtime + (now->now - ioc->period_at) * now->vrate; } while (read_seqcount_retry(&ioc->period_seqcount, seq)); } static void ioc_start_period(struct ioc *ioc, struct ioc_now *now) { WARN_ON_ONCE(ioc->running != IOC_RUNNING); write_seqcount_begin(&ioc->period_seqcount); ioc->period_at = now->now; ioc->period_at_vtime = now->vnow; write_seqcount_end(&ioc->period_seqcount); ioc->timer.expires = jiffies + usecs_to_jiffies(ioc->period_us); add_timer(&ioc->timer); } /* * Update @iocg's `active` and `inuse` to @active and @inuse, update level * weight sums and propagate upwards accordingly. If @save, the current margin * is saved to be used as reference for later inuse in-period adjustments. */ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; int lvl; lockdep_assert_held(&ioc->lock); /* * For an active leaf node, its inuse shouldn't be zero or exceed * @active. An active internal node's inuse is solely determined by the * inuse to active ratio of its children regardless of @inuse. */ if (list_empty(&iocg->active_list) && iocg->child_active_sum) { inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { inuse = clamp_t(u32, inuse, 1, active); } iocg->last_inuse = iocg->inuse; if (save) iocg->saved_margin = now->vnow - atomic64_read(&iocg->vtime); if (active == iocg->active && inuse == iocg->inuse) return; for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u32 parent_active = 0, parent_inuse = 0; /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); /* apply the updates */ child->active = active; child->inuse = inuse; /* * The delta between inuse and active sums indicates that * much of weight is being given away. Parent's inuse * and active should reflect the ratio. */ if (parent->child_active_sum) { parent_active = parent->weight; parent_inuse = DIV64_U64_ROUND_UP( parent_active * parent->child_inuse_sum, parent->child_active_sum); } /* do we need to keep walking up? */ if (parent_active == parent->active && parent_inuse == parent->inuse) break; active = parent_active; inuse = parent_inuse; } ioc->weights_updated = true; } static void commit_weights(struct ioc *ioc) { lockdep_assert_held(&ioc->lock); if (ioc->weights_updated) { /* paired with rmb in current_hweight(), see there */ smp_wmb(); atomic_inc(&ioc->hweight_gen); ioc->weights_updated = false; } } static void propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { __propagate_weights(iocg, active, inuse, save, now); commit_weights(iocg->ioc); } static void current_hweight(struct ioc_gq *iocg, u32 *hw_activep, u32 *hw_inusep) { struct ioc *ioc = iocg->ioc; int lvl; u32 hwa, hwi; int ioc_gen; /* hot path - if uptodate, use cached */ ioc_gen = atomic_read(&ioc->hweight_gen); if (ioc_gen == iocg->hweight_gen) goto out; /* * Paired with wmb in commit_weights(). If we saw the updated * hweight_gen, all the weight updates from __propagate_weights() are * visible too. * * We can race with weight updates during calculation and get it * wrong. However, hweight_gen would have changed and a future * reader will recalculate and we're guaranteed to discard the * wrong result soon. */ smp_rmb(); hwa = hwi = WEIGHT_ONE; for (lvl = 0; lvl <= iocg->level - 1; lvl++) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u64 active_sum = READ_ONCE(parent->child_active_sum); u64 inuse_sum = READ_ONCE(parent->child_inuse_sum); u32 active = READ_ONCE(child->active); u32 inuse = READ_ONCE(child->inuse); /* we can race with deactivations and either may read as zero */ if (!active_sum || !inuse_sum) continue; active_sum = max_t(u64, active, active_sum); hwa = div64_u64((u64)hwa * active, active_sum); inuse_sum = max_t(u64, inuse, inuse_sum); hwi = div64_u64((u64)hwi * inuse, inuse_sum); } iocg->hweight_active = max_t(u32, hwa, 1); iocg->hweight_inuse = max_t(u32, hwi, 1); iocg->hweight_gen = ioc_gen; out: if (hw_activep) *hw_activep = iocg->hweight_active; if (hw_inusep) *hw_inusep = iocg->hweight_inuse; } /* * Calculate the hweight_inuse @iocg would get with max @inuse assuming all the * other weights stay unchanged. */ static u32 current_hweight_max(struct ioc_gq *iocg) { u32 hwm = WEIGHT_ONE; u32 inuse = iocg->active; u64 child_inuse_sum; int lvl; lockdep_assert_held(&iocg->ioc->lock); for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; child_inuse_sum = parent->child_inuse_sum + inuse - child->inuse; hwm = div64_u64((u64)hwm * inuse, child_inuse_sum); inuse = DIV64_U64_ROUND_UP(parent->active * child_inuse_sum, parent->child_active_sum); } return max_t(u32, hwm, 1); } static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); struct ioc_cgrp *iocc = blkcg_to_iocc(blkg->blkcg); u32 weight; lockdep_assert_held(&ioc->lock); weight = iocg->cfg_weight ?: iocc->dfl_weight; if (weight != iocg->weight && iocg->active) propagate_weights(iocg, weight, iocg->inuse, true, now); iocg->weight = weight; } static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 last_period, cur_period; u64 vtime, vtarget; int i; /* * If seem to be already active, just update the stamp to tell the * timer that we're still active. We don't mind occassional races. */ if (!list_empty(&iocg->active_list)) { ioc_now(ioc, now); cur_period = atomic64_read(&ioc->cur_period); if (atomic64_read(&iocg->active_period) != cur_period) atomic64_set(&iocg->active_period, cur_period); return true; } /* racy check on internal node IOs, treat as root level IOs */ if (iocg->child_active_sum) return false; spin_lock_irq(&ioc->lock); ioc_now(ioc, now); /* update period */ cur_period = atomic64_read(&ioc->cur_period); last_period = atomic64_read(&iocg->active_period); atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ if (!list_empty(&iocg->active_list)) goto succeed_unlock; for (i = iocg->level - 1; i > 0; i--) if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; if (iocg->child_active_sum) goto fail_unlock; /* * Always start with the target budget. On deactivation, we throw away * anything above it. */ vtarget = now->vnow - ioc->margins.target; vtime = atomic64_read(&iocg->vtime); atomic64_add(vtarget - vtime, &iocg->vtime); atomic64_add(vtarget - vtime, &iocg->done_vtime); vtime = vtarget; /* * Activate, propagate weight and start period timer if not * running. Reset hweight_gen to avoid accidental match from * wrapping. */ iocg->hweight_gen = atomic_read(&ioc->hweight_gen) - 1; list_add(&iocg->active_list, &ioc->active_iocgs); propagate_weights(iocg, iocg->weight, iocg->last_inuse ?: iocg->weight, true, now); TRACE_IOCG_PATH(iocg_activate, iocg, now, last_period, cur_period, vtime); iocg->activated_at = now->now; if (ioc->running == IOC_IDLE) { ioc->running = IOC_RUNNING; ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc_start_period(ioc, now); } succeed_unlock: spin_unlock_irq(&ioc->lock); return true; fail_unlock: spin_unlock_irq(&ioc->lock); return false; } static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); /* * If the delay is set by another CPU, we may be in the past. No need to * change anything if so. This avoids decay calculation underflow. */ if (time_before64(now->now, iocg->delay_at)) return false; /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; shift = div64_u64(tdelta, USEC_PER_SEC); if (iocg->delay && shift < BITS_PER_LONG) delay = iocg->delay >> shift; else delay = 0; /* calculate the new delay from the debt amount */ current_hweight(iocg, &hwa, NULL); vover = atomic64_read(&iocg->vtime) + abs_cost_to_cost(iocg->abs_vdebt, hwa) - now->vnow; vover_pct = div64_s64(100 * vover, ioc->period_us * ioc->vtime_base_rate); if (vover_pct <= MIN_DELAY_THR_PCT) new_delay = 0; else if (vover_pct >= MAX_DELAY_THR_PCT) new_delay = MAX_DELAY; else new_delay = MIN_DELAY + div_u64((MAX_DELAY - MIN_DELAY) * (vover_pct - MIN_DELAY_THR_PCT), MAX_DELAY_THR_PCT - MIN_DELAY_THR_PCT); /* pick the higher one and apply */ if (new_delay > delay) { iocg->delay = new_delay; iocg->delay_at = now->now; delay = new_delay; } if (delay >= MIN_DELAY) { if (!iocg->indelay_since) iocg->indelay_since = now->now; blkcg_set_delay(blkg, delay * NSEC_PER_USEC); return true; } else { if (iocg->indelay_since) { iocg->local_stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; blkcg_clear_delay(blkg); return false; } } static void iocg_incur_debt(struct ioc_gq *iocg, u64 abs_cost, struct ioc_now *now) { struct iocg_pcpu_stat *gcs; lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); WARN_ON_ONCE(list_empty(&iocg->active_list)); /* * Once in debt, debt handling owns inuse. @iocg stays at the minimum * inuse donating all of it share to others until its debt is paid off. */ if (!iocg->abs_vdebt && abs_cost) { iocg->indebt_since = now->now; propagate_weights(iocg, iocg->active, 0, false, now); } iocg->abs_vdebt += abs_cost; gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, struct ioc_now *now) { lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); /* make sure that nobody messed with @iocg */ WARN_ON_ONCE(list_empty(&iocg->active_list)); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { iocg->local_stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, false, now); } } static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key) { struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait); struct iocg_wake_ctx *ctx = (struct iocg_wake_ctx *)key; u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse); ctx->vbudget -= cost; if (ctx->vbudget < 0) return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it * actually changed the task state. We want the wait always removed. * Remove explicitly and use default_wake_function(). Note that the * order of operations is important as finish_wait() tests whether * @wq_entry is removed without grabbing the lock. */ default_wake_function(wq_entry, mode, flags, key); list_del_init_careful(&wq_entry->entry); return 0; } /* * Calculate the accumulated budget, pay debt if @pay_debt and wake up waiters * accordingly. When @pay_debt is %true, the caller must be holding ioc->lock in * addition to iocg->waitq.lock. */ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 vshortage, expires, oexpires; s64 vbudget; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); current_hweight(iocg, &hwa, NULL); vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ if (pay_debt && iocg->abs_vdebt && vbudget > 0) { u64 abs_vbudget = cost_to_abs_cost(vbudget, hwa); u64 abs_vpay = min_t(u64, abs_vbudget, iocg->abs_vdebt); u64 vpay = abs_cost_to_cost(abs_vpay, hwa); lockdep_assert_held(&ioc->lock); atomic64_add(vpay, &iocg->vtime); atomic64_add(vpay, &iocg->done_vtime); iocg_pay_debt(iocg, abs_vpay, now); vbudget -= vpay; } if (iocg->abs_vdebt || iocg->delay) iocg_kick_delay(iocg, now); /* * Debt can still be outstanding if we haven't paid all yet or the * caller raced and called without @pay_debt. Shouldn't wake up waiters * under debt. Make sure @vbudget reflects the outstanding amount and is * not positive. */ if (iocg->abs_vdebt) { s64 vdebt = abs_cost_to_cost(iocg->abs_vdebt, hwa); vbudget = min_t(s64, 0, vbudget - vdebt); } /* * Wake up the ones which are due and see how much vtime we'll need for * the next one. As paying off debt restores hw_inuse, it must be read * after the above debt payment. */ ctx.vbudget = vbudget; current_hweight(iocg, NULL, &ctx.hw_inuse); __wake_up_locked_key(&iocg->waitq, TASK_NORMAL, &ctx); if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { iocg->local_stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; } if (!iocg->wait_since) iocg->wait_since = now->now; if (WARN_ON_ONCE(ctx.vbudget >= 0)) return; /* determine next wakeup, add a timer margin to guarantee chunking */ vshortage = -ctx.vbudget; expires = now->now_ns + DIV64_U64_ROUND_UP(vshortage, ioc->vtime_base_rate) * NSEC_PER_USEC; expires += ioc->timer_slack_ns; /* if already active and close enough, don't bother */ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->waitq_timer)); if (hrtimer_is_queued(&iocg->waitq_timer) && abs(oexpires - expires) <= ioc->timer_slack_ns) return; hrtimer_start_range_ns(&iocg->waitq_timer, ns_to_ktime(expires), ioc->timer_slack_ns, HRTIMER_MODE_ABS); } static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, waitq_timer); bool pay_debt = READ_ONCE(iocg->abs_vdebt); struct ioc_now now; unsigned long flags; ioc_now(iocg->ioc, &now); iocg_lock(iocg, pay_debt, &flags); iocg_kick_waitq(iocg, pay_debt, &now); iocg_unlock(iocg, pay_debt, &flags); return HRTIMER_NORESTART; } static void ioc_lat_stat(struct ioc *ioc, u32 *missed_ppm_ar, u32 *rq_wait_pct_p) { u32 nr_met[2] = { }; u32 nr_missed[2] = { }; u64 rq_wait_ns = 0; int cpu, rw; for_each_online_cpu(cpu) { struct ioc_pcpu_stat *stat = per_cpu_ptr(ioc->pcpu_stat, cpu); u64 this_rq_wait_ns; for (rw = READ; rw <= WRITE; rw++) { u32 this_met = local_read(&stat->missed[rw].nr_met); u32 this_missed = local_read(&stat->missed[rw].nr_missed); nr_met[rw] += this_met - stat->missed[rw].last_met; nr_missed[rw] += this_missed - stat->missed[rw].last_missed; stat->missed[rw].last_met = this_met; stat->missed[rw].last_missed = this_missed; } this_rq_wait_ns = local64_read(&stat->rq_wait_ns); rq_wait_ns += this_rq_wait_ns - stat->last_rq_wait_ns; stat->last_rq_wait_ns = this_rq_wait_ns; } for (rw = READ; rw <= WRITE; rw++) { if (nr_met[rw] + nr_missed[rw]) missed_ppm_ar[rw] = DIV64_U64_ROUND_UP((u64)nr_missed[rw] * MILLION, nr_met[rw] + nr_missed[rw]); else missed_ppm_ar[rw] = 0; } *rq_wait_pct_p = div64_u64(rq_wait_ns * 100, ioc->period_us * NSEC_PER_USEC); } /* was iocg idle this period? */ static bool iocg_is_idle(struct ioc_gq *iocg) { struct ioc *ioc = iocg->ioc; /* did something get issued this period? */ if (atomic64_read(&iocg->active_period) == atomic64_read(&ioc->cur_period)) return false; /* is something in flight? */ if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; } /* * Call this function on the target leaf @iocg's to build pre-order traversal * list of all the ancestors in @inner_walk. The inner nodes are linked through * ->walk_list and the caller is responsible for dissolving the list after use. */ static void iocg_build_inner_walk(struct ioc_gq *iocg, struct list_head *inner_walk) { int lvl; WARN_ON_ONCE(!list_empty(&iocg->walk_list)); /* find the first ancestor which hasn't been visited yet */ for (lvl = iocg->level - 1; lvl >= 0; lvl--) { if (!list_empty(&iocg->ancestors[lvl]->walk_list)) break; } /* walk down and visit the inner nodes to get pre-order traversal */ while (++lvl <= iocg->level - 1) { struct ioc_gq *inner = iocg->ancestors[lvl]; /* record traversal order */ list_add_tail(&inner->walk_list, inner_walk); } } /* collect per-cpu counters and propagate the deltas to the parent */ static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct iocg_stat new_stat; u64 abs_vusage = 0; u64 vusage_delta; int cpu; lockdep_assert_held(&iocg->ioc->lock); /* collect per-cpu counters */ for_each_possible_cpu(cpu) { abs_vusage += local64_read( per_cpu_ptr(&iocg->pcpu_stat->abs_vusage, cpu)); } vusage_delta = abs_vusage - iocg->last_stat_abs_vusage; iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); iocg->local_stat.usage_us += iocg->usage_delta_us; /* propagate upwards */ new_stat.usage_us = iocg->local_stat.usage_us + iocg->desc_stat.usage_us; new_stat.wait_us = iocg->local_stat.wait_us + iocg->desc_stat.wait_us; new_stat.indebt_us = iocg->local_stat.indebt_us + iocg->desc_stat.indebt_us; new_stat.indelay_us = iocg->local_stat.indelay_us + iocg->desc_stat.indelay_us; /* propagate the deltas to the parent */ if (iocg->level > 0) { struct iocg_stat *parent_stat = &iocg->ancestors[iocg->level - 1]->desc_stat; parent_stat->usage_us += new_stat.usage_us - iocg->last_stat.usage_us; parent_stat->wait_us += new_stat.wait_us - iocg->last_stat.wait_us; parent_stat->indebt_us += new_stat.indebt_us - iocg->last_stat.indebt_us; parent_stat->indelay_us += new_stat.indelay_us - iocg->last_stat.indelay_us; } iocg->last_stat = new_stat; } /* get stat counters ready for reading on all active iocgs */ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) { LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg; /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { iocg_flush_stat_one(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { iocg_flush_stat_one(iocg, now); list_del_init(&iocg->walk_list); } } /* * Determine what @iocg's hweight_inuse should be after donating unused * capacity. @hwm is the upper bound and used to signal no donation. This * function also throws away @iocg's excess budget. */ static u32 hweight_after_donation(struct ioc_gq *iocg, u32 old_hwi, u32 hwm, u32 usage, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 vtime = atomic64_read(&iocg->vtime); s64 excess, delta, target, new_hwi; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return 1; /* see whether minimum margin requirement is met */ if (waitqueue_active(&iocg->waitq) || time_after64(vtime, now->vnow - ioc->margins.min)) return hwm; /* throw away excess above target */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { atomic64_add(excess, &iocg->vtime); atomic64_add(excess, &iocg->done_vtime); vtime += excess; ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } /* * Let's say the distance between iocg's and device's vtimes as a * fraction of period duration is delta. Assuming that the iocg will * consume the usage determined above, we want to determine new_hwi so * that delta equals MARGIN_TARGET at the end of the next period. * * We need to execute usage worth of IOs while spending the sum of the * new budget (1 - MARGIN_TARGET) and the leftover from the last period * (delta): * * usage = (1 - MARGIN_TARGET + delta) * new_hwi * * Therefore, the new_hwi is: * * new_hwi = usage / (1 - MARGIN_TARGET + delta) */ delta = div64_s64(WEIGHT_ONE * (now->vnow - vtime), now->vnow - ioc->period_at_vtime); target = WEIGHT_ONE * MARGIN_TARGET_PCT / 100; new_hwi = div64_s64(WEIGHT_ONE * usage, WEIGHT_ONE - target + delta); return clamp_t(s64, new_hwi, 1, hwm); } /* * For work-conservation, an iocg which isn't using all of its share should * donate the leftover to other iocgs. There are two ways to achieve this - 1. * bumping up vrate accordingly 2. lowering the donating iocg's inuse weight. * * #1 is mathematically simpler but has the drawback of requiring synchronous * global hweight_inuse updates when idle iocg's get activated or inuse weights * change due to donation snapbacks as it has the possibility of grossly * overshooting what's allowed by the model and vrate. * * #2 is inherently safe with local operations. The donating iocg can easily * snap back to higher weights when needed without worrying about impacts on * other nodes as the impacts will be inherently correct. This also makes idle * iocg activations safe. The only effect activations have is decreasing * hweight_inuse of others, the right solution to which is for those iocgs to * snap back to higher weights. * * So, we go with #2. The challenge is calculating how each donating iocg's * inuse should be adjusted to achieve the target donation amounts. This is done * using Andy's method described in the following pdf. * * https://drive.google.com/file/d/1PsJwxPFtjUnwOY1QJ5AeICCcsL7BM3bo * * Given the weights and target after-donation hweight_inuse values, Andy's * method determines how the proportional distribution should look like at each * sibling level to maintain the relative relationship between all non-donating * pairs. To roughly summarize, it divides the tree into donating and * non-donating parts, calculates global donation rate which is used to * determine the target hweight_inuse for each node, and then derives per-level * proportions. * * The following pdf shows that global distribution calculated this way can be * achieved by scaling inuse weights of donating leaves and propagating the * adjustments upwards proportionally. * * https://drive.google.com/file/d/1vONz1-fzVO7oY5DXXsLjSxEtYYQbOvsE * * Combining the above two, we can determine how each leaf iocg's inuse should * be adjusted to achieve the target donation. * * https://drive.google.com/file/d/1WcrltBOSPN0qXVdBgnKm4mdp9FhuEFQN * * The inline comments use symbols from the last pdf. * * b is the sum of the absolute budgets in the subtree. 1 for the root node. * f is the sum of the absolute budgets of non-donating nodes in the subtree. * t is the sum of the absolute budgets of donating nodes in the subtree. * w is the weight of the node. w = w_f + w_t * w_f is the non-donating portion of w. w_f = w * f / b * w_b is the donating portion of w. w_t = w * t / b * s is the sum of all sibling weights. s = Sum(w) for siblings * s_f and s_t are the non-donating and donating portions of s. * * Subscript p denotes the parent's counterpart and ' the adjusted value - e.g. * w_pt is the donating portion of the parent's weight and w'_pt the same value * after adjustments. Subscript r denotes the root node's values. */ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now) { LIST_HEAD(over_hwa); LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg, *root_iocg; u32 after_sum, over_sum, over_target, gamma; /* * It's pretty unlikely but possible for the total sum of * hweight_after_donation's to be higher than WEIGHT_ONE, which will * confuse the following calculations. If such condition is detected, * scale down everyone over its full share equally to keep the sum below * WEIGHT_ONE. */ after_sum = 0; over_sum = 0; list_for_each_entry(iocg, surpluses, surplus_list) { u32 hwa; current_hweight(iocg, &hwa, NULL); after_sum += iocg->hweight_after_donation; if (iocg->hweight_after_donation > hwa) { over_sum += iocg->hweight_after_donation; list_add(&iocg->walk_list, &over_hwa); } } if (after_sum >= WEIGHT_ONE) { /* * The delta should be deducted from the over_sum, calculate * target over_sum value. */ u32 over_delta = after_sum - (WEIGHT_ONE - 1); WARN_ON_ONCE(over_sum <= over_delta); over_target = over_sum - over_delta; } else { over_target = 0; } list_for_each_entry_safe(iocg, tiocg, &over_hwa, walk_list) { if (over_target) iocg->hweight_after_donation = div_u64((u64)iocg->hweight_after_donation * over_target, over_sum); list_del_init(&iocg->walk_list); } /* * Build pre-order inner node walk list and prepare for donation * adjustment calculations. */ list_for_each_entry(iocg, surpluses, surplus_list) { iocg_build_inner_walk(iocg, &inner_walk); } root_iocg = list_first_entry(&inner_walk, struct ioc_gq, walk_list); WARN_ON_ONCE(root_iocg->level > 0); list_for_each_entry(iocg, &inner_walk, walk_list) { iocg->child_adjusted_sum = 0; iocg->hweight_donating = 0; iocg->hweight_after_donation = 0; } /* * Propagate the donating budget (b_t) and after donation budget (b'_t) * up the hierarchy. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } list_for_each_entry_reverse(iocg, &inner_walk, walk_list) { if (iocg->level > 0) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } } /* * Calculate inner hwa's (b) and make sure the donation values are * within the accepted ranges as we're doing low res calculations with * roundups. */ list_for_each_entry(iocg, &inner_walk, walk_list) { if (iocg->level) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; iocg->hweight_active = DIV64_U64_ROUND_UP( (u64)parent->hweight_active * iocg->active, parent->child_active_sum); } iocg->hweight_donating = min(iocg->hweight_donating, iocg->hweight_active); iocg->hweight_after_donation = min(iocg->hweight_after_donation, iocg->hweight_donating - 1); if (WARN_ON_ONCE(iocg->hweight_active <= 1 || iocg->hweight_donating <= 1 || iocg->hweight_after_donation == 0)) { pr_warn("iocg: invalid donation weights in "); pr_cont_cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup); pr_cont(": active=%u donating=%u after=%u\n", iocg->hweight_active, iocg->hweight_donating, iocg->hweight_after_donation); } } /* * Calculate the global donation rate (gamma) - the rate to adjust * non-donating budgets by. * * No need to use 64bit multiplication here as the first operand is * guaranteed to be smaller than WEIGHT_ONE (1<<16). * * We know that there are beneficiary nodes and the sum of the donating * hweights can't be whole; however, due to the round-ups during hweight * calculations, root_iocg->hweight_donating might still end up equal to * or greater than whole. Limit the range when calculating the divider. * * gamma = (1 - t_r') / (1 - t_r) */ gamma = DIV_ROUND_UP( (WEIGHT_ONE - root_iocg->hweight_after_donation) * WEIGHT_ONE, WEIGHT_ONE - min_t(u32, root_iocg->hweight_donating, WEIGHT_ONE - 1)); /* * Calculate adjusted hwi, child_adjusted_sum and inuse for the inner * nodes. */ list_for_each_entry(iocg, &inner_walk, walk_list) { struct ioc_gq *parent; u32 inuse, wpt, wptp; u64 st, sf; if (iocg->level == 0) { /* adjusted weight sum for 1st level: s' = s * b_pf / b'_pf */ iocg->child_adjusted_sum = DIV64_U64_ROUND_UP( iocg->child_active_sum * (WEIGHT_ONE - iocg->hweight_donating), WEIGHT_ONE - iocg->hweight_after_donation); continue; } parent = iocg->ancestors[iocg->level - 1]; /* b' = gamma * b_f + b_t' */ iocg->hweight_inuse = DIV64_U64_ROUND_UP( (u64)gamma * (iocg->hweight_active - iocg->hweight_donating), WEIGHT_ONE) + iocg->hweight_after_donation; /* w' = s' * b' / b'_p */ inuse = DIV64_U64_ROUND_UP( (u64)parent->child_adjusted_sum * iocg->hweight_inuse, parent->hweight_inuse); /* adjusted weight sum for children: s' = s_f + s_t * w'_pt / w_pt */ st = DIV64_U64_ROUND_UP( iocg->child_active_sum * iocg->hweight_donating, iocg->hweight_active); sf = iocg->child_active_sum - st; wpt = DIV64_U64_ROUND_UP( (u64)iocg->active * iocg->hweight_donating, iocg->hweight_active); wptp = DIV64_U64_ROUND_UP( (u64)inuse * iocg->hweight_after_donation, iocg->hweight_inuse); iocg->child_adjusted_sum = sf + DIV64_U64_ROUND_UP(st * wptp, wpt); } /* * All inner nodes now have ->hweight_inuse and ->child_adjusted_sum and * we can finally determine leaf adjustments. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; u32 inuse; /* * In-debt iocgs participated in the donation calculation with * the minimum target hweight_inuse. Configuring inuse * accordingly would work fine but debt handling expects * @iocg->inuse stay at the minimum and we don't wanna * interfere. */ if (iocg->abs_vdebt) { WARN_ON_ONCE(iocg->inuse > 1); continue; } /* w' = s' * b' / b'_p, note that b' == b'_t for donating leaves */ inuse = DIV64_U64_ROUND_UP( parent->child_adjusted_sum * iocg->hweight_after_donation, parent->hweight_inuse); TRACE_IOCG_PATH(inuse_transfer, iocg, now, iocg->inuse, inuse, iocg->hweight_inuse, iocg->hweight_after_donation); __propagate_weights(iocg, iocg->active, inuse, true, now); } /* walk list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &inner_walk, walk_list) list_del_init(&iocg->walk_list); } /* * A low weight iocg can amass a large amount of debt, for example, when * anonymous memory gets reclaimed aggressively. If the system has a lot of * memory paired with a slow IO device, the debt can span multiple seconds or * more. If there are no other subsequent IO issuers, the in-debt iocg may end * up blocked paying its debt while the IO device is idle. * * The following protects against such cases. If the device has been * sufficiently idle for a while, the debts are halved and delays are * recalculated. */ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; u64 dur, usage_pct, nr_cycles; /* if no debtor, reset the cycle */ if (!nr_debtors) { ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc->dfgv_usage_us_sum = 0; return; } /* * Debtors can pass through a lot of writes choking the device and we * don't want to be forgiving debts while the device is struggling from * write bursts. If we're missing latency targets, consider the device * fully utilized. */ if (ioc->busy_level > 0) usage_us_sum = max_t(u64, usage_us_sum, ioc->period_us); ioc->dfgv_usage_us_sum += usage_us_sum; if (time_before64(now->now, ioc->dfgv_period_at + DFGV_PERIOD)) return; /* * At least DFGV_PERIOD has passed since the last period. Calculate the * average usage and reset the period counters. */ dur = now->now - ioc->dfgv_period_at; usage_pct = div64_u64(100 * ioc->dfgv_usage_us_sum, dur); ioc->dfgv_period_at = now->now; ioc->dfgv_usage_us_sum = 0; /* if was too busy, reset everything */ if (usage_pct > DFGV_USAGE_PCT) { ioc->dfgv_period_rem = 0; return; } /* * Usage is lower than threshold. Let's forgive some debts. Debt * forgiveness runs off of the usual ioc timer but its period usually * doesn't match ioc's. Compensate the difference by performing the * reduction as many times as would fit in the duration since the last * run and carrying over the left-over duration in @ioc->dfgv_period_rem * - if ioc period is 75% of DFGV_PERIOD, one out of three consecutive * reductions is doubled. */ nr_cycles = dur + ioc->dfgv_period_rem; ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD); list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 __maybe_unused old_debt, __maybe_unused old_delay; if (!iocg->abs_vdebt && !iocg->delay) continue; spin_lock(&iocg->waitq.lock); old_debt = iocg->abs_vdebt; old_delay = iocg->delay; if (iocg->abs_vdebt) iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles ?: 1; if (iocg->delay) iocg->delay = iocg->delay >> nr_cycles ?: 1; iocg_kick_waitq(iocg, true, now); TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct, old_debt, iocg->abs_vdebt, old_delay, iocg->delay); spin_unlock(&iocg->waitq.lock); } } /* * Check the active iocgs' state to avoid oversleeping and deactive * idle iocgs. * * Since waiters determine the sleep durations based on the vrate * they saw at the time of sleep, if vrate has increased, some * waiters could be sleeping for too long. Wake up tardy waiters * which should have woken up in the last period and expire idle * iocgs. */ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) { int nr_debtors = 0; struct ioc_gq *iocg, *tiocg; list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && !iocg->delay && !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); /* flush wait and indebt stat deltas */ if (iocg->wait_since) { iocg->local_stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { iocg->local_stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { iocg->local_stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt || iocg->delay) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, true, now); if (iocg->abs_vdebt || iocg->delay) nr_debtors++; } else if (iocg_is_idle(iocg)) { /* no waiter and idle, deactivate */ u64 vtime = atomic64_read(&iocg->vtime); s64 excess; /* * @iocg has been inactive for a full duration and will * have a high budget. Account anything above target as * error and throw away. On reactivation, it'll start * with the target budget. */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { u32 old_hwi; current_hweight(iocg, NULL, &old_hwi); ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } TRACE_IOCG_PATH(iocg_idle, iocg, now, atomic64_read(&iocg->active_period), atomic64_read(&ioc->cur_period), vtime); __propagate_weights(iocg, 0, 0, false, now); list_del_init(&iocg->active_list); } spin_unlock(&iocg->waitq.lock); } commit_weights(ioc); return nr_debtors; } static void ioc_timer_fn(struct timer_list *timer) { struct ioc *ioc = container_of(timer, struct ioc, timer); struct ioc_gq *iocg, *tiocg; struct ioc_now now; LIST_HEAD(surpluses); int nr_debtors, nr_shortages = 0, nr_lagging = 0; u64 usage_us_sum = 0; u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM]; u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM]; u32 missed_ppm[2], rq_wait_pct; u64 period_vtime; int prev_busy_level; /* how were the latencies during the period? */ ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct); /* take care of active iocgs */ spin_lock_irq(&ioc->lock); ioc_now(ioc, &now); period_vtime = now.vnow - ioc->period_at_vtime; if (WARN_ON_ONCE(!period_vtime)) { spin_unlock_irq(&ioc->lock); return; } nr_debtors = ioc_check_iocgs(ioc, &now); /* * Wait and indebt stat are flushed above and the donation calculation * below needs updated usage stat. Let's bring stat up-to-date. */ iocg_flush_stat(&ioc->active_iocgs, &now); /* calc usage and see whether some weights need to be moved around */ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 vdone, vtime, usage_us; u32 hw_active, hw_inuse; /* * Collect unused and wind vtime closer to vnow to prevent * iocgs from accumulating a large amount of budget. */ vdone = atomic64_read(&iocg->done_vtime); vtime = atomic64_read(&iocg->vtime); current_hweight(iocg, &hw_active, &hw_inuse); /* * Latency QoS detection doesn't account for IOs which are * in-flight for longer than a period. Detect them by * comparing vdone against period start. If lagging behind * IOs from past periods, don't increase vrate. */ if ((ppm_rthr != MILLION || ppm_wthr != MILLION) && !atomic_read(&iocg_to_blkg(iocg)->use_delay) && time_after64(vtime, vdone) && time_after64(vtime, now.vnow - MAX_LAGGING_PERIODS * period_vtime) && time_before64(vdone, now.vnow - period_vtime)) nr_lagging++; /* * Determine absolute usage factoring in in-flight IOs to avoid * high-latency completions appearing as idle. */ usage_us = iocg->usage_delta_us; usage_us_sum += usage_us; /* see whether there's surplus vtime */ WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); if (hw_inuse < hw_active || (!waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow - ioc->margins.low))) { u32 hwa, old_hwi, hwm, new_hwi, usage; u64 usage_dur; if (vdone != vtime) { u64 inflight_us = DIV64_U64_ROUND_UP( cost_to_abs_cost(vtime - vdone, hw_inuse), ioc->vtime_base_rate); usage_us = max(usage_us, inflight_us); } /* convert to hweight based usage ratio */ if (time_after64(iocg->activated_at, ioc->period_at)) usage_dur = max_t(u64, now.now - iocg->activated_at, 1); else usage_dur = max_t(u64, now.now - ioc->period_at, 1); usage = clamp_t(u32, DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, usage_dur), 1, WEIGHT_ONE); /* * Already donating or accumulated enough to start. * Determine the donation amount. */ current_hweight(iocg, &hwa, &old_hwi); hwm = current_hweight_max(iocg); new_hwi = hweight_after_donation(iocg, old_hwi, hwm, usage, &now); /* * Donation calculation assumes hweight_after_donation * to be positive, a condition that a donor w/ hwa < 2 * can't meet. Don't bother with donation if hwa is * below 2. It's not gonna make a meaningful difference * anyway. */ if (new_hwi < hwm && hwa >= 2) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); } else if (!iocg->abs_vdebt) { /* * @iocg doesn't have enough to donate. Reset * its inuse to active. * * Don't reset debtors as their inuse's are * owned by debt handling. This shouldn't affect * donation calculuation in any meaningful way * as @iocg doesn't have a meaningful amount of * share anyway. */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); __propagate_weights(iocg, iocg->active, iocg->active, true, &now); nr_shortages++; } } else { /* genuinely short on vtime */ nr_shortages++; } } if (!list_empty(&surpluses) && nr_shortages) transfer_surpluses(&surpluses, &now); commit_weights(ioc); /* surplus list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &surpluses, surplus_list) list_del_init(&iocg->surplus_list); /* * If q is getting clogged or we're missing too much, we're issuing * too much IO and should lower vtime rate. If we're not missing * and experiencing shortages but not surpluses, we're too stingy * and should increase vtime rate. */ prev_busy_level = ioc->busy_level; if (rq_wait_pct > RQ_WAIT_BUSY_PCT || missed_ppm[READ] > ppm_rthr || missed_ppm[WRITE] > ppm_wthr) { /* clearly missing QoS targets, slow down vrate */ ioc->busy_level = max(ioc->busy_level, 0); ioc->busy_level++; } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 && missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 && missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) { /* QoS targets are being met with >25% margin */ if (nr_shortages) { /* * We're throttling while the device has spare * capacity. If vrate was being slowed down, stop. */ ioc->busy_level = min(ioc->busy_level, 0); /* * If there are IOs spanning multiple periods, wait * them out before pushing the device harder. */ if (!nr_lagging) ioc->busy_level--; } else { /* * Nobody is being throttled and the users aren't * issuing enough IOs to saturate the device. We * simply don't know how close the device is to * saturation. Coast. */ ioc->busy_level = 0; } } else { /* inside the hysterisis margin, we're good */ ioc->busy_level = 0; } ioc->busy_level = clamp(ioc->busy_level, -1000, 1000); ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages, prev_busy_level, missed_ppm); ioc_refresh_params(ioc, false); ioc_forgive_debts(ioc, usage_us_sum, nr_debtors, &now); /* * This period is done. Move onto the next one. If nothing's * going on with the device, stop the timer. */ atomic64_inc(&ioc->cur_period); if (ioc->running != IOC_STOP) { if (!list_empty(&ioc->active_iocgs)) { ioc_start_period(ioc, &now); } else { ioc->busy_level = 0; ioc->vtime_err = 0; ioc->running = IOC_IDLE; } ioc_refresh_vrate(ioc, &now); } spin_unlock_irq(&ioc->lock); } static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u64 abs_cost, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct ioc_margins *margins = &ioc->margins; u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi; u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; cost = abs_cost_to_cost(abs_cost, hwi); margin = now->vnow - vtime - cost; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return cost; /* * We only increase inuse during period and do so if the margin has * deteriorated since the previous adjustment. */ if (margin >= iocg->saved_margin || margin >= margins->low || iocg->inuse == iocg->active) return cost; spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { spin_unlock_irqrestore(&ioc->lock, flags); return cost; } /* * Bump up inuse till @abs_cost fits in the existing budget. * adj_step must be determined after acquiring ioc->lock - we might * have raced and lost to another thread for activation and could * be reading 0 iocg->active before ioc->lock which will lead to * infinite loop. */ new_inuse = iocg->inuse; adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100); do { new_inuse = new_inuse + adj_step; propagate_weights(iocg, iocg->active, new_inuse, true, now); current_hweight(iocg, NULL, &hwi); cost = abs_cost_to_cost(abs_cost, hwi); } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); return cost; } static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg, bool is_merge, u64 *costp) { struct ioc *ioc = iocg->ioc; u64 coef_seqio, coef_randio, coef_page; u64 pages = max_t(u64, bio_sectors(bio) >> IOC_SECT_TO_PAGE_SHIFT, 1); u64 seek_pages = 0; u64 cost = 0; switch (bio_op(bio)) { case REQ_OP_READ: coef_seqio = ioc->params.lcoefs[LCOEF_RSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_RRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: coef_seqio = ioc->params.lcoefs[LCOEF_WSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_WRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_WPAGE]; break; default: goto out; } if (iocg->cursor) { seek_pages = abs(bio->bi_iter.bi_sector - iocg->cursor); seek_pages >>= IOC_SECT_TO_PAGE_SHIFT; } if (!is_merge) { if (seek_pages > LCOEF_RANDIO_PAGES) { cost += coef_randio; } else { cost += coef_seqio; } } cost += pages * coef_page; out: *costp = cost; } static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge) { u64 cost; calc_vtime_cost_builtin(bio, iocg, is_merge, &cost); return cost; } static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc, u64 *costp) { unsigned int pages = blk_rq_stats_sectors(rq) >> IOC_SECT_TO_PAGE_SHIFT; switch (req_op(rq)) { case REQ_OP_READ: *costp = pages * ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: *costp = pages * ioc->params.lcoefs[LCOEF_WPAGE]; break; default: *costp = 0; } } static u64 calc_size_vtime_cost(struct request *rq, struct ioc *ioc) { u64 cost; calc_size_vtime_cost_builtin(rq, ioc, &cost); return cost; } static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_gq *iocg = blkg_to_iocg(blkg); struct ioc_now now; struct iocg_wait wait; u64 abs_cost, cost, vtime; bool use_debt, ioc_locked; unsigned long flags; /* bypass IOs if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; /* calculate the absolute vtime cost */ abs_cost = calc_vtime_cost(bio, iocg, false); if (!abs_cost) return; if (!iocg_activate(iocg, &now)) return; iocg->cursor = bio_end_sector(bio); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* * If no one's waiting and within budget, issue right away. The * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. This can be handled in two ways. IOs which may * cause priority inversions are punted to @ioc->aux_iocg and charged as * debt. Otherwise, the issuer is blocked on @iocg->waitq. Debt handling * requires @ioc->lock, waitq handling @iocg->waitq.lock. Determine * whether debt handling is needed and acquire locks accordingly. */ use_debt = bio_issue_as_root_blkg(bio) || fatal_signal_pending(current); ioc_locked = use_debt || READ_ONCE(iocg->abs_vdebt); retry_lock: iocg_lock(iocg, ioc_locked, &flags); /* * @iocg must stay activated for debt and waitq handling. Deactivation * is synchronized against both ioc->lock and waitq.lock and we won't * get deactivated as long as we're waiting or has debt, so we're good * if we're activated here. In the unlikely cases that we aren't, just * issue the IO. */ if (unlikely(list_empty(&iocg->active_list))) { iocg_unlock(iocg, ioc_locked, &flags); iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. If @bio has to be issued regardless, remember * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay * off the debt before waking more IOs. * * This way, the debt is continuously paid off each period with the * actual budget available to the cgroup. If we just wound vtime, we * would incorrectly use the current hw_inuse for the entire amount * which, for example, can lead to the cgroup staying blocked for a * long time even with substantially raised hw_inuse. * * An iocg with vdebt should stay online so that the timer can keep * deducting its vdebt and [de]activate use_delay mechanism * accordingly. We don't want to race against the timer trying to * clear them and leave @iocg inactive w/ dangling use_delay heavily * penalizing the cgroup and its descendants. */ if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; } /* guarantee that iocgs w/ waiters have maximum inuse */ if (!iocg->abs_vdebt && iocg->inuse != iocg->active) { if (!ioc_locked) { iocg_unlock(iocg, false, &flags); ioc_locked = true; goto retry_lock; } propagate_weights(iocg, iocg->active, iocg->active, true, &now); } /* * Append self to the waitq and schedule the wakeup timer if we're * the first waiter. The timer duration is calculated based on the * current vrate. vtime and hweight changes can make it too short * or too long. Each wait entry records the absolute cost it's * waiting for to allow re-evaluation using a custom wait entry. * * If too short, the timer simply reschedules itself. If too long, * the period timer will notice and trigger wakeups. * * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; wait.abs_cost = abs_cost; wait.committed = false; /* will be set true by waker */ __add_wait_queue_entry_tail(&iocg->waitq, &wait.wait); iocg_kick_waitq(iocg, ioc_locked, &now); iocg_unlock(iocg, ioc_locked, &flags); while (true) { set_current_state(TASK_UNINTERRUPTIBLE); if (wait.committed) break; io_schedule(); } /* waker already committed us, proceed */ finish_wait(&iocg->waitq, &wait.wait); } static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); struct ioc *ioc = rqos_to_ioc(rqos); sector_t bio_end = bio_end_sector(bio); struct ioc_now now; u64 vtime, abs_cost, cost; unsigned long flags; /* bypass if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; abs_cost = calc_vtime_cost(bio, iocg, true); if (!abs_cost) return; ioc_now(ioc, &now); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* update cursor if backmerging into the request at the cursor */ if (blk_rq_pos(rq) < bio_end && blk_rq_pos(rq) + blk_rq_sectors(rq) == iocg->cursor) iocg->cursor = bio_end; /* * Charge if there's enough vtime budget and the existing request has * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * Otherwise, account it as debt if @iocg is online, which it should * be for the vast majority of cases. See debt handling in * ioc_rqos_throttle() for details. */ spin_lock_irqsave(&ioc->lock, flags); spin_lock(&iocg->waitq.lock); if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); } spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); if (iocg && bio->bi_iocost_cost) atomic64_add(bio->bi_iocost_cost, &iocg->done_vtime); } static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) { struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_pcpu_stat *ccs; u64 on_q_ns, rq_wait_ns, size_nsec; int pidx, rw; if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) return; switch (req_op(rq) & REQ_OP_MASK) { case REQ_OP_READ: pidx = QOS_RLAT; rw = READ; break; case REQ_OP_WRITE: pidx = QOS_WLAT; rw = WRITE; break; default: return; } on_q_ns = ktime_get_ns() - rq->alloc_time_ns; rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns; size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC); ccs = get_cpu_ptr(ioc->pcpu_stat); if (on_q_ns <= size_nsec || on_q_ns - size_nsec <= ioc->params.qos[pidx] * NSEC_PER_USEC) local_inc(&ccs->missed[rw].nr_met); else local_inc(&ccs->missed[rw].nr_missed); local64_add(rq_wait_ns, &ccs->rq_wait_ns); put_cpu_ptr(ccs); } static void ioc_rqos_queue_depth_changed(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); spin_lock_irq(&ioc->lock); ioc_refresh_params(ioc, false); spin_unlock_irq(&ioc->lock); } static void ioc_rqos_exit(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); blkcg_deactivate_policy(rqos->q, &blkcg_policy_iocost); spin_lock_irq(&ioc->lock); ioc->running = IOC_STOP; spin_unlock_irq(&ioc->lock); del_timer_sync(&ioc->timer); free_percpu(ioc->pcpu_stat); kfree(ioc); } static struct rq_qos_ops ioc_rqos_ops = { .throttle = ioc_rqos_throttle, .merge = ioc_rqos_merge, .done_bio = ioc_rqos_done_bio, .done = ioc_rqos_done, .queue_depth_changed = ioc_rqos_queue_depth_changed, .exit = ioc_rqos_exit, }; static int blk_iocost_init(struct request_queue *q) { struct ioc *ioc; struct rq_qos *rqos; int i, cpu, ret; ioc = kzalloc(sizeof(*ioc), GFP_KERNEL); if (!ioc) return -ENOMEM; ioc->pcpu_stat = alloc_percpu(struct ioc_pcpu_stat); if (!ioc->pcpu_stat) { kfree(ioc); return -ENOMEM; } for_each_possible_cpu(cpu) { struct ioc_pcpu_stat *ccs = per_cpu_ptr(ioc->pcpu_stat, cpu); for (i = 0; i < ARRAY_SIZE(ccs->missed); i++) { local_set(&ccs->missed[i].nr_met, 0); local_set(&ccs->missed[i].nr_missed, 0); } local64_set(&ccs->rq_wait_ns, 0); } rqos = &ioc->rqos; rqos->id = RQ_QOS_COST; rqos->ops = &ioc_rqos_ops; rqos->q = q; spin_lock_init(&ioc->lock); timer_setup(&ioc->timer, ioc_timer_fn, 0); INIT_LIST_HEAD(&ioc->active_iocgs); ioc->running = IOC_IDLE; ioc->vtime_base_rate = VTIME_PER_USEC; atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock); ioc->period_at = ktime_to_us(ktime_get()); atomic64_set(&ioc->cur_period, 0); atomic_set(&ioc->hweight_gen, 0); spin_lock_irq(&ioc->lock); ioc->autop_idx = AUTOP_INVALID; ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); /* * rqos must be added before activation to allow iocg_pd_init() to * lookup the ioc from q. This means that the rqos methods may get * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ ret = rq_qos_add(q, rqos); if (ret) goto err_free_ioc; ret = blkcg_activate_policy(q, &blkcg_policy_iocost); if (ret) goto err_del_qos; return 0; err_del_qos: rq_qos_del(q, rqos); err_free_ioc: free_percpu(ioc->pcpu_stat); kfree(ioc); return ret; } static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp) { struct ioc_cgrp *iocc; iocc = kzalloc(sizeof(struct ioc_cgrp), gfp); if (!iocc) return NULL; iocc->dfl_weight = CGROUP_WEIGHT_DFL * WEIGHT_ONE; return &iocc->cpd; } static void ioc_cpd_free(struct blkcg_policy_data *cpd) { kfree(container_of(cpd, struct ioc_cgrp, cpd)); } static struct blkg_policy_data *ioc_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) { int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, q->node); if (!iocg) return NULL; iocg->pcpu_stat = alloc_percpu_gfp(struct iocg_pcpu_stat, gfp); if (!iocg->pcpu_stat) { kfree(iocg); return NULL; } return &iocg->pd; } static void ioc_pd_init(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd); struct ioc *ioc = q_to_ioc(blkg->q); struct ioc_now now; struct blkcg_gq *tblkg; unsigned long flags; ioc_now(ioc, &now); iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); INIT_LIST_HEAD(&iocg->walk_list); INIT_LIST_HEAD(&iocg->surplus_list); iocg->hweight_active = WEIGHT_ONE; iocg->hweight_inuse = WEIGHT_ONE; init_waitqueue_head(&iocg->waitq); hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); iocg->waitq_timer.function = iocg_waitq_timer_fn; iocg->level = blkg->blkcg->css.cgroup->level; for (tblkg = blkg; tblkg; tblkg = tblkg->parent) { struct ioc_gq *tiocg = blkg_to_iocg(tblkg); iocg->ancestors[tiocg->level] = tiocg; } spin_lock_irqsave(&ioc->lock, flags); weight_updated(iocg, &now); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_pd_free(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; unsigned long flags; if (ioc) { spin_lock_irqsave(&ioc->lock, flags); if (!list_empty(&iocg->active_list)) { struct ioc_now now; ioc_now(ioc, &now); propagate_weights(iocg, 0, 0, false, &now); list_del_init(&iocg->active_list); } WARN_ON_ONCE(!list_empty(&iocg->walk_list)); WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); spin_unlock_irqrestore(&ioc->lock, flags); hrtimer_cancel(&iocg->waitq_timer); } free_percpu(iocg->pcpu_stat); kfree(iocg); } static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) return false; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); return true; } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc_gq *iocg = pd_to_iocg(pd); if (dname && iocg->cfg_weight) seq_printf(sf, "%s %u\n", dname, iocg->cfg_weight / WEIGHT_ONE); return 0; } static int ioc_weight_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); seq_printf(sf, "default %u\n", iocc->dfl_weight / WEIGHT_ONE); blkcg_print_blkgs(sf, blkcg, ioc_weight_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); struct blkg_conf_ctx ctx; struct ioc_now now; struct ioc_gq *iocg; u32 v; int ret; if (!strchr(buf, ':')) { struct blkcg_gq *blkg; if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v)) return -EINVAL; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); } } spin_unlock_irq(&blkcg->lock); return nbytes; } ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, buf, &ctx); if (ret) return ret; iocg = blkg_to_iocg(ctx.blkg); if (!strncmp(ctx.body, "default", 7)) { v = 0; } else { if (!sscanf(ctx.body, "%u", &v)) goto einval; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) goto einval; } spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v * WEIGHT_ONE; ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); blkg_conf_finish(&ctx); return nbytes; einval: blkg_conf_finish(&ctx); return -EINVAL; } static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; if (!dname) return 0; seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, ioc->params.qos[QOS_RPPM] % 10000 / 100, ioc->params.qos[QOS_RLAT], ioc->params.qos[QOS_WPPM] / 10000, ioc->params.qos[QOS_WPPM] % 10000 / 100, ioc->params.qos[QOS_WLAT], ioc->params.qos[QOS_MIN] / 10000, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); return 0; } static int ioc_qos_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_qos_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t qos_ctrl_tokens = { { QOS_ENABLE, "enable=%u" }, { QOS_CTRL, "ctrl=%s" }, { NR_QOS_CTRL_PARAMS, NULL }, }; static const match_table_t qos_tokens = { { QOS_RPPM, "rpct=%s" }, { QOS_RLAT, "rlat=%u" }, { QOS_WPPM, "wpct=%s" }, { QOS_WLAT, "wlat=%u" }, { QOS_MIN, "min=%s" }, { QOS_MAX, "max=%s" }, { NR_QOS_PARAMS, NULL }, }; static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct block_device *bdev; struct ioc *ioc; u32 qos[NR_QOS_PARAMS]; bool enable, user; char *p; int ret; bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); ioc = q_to_ioc(bdev->bd_disk->queue); if (!ioc) { ret = blk_iocost_init(bdev->bd_disk->queue); if (ret) goto err; ioc = q_to_ioc(bdev->bd_disk->queue); } spin_lock_irq(&ioc->lock); memcpy(qos, ioc->params.qos, sizeof(qos)); enable = ioc->enabled; user = ioc->user_qos_params; spin_unlock_irq(&ioc->lock); while ((p = strsep(&input, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; s64 v; if (!*p) continue; switch (match_token(p, qos_ctrl_tokens, args)) { case QOS_ENABLE: match_u64(&args[0], &v); enable = v; continue; case QOS_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; } tok = match_token(p, qos_tokens, args); switch (tok) { case QOS_RPPM: case QOS_WPPM: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0 || v > 10000) goto einval; qos[tok] = v * 100; break; case QOS_RLAT: case QOS_WLAT: if (match_u64(&args[0], &v)) goto einval; qos[tok] = v; break; case QOS_MIN: case QOS_MAX: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0) goto einval; qos[tok] = clamp_t(s64, v * 100, VRATE_MIN_PPM, VRATE_MAX_PPM); break; default: goto einval; } user = true; } if (qos[QOS_MIN] > qos[QOS_MAX]) goto einval; spin_lock_irq(&ioc->lock); if (enable) { blk_stat_enable_accounting(ioc->rqos.q); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q); ioc->enabled = true; } else { blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q); ioc->enabled = false; } if (user) { memcpy(ioc->params.qos, qos, sizeof(qos)); ioc->user_qos_params = true; } else { ioc->user_qos_params = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blkdev_put_no_open(bdev); return nbytes; einval: ret = -EINVAL; err: blkdev_put_no_open(bdev); return ret; } static u64 ioc_cost_model_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; u64 *u = ioc->params.i_lcoefs; if (!dname) return 0; seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); return 0; } static int ioc_cost_model_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_cost_model_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t cost_ctrl_tokens = { { COST_CTRL, "ctrl=%s" }, { COST_MODEL, "model=%s" }, { NR_COST_CTRL_PARAMS, NULL }, }; static const match_table_t i_lcoef_tokens = { { I_LCOEF_RBPS, "rbps=%u" }, { I_LCOEF_RSEQIOPS, "rseqiops=%u" }, { I_LCOEF_RRANDIOPS, "rrandiops=%u" }, { I_LCOEF_WBPS, "wbps=%u" }, { I_LCOEF_WSEQIOPS, "wseqiops=%u" }, { I_LCOEF_WRANDIOPS, "wrandiops=%u" }, { NR_I_LCOEFS, NULL }, }; static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct block_device *bdev; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; char *p; int ret; bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); ioc = q_to_ioc(bdev->bd_disk->queue); if (!ioc) { ret = blk_iocost_init(bdev->bd_disk->queue); if (ret) goto err; ioc = q_to_ioc(bdev->bd_disk->queue); } spin_lock_irq(&ioc->lock); memcpy(u, ioc->params.i_lcoefs, sizeof(u)); user = ioc->user_cost_model; spin_unlock_irq(&ioc->lock); while ((p = strsep(&input, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; u64 v; if (!*p) continue; switch (match_token(p, cost_ctrl_tokens, args)) { case COST_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; case COST_MODEL: match_strlcpy(buf, &args[0], sizeof(buf)); if (strcmp(buf, "linear")) goto einval; continue; } tok = match_token(p, i_lcoef_tokens, args); if (tok == NR_I_LCOEFS) goto einval; if (match_u64(&args[0], &v)) goto einval; u[tok] = v; user = true; } spin_lock_irq(&ioc->lock); if (user) { memcpy(ioc->params.i_lcoefs, u, sizeof(u)); ioc->user_cost_model = true; } else { ioc->user_cost_model = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blkdev_put_no_open(bdev); return nbytes; einval: ret = -EINVAL; err: blkdev_put_no_open(bdev); return ret; } static struct cftype ioc_files[] = { { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = ioc_weight_show, .write = ioc_weight_write, }, { .name = "cost.qos", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_qos_show, .write = ioc_qos_write, }, { .name = "cost.model", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_cost_model_show, .write = ioc_cost_model_write, }, {} }; static struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, .pd_alloc_fn = ioc_pd_alloc, .pd_init_fn = ioc_pd_init, .pd_free_fn = ioc_pd_free, .pd_stat_fn = ioc_pd_stat, }; static int __init ioc_init(void) { return blkcg_policy_register(&blkcg_policy_iocost); } static void __exit ioc_exit(void) { blkcg_policy_unregister(&blkcg_policy_iocost); } module_init(ioc_init); module_exit(ioc_exit); |
| 99 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resultion entity * * Authors: * net_random Alan Cox * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/ratelimit.h> #include <linux/socket.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/ipv6.h> #include <asm/byteorder.h> #include <linux/uaccess.h> DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); /* * Convert an ASCII string to binary IP. * This is outside of net/ipv4/ because various code that uses IP addresses * is otherwise not dependent on the TCP/IP stack. */ __be32 in_aton(const char *str) { unsigned int l; unsigned int val; int i; l = 0; for (i = 0; i < 4; i++) { l <<= 8; if (*str != '\0') { val = 0; while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; } l |= val; if (*str != '\0') str++; } } return htonl(l); } EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 #define IN6PTON_DIGIT 0x00020000 #define IN6PTON_COLON_MASK 0x00700000 #define IN6PTON_COLON_1 0x00100000 /* single : requested */ #define IN6PTON_COLON_2 0x00200000 /* second : requested */ #define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ #define IN6PTON_DOT 0x00800000 /* . */ #define IN6PTON_DELIM 0x10000000 #define IN6PTON_NULL 0x20000000 /* first/tail */ #define IN6PTON_UNKNOWN 0x40000000 static inline int xdigit2bin(char c, int delim) { int val; if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; val = hex_to_bin(c); if (val >= 0) return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; } /** * in4_pton - convert an IPv4 address from literal to binary representation * @src: the start of the IPv4 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[4] array) representation of the IPv4 address * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s; u8 *d; u8 dbuf[4]; int ret = 0; int i; int w = 0; if (srclen < 0) srclen = strlen(src); s = src; d = dbuf; i = 0; while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { goto out; } if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (w == 0) goto out; *d++ = w & 0xff; w = 0; i++; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (i != 4) goto out; break; } goto cont; } w = (w * 10) + c; if ((w & 0xffff) > 255) { goto out; } cont: if (i >= 4) goto out; s++; srclen--; } ret = 1; memcpy(dst, dbuf, sizeof(dbuf)); out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in4_pton); /** * in6_pton - convert an IPv6 address from literal to binary representation * @src: the start of the IPv6 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[16] array) representation of the IPv6 address * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s, *tok = NULL; u8 *d, *dc = NULL; u8 dbuf[16]; int ret = 0; int i; int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; int w = 0; memset(dbuf, 0, sizeof(dbuf)); s = src; d = dbuf; if (srclen < 0) srclen = strlen(src); while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & state)) goto out; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { /* process one 16-bit word */ if (!(state & IN6PTON_NULL)) { *d++ = (w >> 8) & 0xff; *d++ = w & 0xff; } w = 0; if (c & IN6PTON_DELIM) { /* We've processed last word */ break; } /* * COLON_1 => XDIGIT * COLON_2 => XDIGIT|DELIM * COLON_1_2 => COLON_2 */ switch (state & IN6PTON_COLON_MASK) { case IN6PTON_COLON_2: dc = d; state = IN6PTON_XDIGIT | IN6PTON_DELIM; if (dc - dbuf >= sizeof(dbuf)) state |= IN6PTON_NULL; break; case IN6PTON_COLON_1|IN6PTON_COLON_1_2: state = IN6PTON_XDIGIT | IN6PTON_COLON_2; break; case IN6PTON_COLON_1: state = IN6PTON_XDIGIT; break; case IN6PTON_COLON_1_2: state = IN6PTON_COLON_2; break; default: state = 0; } tok = s + 1; goto cont; } if (c & IN6PTON_DOT) { ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); if (ret > 0) { d += 4; break; } goto out; } w = (w << 4) | (0xff & c); state = IN6PTON_COLON_1 | IN6PTON_DELIM; if (!(w & 0xf000)) { state |= IN6PTON_XDIGIT; } if (!dc && d + 2 < dbuf + sizeof(dbuf)) { state |= IN6PTON_COLON_1_2; state &= ~IN6PTON_DELIM; } if (d + 2 >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); } cont: if ((dc && d + 4 < dbuf + sizeof(dbuf)) || d + 4 == dbuf + sizeof(dbuf)) { state |= IN6PTON_DOT; } if (d >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); } s++; srclen--; } i = 15; d--; if (dc) { while (d >= dc) dst[i--] = *d--; while (i >= dc - dbuf) dst[i--] = 0; while (i >= 0) dst[i--] = *d--; } else memcpy(dst, dbuf, sizeof(dbuf)); ret = 1; out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in6_pton); static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; int srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr, '\n', NULL) == 0) return -EINVAL; addr4->sin_family = AF_INET; addr4->sin_port = htons(port_num); return 0; } static int inet6_pton(struct net *net, const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; int srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr, '%', &scope_delim) == 0) return -EINVAL; if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL && src + srclen != scope_delim && *scope_delim == '%') { struct net_device *dev; char scope_id[16]; size_t scope_len = min_t(size_t, sizeof(scope_id) - 1, src + srclen - scope_delim - 1); memcpy(scope_id, scope_delim + 1, scope_len); scope_id[scope_len] = '\0'; dev = dev_get_by_name(net, scope_id); if (dev) { addr6->sin6_scope_id = dev->ifindex; dev_put(dev); } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) { return -EINVAL; } } addr6->sin6_family = AF_INET6; addr6->sin6_port = htons(port_num); return 0; } /** * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address * @net: net namespace (used for scope handling) * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either * @src: the start of the address string * @port: the start of the port string (or NULL for none) * @addr: output socket address * * Return zero on success, return errno when any error occurs. */ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, const char *src, const char *port, struct sockaddr_storage *addr) { u16 port_num; int ret = -EINVAL; if (port) { if (kstrtou16(port, 0, &port_num)) return -EINVAL; } else { port_num = 0; } switch (af) { case AF_INET: ret = inet4_pton(src, port_num, addr); break; case AF_INET6: ret = inet6_pton(net, src, port_num, addr); break; case AF_UNSPEC: ret = inet4_pton(src, port_num, addr); if (ret) ret = inet6_pton(net, src, port_num, addr); break; default: pr_err("unexpected address family %d\n", af); } return ret; } EXPORT_SYMBOL(inet_pton_with_scope); bool inet_addr_is_any(struct sockaddr *addr) { if (addr->sa_family == AF_INET6) { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; const struct sockaddr_in6 in6_any = { .sin6_addr = IN6ADDR_ANY_INIT }; if (!memcmp(in6->sin6_addr.s6_addr, in6_any.sin6_addr.s6_addr, 16)) return true; } else if (addr->sa_family == AF_INET) { struct sockaddr_in *in = (struct sockaddr_in *)addr; if (in->sin_addr.s_addr == htonl(INADDR_ANY)) return true; } else { pr_warn("unexpected address family %u\n", addr->sa_family); } return false; } EXPORT_SYMBOL(inet_addr_is_any); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(csum_sub(~(skb->csum), (__force __wsum)from), (__force __wsum)to); } else if (pseudohdr) *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), (__force __wsum)from), (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); /** * inet_proto_csum_replace16 - update layer 4 header checksum field * @sum: Layer 4 header checksum field * @skb: sk_buff for the packet * @from: old IPv6 address * @to: new IPv6 address * @pseudohdr: True if layer 4 header checksum includes pseudoheader * * Update layer 4 header as per the update in IPv6 src/dst address. * * There is no need to update skb->csum in this function, because update in two * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as * L4 Header checksum for skb->csum calculation. */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(diff, ~skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); |
| 35 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebtable_filter * * Authors: * Bart De Schuymer <bdschuym@pandora.be> * * April, 2002 * */ #include <linux/netfilter_bridge/ebtables.h> #include <uapi/linux/netfilter_bridge.h> #include <linux/module.h> #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ (1 << NF_BR_LOCAL_OUT)) static struct ebt_entries initial_chains[] = { { .name = "INPUT", .policy = EBT_ACCEPT, }, { .name = "FORWARD", .policy = EBT_ACCEPT, }, { .name = "OUTPUT", .policy = EBT_ACCEPT, }, }; static struct ebt_replace_kernel initial_table = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), .hook_entry = { [NF_BR_LOCAL_IN] = &initial_chains[0], [NF_BR_FORWARD] = &initial_chains[1], [NF_BR_LOCAL_OUT] = &initial_chains[2], }, .entries = (char *)initial_chains, }; static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, }; static unsigned int ebt_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, priv); } static const struct nf_hook_ops ebt_ops_filter[] = { { .hook = ebt_filter_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_filter_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_filter_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_FILTER_OTHER, }, }; static int frame_filter_table_init(struct net *net) { return ebt_register_table(net, &frame_filter, ebt_ops_filter); } static void __net_exit frame_filter_net_pre_exit(struct net *net) { ebt_unregister_table_pre_exit(net, "filter"); } static void __net_exit frame_filter_net_exit(struct net *net) { ebt_unregister_table(net, "filter"); } static struct pernet_operations frame_filter_net_ops = { .exit = frame_filter_net_exit, .pre_exit = frame_filter_net_pre_exit, }; static int __init ebtable_filter_init(void) { int ret = ebt_register_template(&frame_filter, frame_filter_table_init); if (ret) return ret; ret = register_pernet_subsys(&frame_filter_net_ops); if (ret) { ebt_unregister_template(&frame_filter); return ret; } return 0; } static void __exit ebtable_filter_fini(void) { unregister_pernet_subsys(&frame_filter_net_ops); ebt_unregister_template(&frame_filter); } module_init(ebtable_filter_init); module_exit(ebtable_filter_fini); MODULE_LICENSE("GPL"); |
| 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Single-block cipher operations. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/algapi.h> #include <crypto/internal/cipher.h> #include <linux/kernel.h> #include <linux/crypto.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> #include "internal.h" static int setkey_unaligned(struct crypto_cipher *tfm, const u8 *key, unsigned int keylen) { struct cipher_alg *cia = crypto_cipher_alg(tfm); unsigned long alignmask = crypto_cipher_alignmask(tfm); int ret; u8 *buffer, *alignbuffer; unsigned long absize; absize = keylen + alignmask; buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = cia->cia_setkey(crypto_cipher_tfm(tfm), alignbuffer, keylen); kfree_sensitive(buffer); return ret; } int crypto_cipher_setkey(struct crypto_cipher *tfm, const u8 *key, unsigned int keylen) { struct cipher_alg *cia = crypto_cipher_alg(tfm); unsigned long alignmask = crypto_cipher_alignmask(tfm); if (keylen < cia->cia_min_keysize || keylen > cia->cia_max_keysize) return -EINVAL; if ((unsigned long)key & alignmask) return setkey_unaligned(tfm, key, keylen); return cia->cia_setkey(crypto_cipher_tfm(tfm), key, keylen); } EXPORT_SYMBOL_NS_GPL(crypto_cipher_setkey, CRYPTO_INTERNAL); static inline void cipher_crypt_one(struct crypto_cipher *tfm, u8 *dst, const u8 *src, bool enc) { unsigned long alignmask = crypto_cipher_alignmask(tfm); struct cipher_alg *cia = crypto_cipher_alg(tfm); void (*fn)(struct crypto_tfm *, u8 *, const u8 *) = enc ? cia->cia_encrypt : cia->cia_decrypt; if (unlikely(((unsigned long)dst | (unsigned long)src) & alignmask)) { unsigned int bs = crypto_cipher_blocksize(tfm); u8 buffer[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK]; u8 *tmp = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(tmp, src, bs); fn(crypto_cipher_tfm(tfm), tmp, tmp); memcpy(dst, tmp, bs); } else { fn(crypto_cipher_tfm(tfm), dst, src); } } void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, u8 *dst, const u8 *src) { cipher_crypt_one(tfm, dst, src, true); } EXPORT_SYMBOL_NS_GPL(crypto_cipher_encrypt_one, CRYPTO_INTERNAL); void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, u8 *dst, const u8 *src) { cipher_crypt_one(tfm, dst, src, false); } EXPORT_SYMBOL_NS_GPL(crypto_cipher_decrypt_one, CRYPTO_INTERNAL); |
| 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_simple.c Simple example of an action * * Authors: Jamal Hadi Salim (2005-8) */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> static unsigned int simp_net_id; static struct tc_action_ops act_simp_ops; #define SIMP_MAX_DATA 32 static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_defact *d = to_defact(a); spin_lock(&d->tcf_lock); tcf_lastuse_update(&d->tcf_tm); bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) */ pr_info("simple: %s_%llu\n", (char *)d->tcfd_defdata, d->tcf_bstats.packets); spin_unlock(&d->tcf_lock); return d->tcf_action; } static void tcf_simp_release(struct tc_action *a) { struct tcf_defact *d = to_defact(a); kfree(d->tcfd_defdata); } static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata) { d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL); if (unlikely(!d->tcfd_defdata)) return -ENOMEM; nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); return 0; } static int reset_policy(struct tc_action *a, const struct nlattr *defdata, struct tc_defact *p, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcf_chain *goto_ch = NULL; struct tcf_defact *d; int err; err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack); if (err < 0) return err; d = to_defact(a); spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); return 0; } static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { [TCA_DEF_PARMS] = { .len = sizeof(struct tc_defact) }, [TCA_DEF_DATA] = { .type = NLA_STRING, .len = SIMP_MAX_DATA }, }; static int tcf_simp_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) { struct tc_action_net *tn = net_generic(net, simp_net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_DEF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; struct tcf_defact *d; bool exists = false; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_DEF_MAX, nla, simple_policy, NULL); if (err < 0) return err; if (tb[TCA_DEF_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; if (tb[TCA_DEF_DATA] == NULL) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } d = to_defact(*a); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; err = alloc_defdata(d, tb[TCA_DEF_DATA]); if (err < 0) goto put_chain; tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { if (!(flags & TCA_ACT_FLAGS_REPLACE)) { err = -EEXIST; goto release_idr; } err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack); if (err) goto release_idr; } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = to_defact(a); struct tc_defact opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD)) goto nla_put_failure; spin_unlock_bh(&d->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_simp_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, simp_net_id); return tcf_idr_search(tn, a, index); } static struct tc_action_ops act_simp_ops = { .kind = "simple", .id = TCA_ID_SIMP, .owner = THIS_MODULE, .act = tcf_simp_act, .dump = tcf_simp_dump, .cleanup = tcf_simp_release, .init = tcf_simp_init, .walk = tcf_simp_walker, .lookup = tcf_simp_search, .size = sizeof(struct tcf_defact), }; static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, simp_net_id); return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, simp_net_id); } static struct pernet_operations simp_net_ops = { .init = simp_init_net, .exit_batch = simp_exit_net, .id = &simp_net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); MODULE_DESCRIPTION("Simple example action"); MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { int ret = tcf_register_action(&act_simp_ops, &simp_net_ops); if (!ret) pr_info("Simple TC action Loaded\n"); return ret; } static void __exit simp_cleanup_module(void) { tcf_unregister_action(&act_simp_ops, &simp_net_ops); } module_init(simp_init_module); module_exit(simp_cleanup_module); |
| 46 46 46 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" /* Internal logging interface, which relies on the real LOG target modules */ #define NFLOGGER_NAME_LEN 64 int sysctl_nf_log_all_netns __read_mostly; EXPORT_SYMBOL(sysctl_nf_log_all_netns); static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); #define nft_log_dereference(logger) \ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex)) static struct nf_logger *__find_logger(int pf, const char *str_logger) { struct nf_logger *log; int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[pf][i] == NULL) continue; log = nft_log_dereference(loggers[pf][i]); if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } return NULL; } int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); if (log == NULL) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_set); void nf_log_unset(struct net *net, const struct nf_logger *logger) { int i; const struct nf_logger *log; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(net->nf.nf_loggers[i]); if (log == logger) RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL); } mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unset); /* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { int i; int ret = 0; if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { ret = -EEXIST; goto unlock; } } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { ret = -EEXIST; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); } unlock: mutex_unlock(&nf_log_mutex); return ret; } EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(loggers[i][logger->type]); if (log == logger) RCU_INIT_POINTER(loggers[i][logger->type], NULL); } mutex_unlock(&nf_log_mutex); synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(struct net *net, u_int8_t pf) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return; mutex_lock(&nf_log_mutex); RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; int ret = -ENOENT; if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) return ret; ret = nf_logger_find_get(NFPROTO_IPV6, type); if (ret < 0) { nf_logger_put(NFPROTO_IPV4, type); return ret; } return 0; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) goto out; if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_logger_find_get); void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; if (pf == NFPROTO_INET) { nf_logger_put(NFPROTO_IPV4, type); nf_logger_put(NFPROTO_IPV6, type); return; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (!logger) WARN_ON_ONCE(1); else module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); if (loginfo != NULL) logger = rcu_dereference(loggers[pf][loginfo->type]); else logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_packet); void nf_log_trace(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_trace); #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { unsigned int count; char buf[S_SIZE + 1]; }; static struct nf_log_buf emergency, *emergency_ptr = &emergency; __printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) { va_list args; int len; if (likely(m->count < S_SIZE)) { va_start(args, f); len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); va_end(args); if (likely(m->count + len < S_SIZE)) { m->count += len; return 0; } } m->count = S_SIZE; printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); return -1; } EXPORT_SYMBOL_GPL(nf_log_buf_add); struct nf_log_buf *nf_log_buf_open(void) { struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC); if (unlikely(!m)) { local_bh_disable(); do { m = xchg(&emergency_ptr, NULL); } while (!m); } m->count = 0; return m; } EXPORT_SYMBOL_GPL(nf_log_buf_open); void nf_log_buf_close(struct nf_log_buf *m) { m->buf[m->count] = 0; printk("%s\n", m->buf); if (likely(m != &emergency)) kfree(m); else { emergency_ptr = m; local_bh_enable(); } } EXPORT_SYMBOL_GPL(nf_log_buf_close); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { struct net *net = seq_file_net(s); (*pos)++; if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void seq_stop(struct seq_file *s, void *v) { mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; int i; struct net *net = seq_file_net(s); logger = nft_log_dereference(net->nf.nf_loggers[*pos]); if (!logger) seq_printf(s, "%2lld NONE (", *pos); else seq_printf(s, "%2lld %s (", *pos, logger->name); if (seq_has_overflowed(s)) return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) continue; logger = nft_log_dereference(loggers[*pos][i]); seq_puts(s, logger->name); if (i == 0 && loggers[*pos][i + 1] != NULL) seq_puts(s, ","); if (seq_has_overflowed(s)) return -ENOSPC; } seq_puts(s, ")\n"); if (seq_has_overflowed(s)) return -ENOSPC; return 0; } static const struct seq_operations nflog_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { { .procname = "nf_log_all_netns", .data = &sysctl_nf_log_all_netns, .maxlen = sizeof(sysctl_nf_log_all_netns), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static int nf_log_proc_dostring(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; /* proc_dostring() can append to existing strings, so we need to * initialize it as an empty string. */ buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); return 0; } mutex_lock(&nf_log_mutex); logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { struct ctl_table tmp = *table; tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) strlcpy(buf, "NONE", sizeof(buf)); else strlcpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; } static int netfilter_log_sysctl_init(struct net *net) { int i; struct ctl_table *table; table = nf_log_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(nf_log_sysctl_table, sizeof(nf_log_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } else { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i], 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", nf_log_sysctl_ftable); if (!nf_log_sysctl_fhdr) goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) table[i].extra2 = net; net->nf.nf_log_dir_header = register_net_sysctl(net, "net/netfilter/nf_log", table); if (!net->nf.nf_log_dir_header) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); err_freg: err_alloc: return -ENOMEM; } static void netfilter_log_sysctl_exit(struct net *net) { struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) { return 0; } static void netfilter_log_sysctl_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ static int __net_init nf_log_net_init(struct net *net) { int ret = -ENOMEM; #ifdef CONFIG_PROC_FS if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter, &nflog_seq_ops, sizeof(struct seq_net_private))) return ret; #endif ret = netfilter_log_sysctl_init(net); if (ret < 0) goto out_sysctl; return 0; out_sysctl: #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif return ret; } static void __net_exit nf_log_net_exit(struct net *net) { netfilter_log_sysctl_exit(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif } static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, }; int __init netfilter_log_init(void) { return register_pernet_subsys(&nf_log_net_ops); } |
| 161 161 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * cn_proc.c - process events connector * * Copyright (C) Matt Helsley, IBM Corp. 2005 * Based on cn_fork.c by Guillaume Thouvenin <guillaume.thouvenin@bull.net> * Original copyright notice follows: * Copyright (C) 2005 BULL SA. */ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/init.h> #include <linux/connector.h> #include <linux/gfp.h> #include <linux/ptrace.h> #include <linux/atomic.h> #include <linux/pid_namespace.h> #include <linux/cn_proc.h> #include <linux/local_lock.h> /* * Size of a cn_msg followed by a proc_event structure. Since the * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we * add one 4-byte word to the size here, and then start the actual * cn_msg structure 4 bytes into the stack buffer. The result is that * the immediately following proc_event structure is aligned to 8 bytes. */ #define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4) /* See comment above; we test our assumption about sizeof struct cn_msg here. */ static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer) { BUILD_BUG_ON(sizeof(struct cn_msg) != 20); return (struct cn_msg *)(buffer + 4); } static atomic_t proc_event_num_listeners = ATOMIC_INIT(0); static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* local_event.count is used as the sequence number of the netlink message */ struct local_event { local_lock_t lock; __u32 count; }; static DEFINE_PER_CPU(struct local_event, local_event) = { .lock = INIT_LOCAL_LOCK(lock), }; static inline void send_msg(struct cn_msg *msg) { local_lock(&local_event.lock); msg->seq = __this_cpu_inc_return(local_event.count) - 1; ((struct proc_event *)msg->data)->cpu = smp_processor_id(); /* * local_lock() disables preemption during send to ensure the messages * are ordered according to their sequence numbers. * * If cn_netlink_send() fails, the data is not sent. */ cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); local_unlock(&local_event.lock); } void proc_fork_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct task_struct *parent; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); parent = rcu_dereference(task->real_parent); ev->event_data.fork.parent_pid = parent->pid; ev->event_data.fork.parent_tgid = parent->tgid; rcu_read_unlock(); ev->event_data.fork.child_pid = task->pid; ev->event_data.fork.child_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exec_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; ev->event_data.exec.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_id_connector(struct task_struct *task, int which_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; rcu_read_lock(); cred = __task_cred(task); if (which_id == PROC_EVENT_UID) { ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid); ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid); } else if (which_id == PROC_EVENT_GID) { ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid); ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid); } else { rcu_read_unlock(); return; } rcu_read_unlock(); ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_sid_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; ev->event_data.sid.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_ptrace_connector(struct task_struct *task, int ptrace_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; ev->event_data.ptrace.process_tgid = task->tgid; if (ptrace_id == PTRACE_ATTACH) { ev->event_data.ptrace.tracer_pid = current->pid; ev->event_data.ptrace.tracer_tgid = current->tgid; } else if (ptrace_id == PTRACE_DETACH) { ev->event_data.ptrace.tracer_pid = 0; ev->event_data.ptrace.tracer_tgid = 0; } else return; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_comm_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; ev->event_data.comm.process_tgid = task->tgid; get_task_comm(ev->event_data.comm.comm, task); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_coredump_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.coredump.parent_pid = parent->pid; ev->event_data.coredump.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exit_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; ev->event_data.exit.process_tgid = task->tgid; ev->event_data.exit.exit_code = task->exit_code; ev->event_data.exit.exit_signal = task->exit_signal; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.exit.parent_pid = parent->pid; ev->event_data.exit.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /* * Send an acknowledgement message to userspace * * Use 0 for success, EFOO otherwise. * Note: this is the negative of conventional kernel error * values because it's not being returned via syscall return * mechanisms. */ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ev->timestamp_ns = ktime_get_ns(); ev->cpu = -1; ev->what = PROC_EVENT_NONE; ev->event_data.ack.err = err; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /** * cn_proc_mcast_ctl * @data: message sent from userspace via the connector */ static void cn_proc_mcast_ctl(struct cn_msg *msg, struct netlink_skb_parms *nsp) { enum proc_cn_mcast_op *mc_op = NULL; int err = 0; if (msg->len != sizeof(*mc_op)) return; /* * Events are reported with respect to the initial pid * and user namespaces so ignore requestors from * other namespaces. */ if ((current_user_ns() != &init_user_ns) || (task_active_pid_ns(current) != &init_pid_ns)) return; /* Can only change if privileged. */ if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) { err = EPERM; goto out; } mc_op = (enum proc_cn_mcast_op *)msg->data; switch (*mc_op) { case PROC_CN_MCAST_LISTEN: atomic_inc(&proc_event_num_listeners); break; case PROC_CN_MCAST_IGNORE: atomic_dec(&proc_event_num_listeners); break; default: err = EINVAL; break; } out: cn_proc_ack(err, msg->seq, msg->ack); } /* * cn_proc_init - initialization entry point * * Adds the connector callback to the connector driver. */ static int __init cn_proc_init(void) { int err = cn_add_callback(&cn_proc_event_id, "cn_proc", &cn_proc_mcast_ctl); if (err) { pr_warn("cn_proc failed to register\n"); return err; } return 0; } device_initcall(cn_proc_init); |
| 171 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM xdp #if !defined(_TRACE_XDP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_XDP_H #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/tracepoint.h> #include <linux/bpf.h> #define __XDP_ACT_MAP(FN) \ FN(ABORTED) \ FN(DROP) \ FN(PASS) \ FN(TX) \ FN(REDIRECT) #define __XDP_ACT_TP_FN(x) \ TRACE_DEFINE_ENUM(XDP_##x); #define __XDP_ACT_SYM_FN(x) \ { XDP_##x, #x }, #define __XDP_ACT_SYM_TAB \ __XDP_ACT_MAP(__XDP_ACT_SYM_FN) { -1, NULL } __XDP_ACT_MAP(__XDP_ACT_TP_FN) TRACE_EVENT(xdp_exception, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, u32 act), TP_ARGS(dev, xdp, act), TP_STRUCT__entry( __field(int, prog_id) __field(u32, act) __field(int, ifindex) ), TP_fast_assign( __entry->prog_id = xdp->aux->id; __entry->act = act; __entry->ifindex = dev->ifindex; ), TP_printk("prog_id=%d action=%s ifindex=%d", __entry->prog_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->ifindex) ); TRACE_EVENT(xdp_bulk_tx, TP_PROTO(const struct net_device *dev, int sent, int drops, int err), TP_ARGS(dev, sent, drops, err), TP_STRUCT__entry( __field(int, ifindex) __field(u32, act) __field(int, drops) __field(int, sent) __field(int, err) ), TP_fast_assign( __entry->ifindex = dev->ifindex; __entry->act = XDP_TX; __entry->drops = drops; __entry->sent = sent; __entry->err = err; ), TP_printk("ifindex=%d action=%s sent=%d drops=%d err=%d", __entry->ifindex, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->sent, __entry->drops, __entry->err) ); #ifndef __DEVMAP_OBJ_TYPE #define __DEVMAP_OBJ_TYPE struct _bpf_dtab_netdev { struct net_device *dev; }; #endif /* __DEVMAP_OBJ_TYPE */ DECLARE_EVENT_CLASS(xdp_redirect_template, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, enum bpf_map_type map_type, u32 map_id, u32 index), TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index), TP_STRUCT__entry( __field(int, prog_id) __field(u32, act) __field(int, ifindex) __field(int, err) __field(int, to_ifindex) __field(u32, map_id) __field(int, map_index) ), TP_fast_assign( u32 ifindex = 0, map_index = index; if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Just leave to_ifindex to 0 if do broadcast redirect, * as tgt will be NULL. */ if (tgt) ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; } else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { ifindex = index; map_index = 0; } __entry->prog_id = xdp->aux->id; __entry->act = XDP_REDIRECT; __entry->ifindex = dev->ifindex; __entry->err = err; __entry->to_ifindex = ifindex; __entry->map_id = map_id; __entry->map_index = map_index; ), TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d" " map_id=%d map_index=%d", __entry->prog_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->ifindex, __entry->to_ifindex, __entry->err, __entry->map_id, __entry->map_index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, enum bpf_map_type map_type, u32 map_id, u32 index), TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, enum bpf_map_type map_type, u32 map_id, u32 index), TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); #define _trace_xdp_redirect(dev, xdp, to) \ trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to) #define _trace_xdp_redirect_err(dev, xdp, to, err) \ trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to) #define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \ trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index) #define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \ trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index) /* not used anymore, but kept around so as not to break old programs */ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, enum bpf_map_type map_type, u32 map_id, u32 index), TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, enum bpf_map_type map_type, u32 map_id, u32 index), TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); TRACE_EVENT(xdp_cpumap_kthread, TP_PROTO(int map_id, unsigned int processed, unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats), TP_ARGS(map_id, processed, drops, sched, xdp_stats), TP_STRUCT__entry( __field(int, map_id) __field(u32, act) __field(int, cpu) __field(unsigned int, drops) __field(unsigned int, processed) __field(int, sched) __field(unsigned int, xdp_pass) __field(unsigned int, xdp_drop) __field(unsigned int, xdp_redirect) ), TP_fast_assign( __entry->map_id = map_id; __entry->act = XDP_REDIRECT; __entry->cpu = smp_processor_id(); __entry->drops = drops; __entry->processed = processed; __entry->sched = sched; __entry->xdp_pass = xdp_stats->pass; __entry->xdp_drop = xdp_stats->drop; __entry->xdp_redirect = xdp_stats->redirect; ), TP_printk("kthread" " cpu=%d map_id=%d action=%s" " processed=%u drops=%u" " sched=%d" " xdp_pass=%u xdp_drop=%u xdp_redirect=%u", __entry->cpu, __entry->map_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->processed, __entry->drops, __entry->sched, __entry->xdp_pass, __entry->xdp_drop, __entry->xdp_redirect) ); TRACE_EVENT(xdp_cpumap_enqueue, TP_PROTO(int map_id, unsigned int processed, unsigned int drops, int to_cpu), TP_ARGS(map_id, processed, drops, to_cpu), TP_STRUCT__entry( __field(int, map_id) __field(u32, act) __field(int, cpu) __field(unsigned int, drops) __field(unsigned int, processed) __field(int, to_cpu) ), TP_fast_assign( __entry->map_id = map_id; __entry->act = XDP_REDIRECT; __entry->cpu = smp_processor_id(); __entry->drops = drops; __entry->processed = processed; __entry->to_cpu = to_cpu; ), TP_printk("enqueue" " cpu=%d map_id=%d action=%s" " processed=%u drops=%u" " to_cpu=%d", __entry->cpu, __entry->map_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->processed, __entry->drops, __entry->to_cpu) ); TRACE_EVENT(xdp_devmap_xmit, TP_PROTO(const struct net_device *from_dev, const struct net_device *to_dev, int sent, int drops, int err), TP_ARGS(from_dev, to_dev, sent, drops, err), TP_STRUCT__entry( __field(int, from_ifindex) __field(u32, act) __field(int, to_ifindex) __field(int, drops) __field(int, sent) __field(int, err) ), TP_fast_assign( __entry->from_ifindex = from_dev->ifindex; __entry->act = XDP_REDIRECT; __entry->to_ifindex = to_dev->ifindex; __entry->drops = drops; __entry->sent = sent; __entry->err = err; ), TP_printk("ndo_xdp_xmit" " from_ifindex=%d to_ifindex=%d action=%s" " sent=%d drops=%d" " err=%d", __entry->from_ifindex, __entry->to_ifindex, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->sent, __entry->drops, __entry->err) ); /* Expect users already include <net/xdp.h>, but not xdp_priv.h */ #include <net/xdp_priv.h> #define __MEM_TYPE_MAP(FN) \ FN(PAGE_SHARED) \ FN(PAGE_ORDER0) \ FN(PAGE_POOL) \ FN(XSK_BUFF_POOL) #define __MEM_TYPE_TP_FN(x) \ TRACE_DEFINE_ENUM(MEM_TYPE_##x); #define __MEM_TYPE_SYM_FN(x) \ { MEM_TYPE_##x, #x }, #define __MEM_TYPE_SYM_TAB \ __MEM_TYPE_MAP(__MEM_TYPE_SYM_FN) { -1, 0 } __MEM_TYPE_MAP(__MEM_TYPE_TP_FN) TRACE_EVENT(mem_disconnect, TP_PROTO(const struct xdp_mem_allocator *xa), TP_ARGS(xa), TP_STRUCT__entry( __field(const struct xdp_mem_allocator *, xa) __field(u32, mem_id) __field(u32, mem_type) __field(const void *, allocator) ), TP_fast_assign( __entry->xa = xa; __entry->mem_id = xa->mem.id; __entry->mem_type = xa->mem.type; __entry->allocator = xa->allocator; ), TP_printk("mem_id=%d mem_type=%s allocator=%p", __entry->mem_id, __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), __entry->allocator ) ); TRACE_EVENT(mem_connect, TP_PROTO(const struct xdp_mem_allocator *xa, const struct xdp_rxq_info *rxq), TP_ARGS(xa, rxq), TP_STRUCT__entry( __field(const struct xdp_mem_allocator *, xa) __field(u32, mem_id) __field(u32, mem_type) __field(const void *, allocator) __field(const struct xdp_rxq_info *, rxq) __field(int, ifindex) ), TP_fast_assign( __entry->xa = xa; __entry->mem_id = xa->mem.id; __entry->mem_type = xa->mem.type; __entry->allocator = xa->allocator; __entry->rxq = rxq; __entry->ifindex = rxq->dev->ifindex; ), TP_printk("mem_id=%d mem_type=%s allocator=%p" " ifindex=%d", __entry->mem_id, __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), __entry->allocator, __entry->ifindex ) ); TRACE_EVENT(mem_return_failed, TP_PROTO(const struct xdp_mem_info *mem, const struct page *page), TP_ARGS(mem, page), TP_STRUCT__entry( __field(const struct page *, page) __field(u32, mem_id) __field(u32, mem_type) ), TP_fast_assign( __entry->page = page; __entry->mem_id = mem->id; __entry->mem_type = mem->type; ), TP_printk("mem_id=%d mem_type=%s page=%p", __entry->mem_id, __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), __entry->page ) ); #endif /* _TRACE_XDP_H */ #include <trace/define_trace.h> |
| 45 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2003-2005 Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH * Copyright (C) 2018 - 2020 Intel Corporation */ #include <linux/debugfs.h> #include <linux/ieee80211.h> #include "ieee80211_i.h" #include "debugfs.h" #include "debugfs_sta.h" #include "sta_info.h" #include "driver-ops.h" /* sta attributtes */ #define STA_READ(name, field, format_string) \ static ssize_t sta_ ##name## _read(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ struct sta_info *sta = file->private_data; \ return mac80211_format_buffer(userbuf, count, ppos, \ format_string, sta->field); \ } #define STA_READ_D(name, field) STA_READ(name, field, "%d\n") #define STA_OPS(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define STA_OPS_RW(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .write = sta_##name##_write, \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define STA_FILE(name, field, format) \ STA_READ_##format(name, field) \ STA_OPS(name) STA_FILE(aid, sta.aid, D); static const char * const sta_flag_names[] = { #define FLAG(F) [WLAN_STA_##F] = #F FLAG(AUTH), FLAG(ASSOC), FLAG(PS_STA), FLAG(AUTHORIZED), FLAG(SHORT_PREAMBLE), FLAG(WDS), FLAG(CLEAR_PS_FILT), FLAG(MFP), FLAG(BLOCK_BA), FLAG(PS_DRIVER), FLAG(PSPOLL), FLAG(TDLS_PEER), FLAG(TDLS_PEER_AUTH), FLAG(TDLS_INITIATOR), FLAG(TDLS_CHAN_SWITCH), FLAG(TDLS_OFF_CHANNEL), FLAG(TDLS_WIDER_BW), FLAG(UAPSD), FLAG(SP), FLAG(4ADDR_EVENT), FLAG(INSERTED), FLAG(RATE_CONTROL), FLAG(TOFFSET_KNOWN), FLAG(MPSP_OWNER), FLAG(MPSP_RECIPIENT), FLAG(PS_DELIVER), FLAG(USES_ENCRYPTION), FLAG(DECAP_OFFLOAD), #undef FLAG }; static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[16 * NUM_WLAN_STA_FLAGS], *pos = buf; char *end = buf + sizeof(buf) - 1; struct sta_info *sta = file->private_data; unsigned int flg; BUILD_BUG_ON(ARRAY_SIZE(sta_flag_names) != NUM_WLAN_STA_FLAGS); for (flg = 0; flg < NUM_WLAN_STA_FLAGS; flg++) { if (test_sta_flag(sta, flg)) pos += scnprintf(pos, end - pos, "%s\n", sta_flag_names[flg]); } return simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf)); } STA_OPS(flags); static ssize_t sta_num_ps_buf_frames_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; char buf[17*IEEE80211_NUM_ACS], *p = buf; int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) p += scnprintf(p, sizeof(buf)+buf-p, "AC%d: %d\n", ac, skb_queue_len(&sta->ps_tx_buf[ac]) + skb_queue_len(&sta->tx_filtered[ac])); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(num_ps_buf_frames); static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[15*IEEE80211_NUM_TIDS], *p = buf; int i; struct sta_info *sta = file->private_data; for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%x ", le16_to_cpu(sta->last_seq_ctrl[i])); p += scnprintf(p, sizeof(buf)+buf-p, "\n"); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(last_seq_ctrl); #define AQM_TXQ_ENTRY_LEN 130 static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->local; size_t bufsz = AQM_TXQ_ENTRY_LEN * (IEEE80211_NUM_TIDS + 2); char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; struct txq_info *txqi; ssize_t rv; int i; if (!buf) return -ENOMEM; spin_lock_bh(&local->fq.lock); rcu_read_lock(); p += scnprintf(p, bufsz+buf-p, "target %uus interval %uus ecn %s\n", codel_time_to_us(sta->cparams.target), codel_time_to_us(sta->cparams.interval), sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, bufsz+buf-p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { if (!sta->sta.txq[i]) continue; txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz+buf-p, "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, txqi->tin.backlog_bytes, txqi->tin.backlog_packets, txqi->tin.flows, txqi->cstats.drop_count, txqi->cstats.ecn_mark, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, txqi->tin.tx_packets, txqi->flags, test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN", test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : ""); } rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } STA_OPS(aqm); static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; u64 v_t[IEEE80211_NUM_ACS]; ssize_t rv; int ac; if (!buf) return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->airtime[ac].lock); rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; v_t[ac] = sta->airtime[ac].v_t; spin_unlock_bh(&local->airtime[ac].lock); } p += scnprintf(p, bufsz + buf - p, "RX: %llu us\nTX: %llu us\nWeight: %u\n" "Virt-T: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", rx_airtime, tx_airtime, sta->airtime[0].weight, v_t[0], v_t[1], v_t[2], v_t[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->airtime[ac].lock); sta->airtime[ac].rx_airtime = 0; sta->airtime[ac].tx_airtime = 0; sta->airtime[ac].v_t = 0; spin_unlock_bh(&local->airtime[ac].lock); } return count; } STA_OPS_RW(airtime); static ssize_t sta_aql_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u32 q_depth[IEEE80211_NUM_ACS]; u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; if (!buf) return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->airtime[ac].lock); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->airtime[ac].lock); q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending); } p += scnprintf(p, bufsz + buf - p, "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; if (count > sizeof(_buf)) return -EINVAL; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; if (ac >= IEEE80211_NUM_ACS) return -EINVAL; sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; return count; } STA_OPS_RW(aql); static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[71 + IEEE80211_NUM_TIDS * 40], *p = buf; int i; struct sta_info *sta = file->private_data; struct tid_ampdu_rx *tid_rx; struct tid_ampdu_tx *tid_tx; rcu_read_lock(); p += scnprintf(p, sizeof(buf) + buf - p, "next dialog_token: %#02x\n", sta->ampdu_mlme.dialog_token_allocator + 1); p += scnprintf(p, sizeof(buf) + buf - p, "TID\t\tRX\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { bool tid_rx_valid; tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]); tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]); tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid); p += scnprintf(p, sizeof(buf) + buf - p, "%02d", i); p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x", tid_rx_valid); p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.2x", tid_rx_valid ? sta->ampdu_mlme.tid_rx_token[i] : 0); p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.3x", tid_rx ? tid_rx->ssn : 0); p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x", !!tid_tx); p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.2x", tid_tx ? tid_tx->dialog_token : 0); p += scnprintf(p, sizeof(buf) + buf - p, "\t%03d", tid_tx ? skb_queue_len(&tid_tx->pending) : 0); p += scnprintf(p, sizeof(buf) + buf - p, "\n"); } rcu_read_unlock(); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { char _buf[25] = {}, *buf = _buf; struct sta_info *sta = file->private_data; bool start, tx; unsigned long tid; char *pos; int ret, timeout = 5000; if (count > sizeof(_buf)) return -EINVAL; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; pos = buf; buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (!strcmp(buf, "tx")) tx = true; else if (!strcmp(buf, "rx")) tx = false; else return -EINVAL; buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (!strcmp(buf, "start")) { start = true; if (!tx) return -EINVAL; } else if (!strcmp(buf, "stop")) { start = false; } else { return -EINVAL; } buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (sscanf(buf, "timeout=%d", &timeout) == 1) { buf = strsep(&pos, " "); if (!buf || !tx || !start) return -EINVAL; } ret = kstrtoul(buf, 0, &tid); if (ret || tid >= IEEE80211_NUM_TIDS) return -EINVAL; if (tx) { if (start) ret = ieee80211_start_tx_ba_session(&sta->sta, tid, timeout); else ret = ieee80211_stop_tx_ba_session(&sta->sta, tid); } else { __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, 3, true); ret = 0; } return ret ?: count; } STA_OPS_RW(agg_status); static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { #define PRINT_HT_CAP(_cond, _str) \ do { \ if (_cond) \ p += scnprintf(p, sizeof(buf)+buf-p, "\t" _str "\n"); \ } while (0) char buf[512], *p = buf; int i; struct sta_info *sta = file->private_data; struct ieee80211_sta_ht_cap *htc = &sta->sta.ht_cap; p += scnprintf(p, sizeof(buf) + buf - p, "ht %ssupported\n", htc->ht_supported ? "" : "not "); if (htc->ht_supported) { p += scnprintf(p, sizeof(buf)+buf-p, "cap: %#.4x\n", htc->cap); PRINT_HT_CAP((htc->cap & BIT(0)), "RX LDPC"); PRINT_HT_CAP((htc->cap & BIT(1)), "HT20/HT40"); PRINT_HT_CAP(!(htc->cap & BIT(1)), "HT20"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 0, "Static SM Power Save"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 1, "Dynamic SM Power Save"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 3, "SM Power Save disabled"); PRINT_HT_CAP((htc->cap & BIT(4)), "RX Greenfield"); PRINT_HT_CAP((htc->cap & BIT(5)), "RX HT20 SGI"); PRINT_HT_CAP((htc->cap & BIT(6)), "RX HT40 SGI"); PRINT_HT_CAP((htc->cap & BIT(7)), "TX STBC"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 0, "No RX STBC"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 1, "RX STBC 1-stream"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 2, "RX STBC 2-streams"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 3, "RX STBC 3-streams"); PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " "3839 bytes"); PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* * For beacons and probe response this would mean the BSS * does or does not allow the usage of DSSS/CCK HT40. * Otherwise it means the STA does or does not use * DSSS/CCK HT40. */ PRINT_HT_CAP((htc->cap & BIT(12)), "DSSS/CCK HT40"); PRINT_HT_CAP(!(htc->cap & BIT(12)), "No DSSS/CCK HT40"); /* BIT(13) is reserved */ PRINT_HT_CAP((htc->cap & BIT(14)), "40 MHz Intolerant"); PRINT_HT_CAP((htc->cap & BIT(15)), "L-SIG TXOP protection"); p += scnprintf(p, sizeof(buf)+buf-p, "ampdu factor/density: %d/%d\n", htc->ampdu_factor, htc->ampdu_density); p += scnprintf(p, sizeof(buf)+buf-p, "MCS mask:"); for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) p += scnprintf(p, sizeof(buf)+buf-p, " %.2x", htc->mcs.rx_mask[i]); p += scnprintf(p, sizeof(buf)+buf-p, "\n"); /* If not set this is meaningless */ if (le16_to_cpu(htc->mcs.rx_highest)) { p += scnprintf(p, sizeof(buf)+buf-p, "MCS rx highest: %d Mbps\n", le16_to_cpu(htc->mcs.rx_highest)); } p += scnprintf(p, sizeof(buf)+buf-p, "MCS tx params: %x\n", htc->mcs.tx_params); } return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(ht_capa); static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[512], *p = buf; struct sta_info *sta = file->private_data; struct ieee80211_sta_vht_cap *vhtc = &sta->sta.vht_cap; p += scnprintf(p, sizeof(buf) + buf - p, "VHT %ssupported\n", vhtc->vht_supported ? "" : "not "); if (vhtc->vht_supported) { p += scnprintf(p, sizeof(buf) + buf - p, "cap: %#.8x\n", vhtc->cap); #define PFLAG(a, b) \ do { \ if (vhtc->cap & IEEE80211_VHT_CAP_ ## a) \ p += scnprintf(p, sizeof(buf) + buf - p, \ "\t\t%s\n", b); \ } while (0) switch (vhtc->cap & 0x3) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: p += scnprintf(p, sizeof(buf) + buf - p, "\t\tMAX-MPDU-3895\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: p += scnprintf(p, sizeof(buf) + buf - p, "\t\tMAX-MPDU-7991\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: p += scnprintf(p, sizeof(buf) + buf - p, "\t\tMAX-MPDU-11454\n"); break; default: p += scnprintf(p, sizeof(buf) + buf - p, "\t\tMAX-MPDU-UNKNOWN\n"); } switch (vhtc->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case 0: p += scnprintf(p, sizeof(buf) + buf - p, "\t\t80Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: p += scnprintf(p, sizeof(buf) + buf - p, "\t\t160Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ: p += scnprintf(p, sizeof(buf) + buf - p, "\t\t80+80Mhz\n"); break; default: p += scnprintf(p, sizeof(buf) + buf - p, "\t\tUNKNOWN-MHZ: 0x%x\n", (vhtc->cap >> 2) & 0x3); } PFLAG(RXLDPC, "RXLDPC"); PFLAG(SHORT_GI_80, "SHORT-GI-80"); PFLAG(SHORT_GI_160, "SHORT-GI-160"); PFLAG(TXSTBC, "TXSTBC"); p += scnprintf(p, sizeof(buf) + buf - p, "\t\tRXSTBC_%d\n", (vhtc->cap >> 8) & 0x7); PFLAG(SU_BEAMFORMER_CAPABLE, "SU-BEAMFORMER-CAPABLE"); PFLAG(SU_BEAMFORMEE_CAPABLE, "SU-BEAMFORMEE-CAPABLE"); p += scnprintf(p, sizeof(buf) + buf - p, "\t\tBEAMFORMEE-STS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK) >> IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT); p += scnprintf(p, sizeof(buf) + buf - p, "\t\tSOUNDING-DIMENSIONS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK) >> IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT); PFLAG(MU_BEAMFORMER_CAPABLE, "MU-BEAMFORMER-CAPABLE"); PFLAG(MU_BEAMFORMEE_CAPABLE, "MU-BEAMFORMEE-CAPABLE"); PFLAG(VHT_TXOP_PS, "TXOP-PS"); PFLAG(HTC_VHT, "HTC-VHT"); p += scnprintf(p, sizeof(buf) + buf - p, "\t\tMPDU-LENGTH-EXPONENT: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK) >> IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT); PFLAG(VHT_LINK_ADAPTATION_VHT_UNSOL_MFB, "LINK-ADAPTATION-VHT-UNSOL-MFB"); p += scnprintf(p, sizeof(buf) + buf - p, "\t\tLINK-ADAPTATION-VHT-MRQ-MFB: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB) >> 26); PFLAG(RX_ANTENNA_PATTERN, "RX-ANTENNA-PATTERN"); PFLAG(TX_ANTENNA_PATTERN, "TX-ANTENNA-PATTERN"); p += scnprintf(p, sizeof(buf)+buf-p, "RX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.rx_mcs_map)); if (vhtc->vht_mcs.rx_highest) p += scnprintf(p, sizeof(buf)+buf-p, "MCS RX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.rx_highest)); p += scnprintf(p, sizeof(buf)+buf-p, "TX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.tx_mcs_map)); if (vhtc->vht_mcs.tx_highest) p += scnprintf(p, sizeof(buf)+buf-p, "MCS TX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.tx_highest)); #undef PFLAG } return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(vht_capa); static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char *buf, *p; size_t buf_sz = PAGE_SIZE; struct sta_info *sta = file->private_data; struct ieee80211_sta_he_cap *hec = &sta->sta.he_cap; struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; u8 ppe_size; u8 *cap; int i; ssize_t ret; buf = kmalloc(buf_sz, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, buf_sz + buf - p, "HE %ssupported\n", hec->has_he ? "" : "not "); if (!hec->has_he) goto out; cap = hec->he_cap_elem.mac_cap_info; p += scnprintf(p, buf_sz + buf - p, "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", cap[0], cap[1], cap[2], cap[3], cap[4], cap[5]); #define PRINT(fmt, ...) \ p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ ##__VA_ARGS__) #define PFLAG(t, n, a, b) \ do { \ if (cap[n] & IEEE80211_HE_##t##_CAP##n##_##a) \ PRINT("%s", b); \ } while (0) #define PFLAG_RANGE(t, i, n, s, m, off, fmt) \ do { \ u8 msk = IEEE80211_HE_##t##_CAP##i##_##n##_MASK; \ u8 idx = ((cap[i] & msk) >> (ffs(msk) - 1)) + off; \ PRINT(fmt, (s << idx) + (m * idx)); \ } while (0) #define PFLAG_RANGE_DEFAULT(t, i, n, s, m, off, fmt, a, b) \ do { \ if (cap[i] == IEEE80211_HE_##t ##_CAP##i##_##n##_##a) { \ PRINT("%s", b); \ break; \ } \ PFLAG_RANGE(t, i, n, s, m, off, fmt); \ } while (0) PFLAG(MAC, 0, HTC_HE, "HTC-HE"); PFLAG(MAC, 0, TWT_REQ, "TWT-REQ"); PFLAG(MAC, 0, TWT_RES, "TWT-RES"); PFLAG_RANGE_DEFAULT(MAC, 0, DYNAMIC_FRAG, 0, 1, 0, "DYNAMIC-FRAG-LEVEL-%d", NOT_SUPP, "NOT-SUPP"); PFLAG_RANGE_DEFAULT(MAC, 0, MAX_NUM_FRAG_MSDU, 1, 0, 0, "MAX-NUM-FRAG-MSDU-%d", UNLIMITED, "UNLIMITED"); PFLAG_RANGE_DEFAULT(MAC, 1, MIN_FRAG_SIZE, 128, 0, -1, "MIN-FRAG-SIZE-%d", UNLIMITED, "UNLIMITED"); PFLAG_RANGE_DEFAULT(MAC, 1, TF_MAC_PAD_DUR, 0, 8, 0, "TF-MAC-PAD-DUR-%dUS", MASK, "UNKNOWN"); PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_RX_QOS, 0, 1, 1, "MULTI-TID-AGG-RX-QOS-%d"); if (cap[0] & IEEE80211_HE_MAC_CAP0_HTC_HE) { switch (((cap[2] << 1) | (cap[1] >> 7)) & 0x3) { case 0: PRINT("LINK-ADAPTATION-NO-FEEDBACK"); break; case 1: PRINT("LINK-ADAPTATION-RESERVED"); break; case 2: PRINT("LINK-ADAPTATION-UNSOLICITED-FEEDBACK"); break; case 3: PRINT("LINK-ADAPTATION-BOTH"); break; } } PFLAG(MAC, 2, ALL_ACK, "ALL-ACK"); PFLAG(MAC, 2, TRS, "TRS"); PFLAG(MAC, 2, BSR, "BSR"); PFLAG(MAC, 2, BCAST_TWT, "BCAST-TWT"); PFLAG(MAC, 2, 32BIT_BA_BITMAP, "32BIT-BA-BITMAP"); PFLAG(MAC, 2, MU_CASCADING, "MU-CASCADING"); PFLAG(MAC, 2, ACK_EN, "ACK-EN"); PFLAG(MAC, 3, OMI_CONTROL, "OMI-CONTROL"); PFLAG(MAC, 3, OFDMA_RA, "OFDMA-RA"); switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) { case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0: PRINT("MAX-AMPDU-LEN-EXP-USE-EXT-0"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-1"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-2"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-3"); break; } PFLAG(MAC, 3, AMSDU_FRAG, "AMSDU-FRAG"); PFLAG(MAC, 3, FLEX_TWT_SCHED, "FLEX-TWT-SCHED"); PFLAG(MAC, 3, RX_CTRL_FRAME_TO_MULTIBSS, "RX-CTRL-FRAME-TO-MULTIBSS"); PFLAG(MAC, 4, BSRP_BQRP_A_MPDU_AGG, "BSRP-BQRP-A-MPDU-AGG"); PFLAG(MAC, 4, QTP, "QTP"); PFLAG(MAC, 4, BQR, "BQR"); PFLAG(MAC, 4, PSR_RESP, "PSR-RESP"); PFLAG(MAC, 4, NDP_FB_REP, "NDP-FB-REP"); PFLAG(MAC, 4, OPS, "OPS"); PFLAG(MAC, 4, AMSDU_IN_AMPDU, "AMSDU-IN-AMPDU"); PRINT("MULTI-TID-AGG-TX-QOS-%d", ((cap[5] << 1) | (cap[4] >> 7)) & 0x7); PFLAG(MAC, 5, SUBCHAN_SELECTIVE_TRANSMISSION, "SUBCHAN-SELECTIVE-TRANSMISSION"); PFLAG(MAC, 5, UL_2x996_TONE_RU, "UL-2x996-TONE-RU"); PFLAG(MAC, 5, OM_CTRL_UL_MU_DATA_DIS_RX, "OM-CTRL-UL-MU-DATA-DIS-RX"); PFLAG(MAC, 5, HE_DYNAMIC_SM_PS, "HE-DYNAMIC-SM-PS"); PFLAG(MAC, 5, PUNCTURED_SOUNDING, "PUNCTURED-SOUNDING"); PFLAG(MAC, 5, HT_VHT_TRIG_FRAME_RX, "HT-VHT-TRIG-FRAME-RX"); cap = hec->he_cap_elem.phy_cap_info; p += scnprintf(p, buf_sz + buf - p, "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", cap[0], cap[1], cap[2], cap[3], cap[4], cap[5], cap[6], cap[7], cap[8], cap[9], cap[10]); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_IN_2G, "CHANNEL-WIDTH-SET-40MHZ-IN-2G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G, "CHANNEL-WIDTH-SET-40MHZ-80MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_160MHZ_IN_5G, "CHANNEL-WIDTH-SET-160MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, "CHANNEL-WIDTH-SET-80PLUS80-MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G, "CHANNEL-WIDTH-SET-RU-MAPPING-IN-2G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G, "CHANNEL-WIDTH-SET-RU-MAPPING-IN-5G"); switch (cap[1] & IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK) { case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ: PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-20MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ: PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-40MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ: PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-20MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ: PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-40MHZ"); break; } PFLAG(PHY, 1, DEVICE_CLASS_A, "IEEE80211-HE-PHY-CAP1-DEVICE-CLASS-A"); PFLAG(PHY, 1, LDPC_CODING_IN_PAYLOAD, "LDPC-CODING-IN-PAYLOAD"); PFLAG(PHY, 1, HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US, "HY-CAP1-HE-LTF-AND-GI-FOR-HE-PPDUS-0-8US"); PRINT("MIDAMBLE-RX-MAX-NSTS-%d", ((cap[2] << 1) | (cap[1] >> 7)) & 0x3); PFLAG(PHY, 2, NDP_4x_LTF_AND_3_2US, "NDP-4X-LTF-AND-3-2US"); PFLAG(PHY, 2, STBC_TX_UNDER_80MHZ, "STBC-TX-UNDER-80MHZ"); PFLAG(PHY, 2, STBC_RX_UNDER_80MHZ, "STBC-RX-UNDER-80MHZ"); PFLAG(PHY, 2, DOPPLER_TX, "DOPPLER-TX"); PFLAG(PHY, 2, DOPPLER_RX, "DOPPLER-RX"); PFLAG(PHY, 2, UL_MU_FULL_MU_MIMO, "UL-MU-FULL-MU-MIMO"); PFLAG(PHY, 2, UL_MU_PARTIAL_MU_MIMO, "UL-MU-PARTIAL-MU-MIMO"); switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK) { case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM: PRINT("DCM-MAX-CONST-TX-NO-DCM"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK: PRINT("DCM-MAX-CONST-TX-BPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK: PRINT("DCM-MAX-CONST-TX-QPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM: PRINT("DCM-MAX-CONST-TX-16-QAM"); break; } PFLAG(PHY, 3, DCM_MAX_TX_NSS_1, "DCM-MAX-TX-NSS-1"); PFLAG(PHY, 3, DCM_MAX_TX_NSS_2, "DCM-MAX-TX-NSS-2"); switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK) { case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM: PRINT("DCM-MAX-CONST-RX-NO-DCM"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK: PRINT("DCM-MAX-CONST-RX-BPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK: PRINT("DCM-MAX-CONST-RX-QPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM: PRINT("DCM-MAX-CONST-RX-16-QAM"); break; } PFLAG(PHY, 3, DCM_MAX_RX_NSS_1, "DCM-MAX-RX-NSS-1"); PFLAG(PHY, 3, DCM_MAX_RX_NSS_2, "DCM-MAX-RX-NSS-2"); PFLAG(PHY, 3, RX_PARTIAL_BW_SU_IN_20MHZ_MU, "RX-PARTIAL-BW-SU-IN-20MHZ-MU"); PFLAG(PHY, 3, SU_BEAMFORMER, "SU-BEAMFORMER"); PFLAG(PHY, 4, SU_BEAMFORMEE, "SU-BEAMFORMEE"); PFLAG(PHY, 4, MU_BEAMFORMER, "MU-BEAMFORMER"); PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_UNDER_80MHZ, 0, 1, 4, "BEAMFORMEE-MAX-STS-UNDER-%d"); PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_ABOVE_80MHZ, 0, 1, 4, "BEAMFORMEE-MAX-STS-ABOVE-%d"); PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ, 0, 1, 1, "NUM-SND-DIM-UNDER-80MHZ-%d"); PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ, 0, 1, 1, "NUM-SND-DIM-ABOVE-80MHZ-%d"); PFLAG(PHY, 5, NG16_SU_FEEDBACK, "NG16-SU-FEEDBACK"); PFLAG(PHY, 5, NG16_MU_FEEDBACK, "NG16-MU-FEEDBACK"); PFLAG(PHY, 6, CODEBOOK_SIZE_42_SU, "CODEBOOK-SIZE-42-SU"); PFLAG(PHY, 6, CODEBOOK_SIZE_75_MU, "CODEBOOK-SIZE-75-MU"); PFLAG(PHY, 6, TRIG_SU_BEAMFORMING_FB, "TRIG-SU-BEAMFORMING-FB"); PFLAG(PHY, 6, TRIG_MU_BEAMFORMING_PARTIAL_BW_FB, "MU-BEAMFORMING-PARTIAL-BW-FB"); PFLAG(PHY, 6, TRIG_CQI_FB, "TRIG-CQI-FB"); PFLAG(PHY, 6, PARTIAL_BW_EXT_RANGE, "PARTIAL-BW-EXT-RANGE"); PFLAG(PHY, 6, PARTIAL_BANDWIDTH_DL_MUMIMO, "PARTIAL-BANDWIDTH-DL-MUMIMO"); PFLAG(PHY, 6, PPE_THRESHOLD_PRESENT, "PPE-THRESHOLD-PRESENT"); PFLAG(PHY, 7, PSR_BASED_SR, "PSR-BASED-SR"); PFLAG(PHY, 7, POWER_BOOST_FACTOR_SUPP, "POWER-BOOST-FACTOR-SUPP"); PFLAG(PHY, 7, HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, "HE-SU-MU-PPDU-4XLTF-AND-08-US-GI"); PFLAG_RANGE(PHY, 7, MAX_NC, 0, 1, 1, "MAX-NC-%d"); PFLAG(PHY, 7, STBC_TX_ABOVE_80MHZ, "STBC-TX-ABOVE-80MHZ"); PFLAG(PHY, 7, STBC_RX_ABOVE_80MHZ, "STBC-RX-ABOVE-80MHZ"); PFLAG(PHY, 8, HE_ER_SU_PPDU_4XLTF_AND_08_US_GI, "HE-ER-SU-PPDU-4XLTF-AND-08-US-GI"); PFLAG(PHY, 8, 20MHZ_IN_40MHZ_HE_PPDU_IN_2G, "20MHZ-IN-40MHZ-HE-PPDU-IN-2G"); PFLAG(PHY, 8, 20MHZ_IN_160MHZ_HE_PPDU, "20MHZ-IN-160MHZ-HE-PPDU"); PFLAG(PHY, 8, 80MHZ_IN_160MHZ_HE_PPDU, "80MHZ-IN-160MHZ-HE-PPDU"); PFLAG(PHY, 8, HE_ER_SU_1XLTF_AND_08_US_GI, "HE-ER-SU-1XLTF-AND-08-US-GI"); PFLAG(PHY, 8, MIDAMBLE_RX_TX_2X_AND_1XLTF, "MIDAMBLE-RX-TX-2X-AND-1XLTF"); switch (cap[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK) { case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242: PRINT("DCM-MAX-RU-242"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484: PRINT("DCM-MAX-RU-484"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996: PRINT("DCM-MAX-RU-996"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996: PRINT("DCM-MAX-RU-2x996"); break; } PFLAG(PHY, 9, LONGER_THAN_16_SIGB_OFDM_SYM, "LONGER-THAN-16-SIGB-OFDM-SYM"); PFLAG(PHY, 9, NON_TRIGGERED_CQI_FEEDBACK, "NON-TRIGGERED-CQI-FEEDBACK"); PFLAG(PHY, 9, TX_1024_QAM_LESS_THAN_242_TONE_RU, "TX-1024-QAM-LESS-THAN-242-TONE-RU"); PFLAG(PHY, 9, RX_1024_QAM_LESS_THAN_242_TONE_RU, "RX-1024-QAM-LESS-THAN-242-TONE-RU"); PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB, "RX-FULL-BW-SU-USING-MU-WITH-COMP-SIGB"); PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); switch (cap[9] & IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) { case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US: PRINT("NOMINAL-PACKET-PADDING-0US"); break; case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US: PRINT("NOMINAL-PACKET-PADDING-8US"); break; case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US: PRINT("NOMINAL-PACKET-PADDING-16US"); break; } #undef PFLAG_RANGE_DEFAULT #undef PFLAG_RANGE #undef PFLAG #define PRINT_NSS_SUPP(f, n) \ do { \ int _i; \ u16 v = le16_to_cpu(nss->f); \ p += scnprintf(p, buf_sz + buf - p, n ": %#.4x\n", v); \ for (_i = 0; _i < 8; _i += 2) { \ switch ((v >> _i) & 0x3) { \ case 0: \ PRINT(n "-%d-SUPPORT-0-7", _i / 2); \ break; \ case 1: \ PRINT(n "-%d-SUPPORT-0-9", _i / 2); \ break; \ case 2: \ PRINT(n "-%d-SUPPORT-0-11", _i / 2); \ break; \ case 3: \ PRINT(n "-%d-NOT-SUPPORTED", _i / 2); \ break; \ } \ } \ } while (0) PRINT_NSS_SUPP(rx_mcs_80, "RX-MCS-80"); PRINT_NSS_SUPP(tx_mcs_80, "TX-MCS-80"); if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) { PRINT_NSS_SUPP(rx_mcs_160, "RX-MCS-160"); PRINT_NSS_SUPP(tx_mcs_160, "TX-MCS-160"); } if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) { PRINT_NSS_SUPP(rx_mcs_80p80, "RX-MCS-80P80"); PRINT_NSS_SUPP(tx_mcs_80p80, "TX-MCS-80P80"); } #undef PRINT_NSS_SUPP #undef PRINT if (!(cap[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)) goto out; p += scnprintf(p, buf_sz + buf - p, "PPE-THRESHOLDS: %#.2x", hec->ppe_thres[0]); ppe_size = ieee80211_he_ppe_size(hec->ppe_thres[0], cap); for (i = 1; i < ppe_size; i++) { p += scnprintf(p, buf_sz + buf - p, " %#.2x", hec->ppe_thres[i]); } p += scnprintf(p, buf_sz + buf - p, "\n"); out: ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return ret; } STA_OPS(he_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ sta->debugfs_dir, sta, &sta_ ##name## _ops) #define DEBUGFS_ADD_COUNTER(name, field) \ debugfs_create_ulong(#name, 0400, sta->debugfs_dir, &sta->field); void ieee80211_sta_debugfs_add(struct sta_info *sta) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations; u8 mac[3*ETH_ALEN]; if (!stations_dir) return; snprintf(mac, sizeof(mac), "%pM", sta->sta.addr); /* * This might fail due to a race condition: * When mac80211 unlinks a station, the debugfs entries * remain, but it is already possible to link a new * station with the same address which triggers adding * it to debugfs; therefore, if the old station isn't * destroyed quickly enough the old station's debugfs * dir might still be around. */ sta->debugfs_dir = debugfs_create_dir(mac, stations_dir); DEBUGFS_ADD(flags); DEBUGFS_ADD(aid); DEBUGFS_ADD(num_ps_buf_frames); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); DEBUGFS_ADD(ht_capa); DEBUGFS_ADD(vht_capa); DEBUGFS_ADD(he_capa); DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); DEBUGFS_ADD_COUNTER(tx_filtered, status_stats.filtered); if (local->ops->wake_tx_queue) { DEBUGFS_ADD(aqm); DEBUGFS_ADD(airtime); } if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) DEBUGFS_ADD(aql); debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs_dir); } void ieee80211_sta_debugfs_remove(struct sta_info *sta) { debugfs_remove_recursive(sta->debugfs_dir); sta->debugfs_dir = NULL; } |
| 719 721 688 696 27 694 696 689 688 725 1 30 5 341 1 356 425 271 696 27 1 10 27 26 27 31 1 3 27 4673 4673 4673 4051 31 726 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/network.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /* Structure for holding inet domain socket's address. */ struct tomoyo_inet_addr_info { __be16 port; /* In network byte order. */ const __be32 *address; /* In network byte order. */ bool is_ipv6; }; /* Structure for holding unix domain socket's address. */ struct tomoyo_unix_addr_info { u8 *addr; /* This may not be '\0' terminated string. */ unsigned int addr_len; }; /* Structure for holding socket address. */ struct tomoyo_addr_info { u8 protocol; u8 operation; struct tomoyo_inet_addr_info inet; struct tomoyo_unix_addr_info unix0; }; /* String table for socket's protocols. */ const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX] = { [SOCK_STREAM] = "stream", [SOCK_DGRAM] = "dgram", [SOCK_RAW] = "raw", [SOCK_SEQPACKET] = "seqpacket", [0] = " ", /* Dummy for avoiding NULL pointer dereference. */ [4] = " ", /* Dummy for avoiding NULL pointer dereference. */ }; /** * tomoyo_parse_ipaddr_union - Parse an IP address. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_ipaddr_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr) { u8 * const min = ptr->ip[0].in6_u.u6_addr8; u8 * const max = ptr->ip[1].in6_u.u6_addr8; char *address = tomoyo_read_token(param); const char *end; if (!strchr(address, ':') && in4_pton(address, -1, min, '-', &end) > 0) { ptr->is_ipv6 = false; if (!*end) ptr->ip[1].s6_addr32[0] = ptr->ip[0].s6_addr32[0]; else if (*end++ != '-' || in4_pton(end, -1, max, '\0', &end) <= 0 || *end) return false; return true; } if (in6_pton(address, -1, min, '-', &end) > 0) { ptr->is_ipv6 = true; if (!*end) memmove(max, min, sizeof(u16) * 8); else if (*end++ != '-' || in6_pton(end, -1, max, '\0', &end) <= 0 || *end) return false; return true; } return false; } /** * tomoyo_print_ipv4 - Print an IPv4 address. * * @buffer: Buffer to write to. * @buffer_len: Size of @buffer. * @min_ip: Pointer to __be32. * @max_ip: Pointer to __be32. * * Returns nothing. */ static void tomoyo_print_ipv4(char *buffer, const unsigned int buffer_len, const __be32 *min_ip, const __be32 *max_ip) { snprintf(buffer, buffer_len, "%pI4%c%pI4", min_ip, *min_ip == *max_ip ? '\0' : '-', max_ip); } /** * tomoyo_print_ipv6 - Print an IPv6 address. * * @buffer: Buffer to write to. * @buffer_len: Size of @buffer. * @min_ip: Pointer to "struct in6_addr". * @max_ip: Pointer to "struct in6_addr". * * Returns nothing. */ static void tomoyo_print_ipv6(char *buffer, const unsigned int buffer_len, const struct in6_addr *min_ip, const struct in6_addr *max_ip) { snprintf(buffer, buffer_len, "%pI6c%c%pI6c", min_ip, !memcmp(min_ip, max_ip, 16) ? '\0' : '-', max_ip); } /** * tomoyo_print_ip - Print an IP address. * * @buf: Buffer to write to. * @size: Size of @buf. * @ptr: Pointer to "struct ipaddr_union". * * Returns nothing. */ void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr) { if (ptr->is_ipv6) tomoyo_print_ipv6(buf, size, &ptr->ip[0], &ptr->ip[1]); else tomoyo_print_ipv4(buf, size, &ptr->ip[0].s6_addr32[0], &ptr->ip[1].s6_addr32[0]); } /* * Mapping table from "enum tomoyo_network_acl_index" to * "enum tomoyo_mac_index" for inet domain socket. */ static const u8 tomoyo_inet2mac [TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = { [SOCK_STREAM] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_STREAM_BIND, [TOMOYO_NETWORK_LISTEN] = TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, [TOMOYO_NETWORK_CONNECT] = TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, }, [SOCK_DGRAM] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, }, [SOCK_RAW] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_RAW_BIND, [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_INET_RAW_SEND, }, }; /* * Mapping table from "enum tomoyo_network_acl_index" to * "enum tomoyo_mac_index" for unix domain socket. */ static const u8 tomoyo_unix2mac [TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = { [SOCK_STREAM] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, [TOMOYO_NETWORK_LISTEN] = TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, [TOMOYO_NETWORK_CONNECT] = TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, }, [SOCK_DGRAM] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, }, [SOCK_SEQPACKET] = { [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, [TOMOYO_NETWORK_LISTEN] = TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, [TOMOYO_NETWORK_CONNECT] = TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, }, }; /** * tomoyo_same_inet_acl - Check for duplicated "struct tomoyo_inet_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_inet_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_inet_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_inet_acl *p2 = container_of(b, typeof(*p2), head); return p1->protocol == p2->protocol && tomoyo_same_ipaddr_union(&p1->address, &p2->address) && tomoyo_same_number_union(&p1->port, &p2->port); } /** * tomoyo_same_unix_acl - Check for duplicated "struct tomoyo_unix_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_unix_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_unix_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_unix_acl *p2 = container_of(b, typeof(*p2), head); return p1->protocol == p2->protocol && tomoyo_same_name_union(&p1->name, &p2->name); } /** * tomoyo_merge_inet_acl - Merge duplicated "struct tomoyo_inet_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_inet_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_inet_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_inet_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_merge_unix_acl - Merge duplicated "struct tomoyo_unix_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_unix_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_unix_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_unix_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_write_inet_network - Write "struct tomoyo_inet_acl" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_inet_network(struct tomoyo_acl_param *param) { struct tomoyo_inet_acl e = { .head.type = TOMOYO_TYPE_INET_ACL }; int error = -EINVAL; u8 type; const char *protocol = tomoyo_read_token(param); const char *operation = tomoyo_read_token(param); for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++) if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol])) break; for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_socket_keyword[type])) e.perm |= 1 << type; if (e.protocol == TOMOYO_SOCK_MAX || !e.perm) return -EINVAL; if (param->data[0] == '@') { param->data++; e.address.group = tomoyo_get_group(param, TOMOYO_ADDRESS_GROUP); if (!e.address.group) return -ENOMEM; } else { if (!tomoyo_parse_ipaddr_union(param, &e.address)) goto out; } if (!tomoyo_parse_number_union(param, &e.port) || e.port.values[1] > 65535) goto out; error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_inet_acl, tomoyo_merge_inet_acl); out: tomoyo_put_group(e.address.group); tomoyo_put_number_union(&e.port); return error; } /** * tomoyo_write_unix_network - Write "struct tomoyo_unix_acl" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_unix_network(struct tomoyo_acl_param *param) { struct tomoyo_unix_acl e = { .head.type = TOMOYO_TYPE_UNIX_ACL }; int error; u8 type; const char *protocol = tomoyo_read_token(param); const char *operation = tomoyo_read_token(param); for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++) if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol])) break; for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_socket_keyword[type])) e.perm |= 1 << type; if (e.protocol == TOMOYO_SOCK_MAX || !e.perm) return -EINVAL; if (!tomoyo_parse_name_union(param, &e.name)) return -EINVAL; error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_unix_acl, tomoyo_merge_unix_acl); tomoyo_put_name_union(&e.name); return error; } /** * tomoyo_audit_net_log - Audit network log. * * @r: Pointer to "struct tomoyo_request_info". * @family: Name of socket family ("inet" or "unix"). * @protocol: Name of protocol in @family. * @operation: Name of socket operation. * @address: Name of address. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_net_log(struct tomoyo_request_info *r, const char *family, const u8 protocol, const u8 operation, const char *address) { return tomoyo_supervisor(r, "network %s %s %s %s\n", family, tomoyo_proto_keyword[protocol], tomoyo_socket_keyword[operation], address); } /** * tomoyo_audit_inet_log - Audit INET network log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_inet_log(struct tomoyo_request_info *r) { char buf[128]; int len; const __be32 *address = r->param.inet_network.address; if (r->param.inet_network.is_ipv6) tomoyo_print_ipv6(buf, sizeof(buf), (const struct in6_addr *) address, (const struct in6_addr *) address); else tomoyo_print_ipv4(buf, sizeof(buf), address, address); len = strlen(buf); snprintf(buf + len, sizeof(buf) - len, " %u", r->param.inet_network.port); return tomoyo_audit_net_log(r, "inet", r->param.inet_network.protocol, r->param.inet_network.operation, buf); } /** * tomoyo_audit_unix_log - Audit UNIX network log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_unix_log(struct tomoyo_request_info *r) { return tomoyo_audit_net_log(r, "unix", r->param.unix_network.protocol, r->param.unix_network.operation, r->param.unix_network.address->name); } /** * tomoyo_check_inet_acl - Check permission for inet domain socket operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_inet_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_inet_acl *acl = container_of(ptr, typeof(*acl), head); const u8 size = r->param.inet_network.is_ipv6 ? 16 : 4; if (!(acl->perm & (1 << r->param.inet_network.operation)) || !tomoyo_compare_number_union(r->param.inet_network.port, &acl->port)) return false; if (acl->address.group) return tomoyo_address_matches_group (r->param.inet_network.is_ipv6, r->param.inet_network.address, acl->address.group); return acl->address.is_ipv6 == r->param.inet_network.is_ipv6 && memcmp(&acl->address.ip[0], r->param.inet_network.address, size) <= 0 && memcmp(r->param.inet_network.address, &acl->address.ip[1], size) <= 0; } /** * tomoyo_check_unix_acl - Check permission for unix domain socket operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_unix_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_unix_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.unix_network.operation)) && tomoyo_compare_name_union(r->param.unix_network.address, &acl->name); } /** * tomoyo_inet_entry - Check permission for INET network operation. * * @address: Pointer to "struct tomoyo_addr_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_inet_entry(const struct tomoyo_addr_info *address) { const int idx = tomoyo_read_lock(); struct tomoyo_request_info r; int error = 0; const u8 type = tomoyo_inet2mac[address->protocol][address->operation]; if (type && tomoyo_init_request_info(&r, NULL, type) != TOMOYO_CONFIG_DISABLED) { r.param_type = TOMOYO_TYPE_INET_ACL; r.param.inet_network.protocol = address->protocol; r.param.inet_network.operation = address->operation; r.param.inet_network.is_ipv6 = address->inet.is_ipv6; r.param.inet_network.address = address->inet.address; r.param.inet_network.port = ntohs(address->inet.port); do { tomoyo_check_acl(&r, tomoyo_check_inet_acl); error = tomoyo_audit_inet_log(&r); } while (error == TOMOYO_RETRY_REQUEST); } tomoyo_read_unlock(idx); return error; } /** * tomoyo_check_inet_address - Check permission for inet domain socket's operation. * * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * @port: Port number. * @address: Pointer to "struct tomoyo_addr_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_check_inet_address(const struct sockaddr *addr, const unsigned int addr_len, const u16 port, struct tomoyo_addr_info *address) { struct tomoyo_inet_addr_info *i = &address->inet; if (addr_len < offsetofend(struct sockaddr, sa_family)) return 0; switch (addr->sa_family) { case AF_INET6: if (addr_len < SIN6_LEN_RFC2133) goto skip; i->is_ipv6 = true; i->address = (__be32 *) ((struct sockaddr_in6 *) addr)->sin6_addr.s6_addr; i->port = ((struct sockaddr_in6 *) addr)->sin6_port; break; case AF_INET: if (addr_len < sizeof(struct sockaddr_in)) goto skip; i->is_ipv6 = false; i->address = (__be32 *) &((struct sockaddr_in *) addr)->sin_addr; i->port = ((struct sockaddr_in *) addr)->sin_port; break; default: goto skip; } if (address->protocol == SOCK_RAW) i->port = htons(port); return tomoyo_inet_entry(address); skip: return 0; } /** * tomoyo_unix_entry - Check permission for UNIX network operation. * * @address: Pointer to "struct tomoyo_addr_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_unix_entry(const struct tomoyo_addr_info *address) { const int idx = tomoyo_read_lock(); struct tomoyo_request_info r; int error = 0; const u8 type = tomoyo_unix2mac[address->protocol][address->operation]; if (type && tomoyo_init_request_info(&r, NULL, type) != TOMOYO_CONFIG_DISABLED) { char *buf = address->unix0.addr; int len = address->unix0.addr_len - sizeof(sa_family_t); if (len <= 0) { buf = "anonymous"; len = 9; } else if (buf[0]) { len = strnlen(buf, len); } buf = tomoyo_encode2(buf, len); if (buf) { struct tomoyo_path_info addr; addr.name = buf; tomoyo_fill_path_info(&addr); r.param_type = TOMOYO_TYPE_UNIX_ACL; r.param.unix_network.protocol = address->protocol; r.param.unix_network.operation = address->operation; r.param.unix_network.address = &addr; do { tomoyo_check_acl(&r, tomoyo_check_unix_acl); error = tomoyo_audit_unix_log(&r); } while (error == TOMOYO_RETRY_REQUEST); kfree(buf); } else error = -ENOMEM; } tomoyo_read_unlock(idx); return error; } /** * tomoyo_check_unix_address - Check permission for unix domain socket's operation. * * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * @address: Pointer to "struct tomoyo_addr_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_check_unix_address(struct sockaddr *addr, const unsigned int addr_len, struct tomoyo_addr_info *address) { struct tomoyo_unix_addr_info *u = &address->unix0; if (addr_len < offsetofend(struct sockaddr, sa_family)) return 0; if (addr->sa_family != AF_UNIX) return 0; u->addr = ((struct sockaddr_un *) addr)->sun_path; u->addr_len = addr_len; return tomoyo_unix_entry(address); } /** * tomoyo_kernel_service - Check whether I'm kernel service or not. * * Returns true if I'm kernel service, false otherwise. */ static bool tomoyo_kernel_service(void) { /* Nothing to do if I am a kernel service. */ return current->flags & PF_KTHREAD; } /** * tomoyo_sock_family - Get socket's family. * * @sk: Pointer to "struct sock". * * Returns one of PF_INET, PF_INET6, PF_UNIX or 0. */ static u8 tomoyo_sock_family(struct sock *sk) { u8 family; if (tomoyo_kernel_service()) return 0; family = sk->sk_family; switch (family) { case PF_INET: case PF_INET6: case PF_UNIX: return family; default: return 0; } } /** * tomoyo_socket_listen_permission - Check permission for listening a socket. * * @sock: Pointer to "struct socket". * * Returns 0 on success, negative value otherwise. */ int tomoyo_socket_listen_permission(struct socket *sock) { struct tomoyo_addr_info address; const u8 family = tomoyo_sock_family(sock->sk); const unsigned int type = sock->type; struct sockaddr_storage addr; int addr_len; if (!family || (type != SOCK_STREAM && type != SOCK_SEQPACKET)) return 0; { const int error = sock->ops->getname(sock, (struct sockaddr *) &addr, 0); if (error < 0) return error; addr_len = error; } address.protocol = type; address.operation = TOMOYO_NETWORK_LISTEN; if (family == PF_UNIX) return tomoyo_check_unix_address((struct sockaddr *) &addr, addr_len, &address); return tomoyo_check_inet_address((struct sockaddr *) &addr, addr_len, 0, &address); } /** * tomoyo_socket_connect_permission - Check permission for setting the remote address of a socket. * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len) { struct tomoyo_addr_info address; const u8 family = tomoyo_sock_family(sock->sk); const unsigned int type = sock->type; if (!family) return 0; address.protocol = type; switch (type) { case SOCK_DGRAM: case SOCK_RAW: address.operation = TOMOYO_NETWORK_SEND; break; case SOCK_STREAM: case SOCK_SEQPACKET: address.operation = TOMOYO_NETWORK_CONNECT; break; default: return 0; } if (family == PF_UNIX) return tomoyo_check_unix_address(addr, addr_len, &address); return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol, &address); } /** * tomoyo_socket_bind_permission - Check permission for setting the local address of a socket. * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len) { struct tomoyo_addr_info address; const u8 family = tomoyo_sock_family(sock->sk); const unsigned int type = sock->type; if (!family) return 0; switch (type) { case SOCK_STREAM: case SOCK_DGRAM: case SOCK_RAW: case SOCK_SEQPACKET: address.protocol = type; address.operation = TOMOYO_NETWORK_BIND; break; default: return 0; } if (family == PF_UNIX) return tomoyo_check_unix_address(addr, addr_len, &address); return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol, &address); } /** * tomoyo_socket_sendmsg_permission - Check permission for sending a datagram. * * @sock: Pointer to "struct socket". * @msg: Pointer to "struct msghdr". * @size: Unused. * * Returns 0 on success, negative value otherwise. */ int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size) { struct tomoyo_addr_info address; const u8 family = tomoyo_sock_family(sock->sk); const unsigned int type = sock->type; if (!msg->msg_name || !family || (type != SOCK_DGRAM && type != SOCK_RAW)) return 0; address.protocol = type; address.operation = TOMOYO_NETWORK_SEND; if (family == PF_UNIX) return tomoyo_check_unix_address((struct sockaddr *) msg->msg_name, msg->msg_namelen, &address); return tomoyo_check_inet_address((struct sockaddr *) msg->msg_name, msg->msg_namelen, sock->sk->sk_protocol, &address); } |
| 6 6 6 6 6 6 6 6 6 6 6 15 15 15 15 15 6 6 6 15 15 15 15 15 15 15 15 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Scanning implementation * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2004, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/sch_generic.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/random.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "mesh.h" #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) #define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 9) void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss) { if (!bss) return; cfg80211_put_bss(local->hw.wiphy, container_of((void *)bss, struct cfg80211_bss, priv)); } static bool is_uapsd_supported(struct ieee802_11_elems *elems) { u8 qos_info; if (elems->wmm_info && elems->wmm_info_len == 7 && elems->wmm_info[5] == 1) qos_info = elems->wmm_info[6]; else if (elems->wmm_param && elems->wmm_param_len == 24 && elems->wmm_param[5] == 1) qos_info = elems->wmm_param[6]; else /* no valid wmm information or parameter element found */ return false; return qos_info & IEEE80211_WMM_IE_AP_QOSINFO_UAPSD; } static void ieee80211_update_bss_from_elems(struct ieee80211_local *local, struct ieee80211_bss *bss, struct ieee802_11_elems *elems, struct ieee80211_rx_status *rx_status, bool beacon) { int clen, srlen; if (beacon) bss->device_ts_beacon = rx_status->device_timestamp; else bss->device_ts_presp = rx_status->device_timestamp; if (elems->parse_error) { if (beacon) bss->corrupt_data |= IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data |= IEEE80211_BSS_CORRUPT_PROBE_RESP; } else { if (beacon) bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_PROBE_RESP; } /* save the ERP value so that it is available at association time */ if (elems->erp_info && (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_ERP))) { bss->erp_value = elems->erp_info[0]; bss->has_erp_value = true; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_ERP; } /* replace old supported rates if we get new values */ if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_RATES)) { srlen = 0; if (elems->supp_rates) { clen = IEEE80211_MAX_SUPP_RATES; if (clen > elems->supp_rates_len) clen = elems->supp_rates_len; memcpy(bss->supp_rates, elems->supp_rates, clen); srlen += clen; } if (elems->ext_supp_rates) { clen = IEEE80211_MAX_SUPP_RATES - srlen; if (clen > elems->ext_supp_rates_len) clen = elems->ext_supp_rates_len; memcpy(bss->supp_rates + srlen, elems->ext_supp_rates, clen); srlen += clen; } if (srlen) { bss->supp_rates_len = srlen; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_RATES; } } if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_WMM)) { bss->wmm_used = elems->wmm_param || elems->wmm_info; bss->uapsd_supported = is_uapsd_supported(elems); if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_WMM; } if (beacon) { struct ieee80211_supported_band *sband = local->hw.wiphy->bands[rx_status->band]; if (!(rx_status->encoding == RX_ENC_HT) && !(rx_status->encoding == RX_ENC_VHT)) bss->beacon_rate = &sband->bitrates[rx_status->rate_idx]; } if (elems->vht_cap_elem) bss->vht_cap_info = le32_to_cpu(elems->vht_cap_elem->vht_cap_info); else bss->vht_cap_info = 0; } struct ieee80211_bss * ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_rx_status *rx_status, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_channel *channel) { bool beacon = ieee80211_is_beacon(mgmt->frame_control) || ieee80211_is_s1g_beacon(mgmt->frame_control); struct cfg80211_bss *cbss, *non_tx_cbss; struct ieee80211_bss *bss, *non_tx_bss; struct cfg80211_inform_bss bss_meta = { .boottime_ns = rx_status->boottime_ns, }; bool signal_valid; struct ieee80211_sub_if_data *scan_sdata; struct ieee802_11_elems *elems; size_t baselen; u8 *elements; if (rx_status->flag & RX_FLAG_NO_SIGNAL_VAL) bss_meta.signal = 0; /* invalid signal indication */ else if (ieee80211_hw_check(&local->hw, SIGNAL_DBM)) bss_meta.signal = rx_status->signal * 100; else if (ieee80211_hw_check(&local->hw, SIGNAL_UNSPEC)) bss_meta.signal = (rx_status->signal * 100) / local->hw.max_signal; bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_20; if (rx_status->bw == RATE_INFO_BW_5) bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_5; else if (rx_status->bw == RATE_INFO_BW_10) bss_meta.scan_width = NL80211_BSS_CHAN_WIDTH_10; bss_meta.chan = channel; rcu_read_lock(); scan_sdata = rcu_dereference(local->scan_sdata); if (scan_sdata && scan_sdata->vif.type == NL80211_IFTYPE_STATION && scan_sdata->vif.bss_conf.assoc && ieee80211_have_rx_timestamp(rx_status)) { bss_meta.parent_tsf = ieee80211_calculate_rx_timestamp(local, rx_status, len + FCS_LEN, 24); ether_addr_copy(bss_meta.parent_bssid, scan_sdata->vif.bss_conf.bssid); } rcu_read_unlock(); cbss = cfg80211_inform_bss_frame_data(local->hw.wiphy, &bss_meta, mgmt, len, GFP_ATOMIC); if (!cbss) return NULL; if (ieee80211_is_probe_resp(mgmt->frame_control)) { elements = mgmt->u.probe_resp.variable; baselen = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); } else if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { struct ieee80211_ext *ext = (void *) mgmt; baselen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable); elements = ext->u.s1g_beacon.variable; } else { baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable); elements = mgmt->u.beacon.variable; } if (baselen > len) return NULL; elems = ieee802_11_parse_elems(elements, len - baselen, false, mgmt->bssid, cbss->bssid); if (!elems) return NULL; /* In case the signal is invalid update the status */ signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; bss = (void *)cbss->priv; ieee80211_update_bss_from_elems(local, bss, elems, rx_status, beacon); list_for_each_entry(non_tx_cbss, &cbss->nontrans_list, nontrans_list) { non_tx_bss = (void *)non_tx_cbss->priv; ieee80211_update_bss_from_elems(local, non_tx_bss, elems, rx_status, beacon); } kfree(elems); return bss; } static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, u32 scan_flags, const u8 *da) { if (!sdata) return false; /* accept broadcast for OCE */ if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP && is_broadcast_ether_addr(da)) return true; if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) return true; return ether_addr_equal(da, sdata->vif.addr); } void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_sub_if_data *sdata1, *sdata2; struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; size_t min_hdr_len = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); if (!ieee80211_is_probe_resp(mgmt->frame_control) && !ieee80211_is_beacon(mgmt->frame_control) && !ieee80211_is_s1g_beacon(mgmt->frame_control)) return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_short_beacon.variable); else min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); } if (skb->len < min_hdr_len) return; sdata1 = rcu_dereference(local->scan_sdata); sdata2 = rcu_dereference(local->sched_scan_sdata); if (likely(!sdata1 && !sdata2)) return; if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { /* * we were passive scanning because of radar/no-IR, but * the beacon/proberesp rx gives us an opportunity to upgrade * to active scan */ set_bit(SCAN_BEACON_DONE, &local->scanning); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); } if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; u32 scan_req_flags = 0, sched_scan_req_flags = 0; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); if (scan_req) scan_req_flags = scan_req->flags; if (sched_scan_req) sched_scan_req_flags = sched_scan_req->flags; /* ignore ProbeResp to foreign address or non-bcast (OCE) * unless scanning with randomised address */ if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags, mgmt->da) && !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags, mgmt->da)) return; } channel = ieee80211_get_channel_khz(local->hw.wiphy, ieee80211_rx_status_to_khz(rx_status)); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); if (bss) ieee80211_rx_bss_put(local, bss); } static void ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef, enum nl80211_bss_scan_width scan_width) { memset(chandef, 0, sizeof(*chandef)); switch (scan_width) { case NL80211_BSS_CHAN_WIDTH_5: chandef->width = NL80211_CHAN_WIDTH_5; break; case NL80211_BSS_CHAN_WIDTH_10: chandef->width = NL80211_CHAN_WIDTH_10; break; default: chandef->width = NL80211_CHAN_WIDTH_20_NOHT; break; } } /* return false if no more work */ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; int i, ielen, n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } n_chans = req->n_channels; } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; local->hw_scan_req->req.channels[n_chans] = req->channels[i]; n_chans++; bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; } while (!n_chans); } local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef, req->scan_width); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ielen = ieee80211_build_preq_ies(sdata, (u8 *)local->hw_scan_req->req.ie, local->hw_scan_ies_bufsize, &local->hw_scan_req->ies, req->ie, req->ie_len, bands_used, req->rates, &chandef, flags); local->hw_scan_req->req.ie_len = ielen; local->hw_scan_req->req.no_cck = req->no_cck; ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); ether_addr_copy(local->hw_scan_req->req.mac_addr_mask, req->mac_addr_mask); ether_addr_copy(local->hw_scan_req->req.bssid, req->bssid); return true; } static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) { struct ieee80211_local *local = hw_to_local(hw); bool hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); /* * It's ok to abort a not-yet-running scan (that * we have one at all will be verified by checking * local->scan_req next), but not to complete it * successfully. */ if (WARN_ON(!local->scanning && !aborted)) aborted = true; if (WARN_ON(!local->scan_req)) return; scan_sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)); if (hw_scan && !aborted && !ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS) && ieee80211_prep_hw_scan(scan_sdata)) { int rc; rc = drv_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)), local->hw_scan_req); if (rc == 0) return; /* HW scan failed and is going to be reported as aborted, * so clear old scan info. */ memset(&local->scan_info, 0, sizeof(local->scan_info)); aborted = true; } kfree(local->hw_scan_req); local->hw_scan_req = NULL; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); local->scanning = 0; local->scan_chandef.chan = NULL; synchronize_rcu(); if (scan_req != local->int_scan_req) { local->scan_info.aborted = aborted; cfg80211_scan_done(scan_req, &local->scan_info); } /* Set power back to normal operating levels. */ ieee80211_hw_config(local, 0); if (!hw_scan) { ieee80211_configure_filter(local); drv_sw_scan_complete(local, scan_sdata); ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); /* Requeue all the work that might have been ignored while * the scan was in progress; if there was none this will * just be a no-op for the particular interface. */ list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (ieee80211_sdata_running(sdata)) ieee80211_queue_work(&sdata->local->hw, &sdata->work); } if (was_scanning) ieee80211_start_next_roc(local); } void ieee80211_scan_completed(struct ieee80211_hw *hw, struct cfg80211_scan_info *info) { struct ieee80211_local *local = hw_to_local(hw); trace_api_scan_completed(local, info->aborted); set_bit(SCAN_COMPLETED, &local->scanning); if (info->aborted) set_bit(SCAN_ABORTED, &local->scanning); memcpy(&local->scan_info, info, sizeof(*info)); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); } EXPORT_SYMBOL(ieee80211_scan_completed); static int ieee80211_start_sw_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { /* Software scan is not supported in multi-channel cases */ if (local->use_chanctx) return -EOPNOTSUPP; /* * Hardware/driver doesn't support hw_scan, so use software * scanning instead. First send a nullfunc frame with power save * bit on so that AP will buffer the frames for us while we are not * listening, then send probe requests to each channel and wait for * the responses. After all channels are scanned, tune back to the * original channel and send a nullfunc frame with power save bit * off to trigger the AP to send us all the buffered frames. * * Note that while local->sw_scanning is true everything else but * nullfunc frames and probe requests will be dropped in * ieee80211_tx_h_check_assoc(). */ drv_sw_scan_start(local, sdata, local->scan_addr); local->leave_oper_channel_time = jiffies; local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; ieee80211_offchannel_stop_vifs(local); /* ensure nullfunc is transmitted before leaving operating channel */ ieee80211_flush_queues(local, NULL, false); ieee80211_configure_filter(local); /* We need to set power level at maximum rate for scanning. */ ieee80211_hw_config(local, 0); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); return 0; } static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *sdata_iter; if (!ieee80211_is_radar_required(local)) return true; if (!regulatory_pre_cac_allowed(local->hw.wiphy)) return false; mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata_iter, &local->interfaces, list) { if (sdata_iter->wdev.cac_started) { mutex_unlock(&local->iflist_mtx); return false; } } mutex_unlock(&local->iflist_mtx); return true; } static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { if (!__ieee80211_can_leave_ch(sdata)) return false; if (!list_empty(&local->roc_list)) return false; if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.flags & IEEE80211_STA_CONNECTION_POLL) return false; return true; } void ieee80211_run_deferred_scan(struct ieee80211_local *local) { lockdep_assert_held(&local->mtx); if (!local->scan_req || local->scanning) return; if (!ieee80211_can_scan(local, rcu_dereference_protected( local->scan_sdata, lockdep_is_held(&local->mtx)))) return; ieee80211_queue_delayed_work(&local->hw, &local->scan_work, round_jiffies_relative(0)); } static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 ratemask, u32 flags, u32 tx_flags, struct ieee80211_channel *channel) { struct sk_buff *skb; skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel, ssid, ssid_len, ie, ie_len, flags); if (skb) { if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 sn = get_random_u32(); info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, unsigned long *next_delay) { int i; struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; enum nl80211_band band = local->hw.conf.chandef.chan->band; u32 flags = 0, tx_flags; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK; if (scan_req->no_cck) tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE; if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN) flags |= IEEE80211_PROBE_FLAG_RANDOM_SN; sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)); for (i = 0; i < scan_req->n_ssids; i++) ieee80211_send_scan_probe_req( sdata, local->scan_addr, scan_req->bssid, scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len, scan_req->ie, scan_req->ie_len, scan_req->rates[band], flags, tx_flags, local->hw.conf.chandef.chan); /* * After sending probe requests, wait for probe responses * on the channel. */ *next_delay = IEEE80211_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; } static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { struct ieee80211_local *local = sdata->local; bool hw_scan = local->ops->hw_scan; int rc; lockdep_assert_held(&local->mtx); if (local->scan_req) return -EBUSY; if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; if (!ieee80211_can_scan(local, sdata)) { /* wait for the work to finish/time out */ rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); return 0; } again: if (hw_scan) { u8 *ies; local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { int i, n_bands = 0; u8 bands_counted = 0; for (i = 0; i < req->n_channels; i++) { if (bands_counted & BIT(req->channels[i]->band)) continue; bands_counted |= BIT(req->channels[i]->band); n_bands++; } local->hw_scan_ies_bufsize *= n_bands; } local->hw_scan_req = kmalloc(struct_size(local->hw_scan_req, req.channels, req->n_channels) + local->hw_scan_ies_bufsize, GFP_KERNEL); if (!local->hw_scan_req) return -ENOMEM; local->hw_scan_req->req.ssids = req->ssids; local->hw_scan_req->req.n_ssids = req->n_ssids; /* None of the channels are actually set * up but let UBSAN know the boundaries. */ local->hw_scan_req->req.n_channels = req->n_channels; ies = (u8 *)local->hw_scan_req + sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); local->hw_scan_req->req.ie = ies; local->hw_scan_req->req.flags = req->flags; eth_broadcast_addr(local->hw_scan_req->req.bssid); local->hw_scan_req->req.duration = req->duration; local->hw_scan_req->req.duration_mandatory = req->duration_mandatory; local->hw_scan_band = 0; local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params; local->hw_scan_req->req.scan_6ghz_params = req->scan_6ghz_params; local->hw_scan_req->req.scan_6ghz = req->scan_6ghz; /* * After allocating local->hw_scan_req, we must * go through until ieee80211_prep_hw_scan(), so * anything that might be changed here and leave * this function early must not go after this * allocation. */ } rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) get_random_mask_addr(local->scan_addr, req->mac_addr, req->mac_addr_mask); else memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN); if (hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); } else if ((req->n_channels == 1) && (req->channels[0] == local->_oper_chandef.chan)) { /* * If we are scanning only on the operating channel * then we do not need to stop normal activities */ unsigned long next_delay; __set_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); ieee80211_recalc_idle(local); /* Notify driver scan is starting, keep order of operations * same as normal software scan, in case that matters. */ drv_sw_scan_start(local, sdata, local->scan_addr); ieee80211_configure_filter(local); /* accept probe-responses */ /* We need to ensure power level is at max for scanning. */ ieee80211_hw_config(local, 0); if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !req->n_ssids) { next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; if (req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); } else { ieee80211_scan_state_send_probe(local, &next_delay); next_delay = IEEE80211_CHANNEL_TIME; } /* Now, just wait a bit and we are all done! */ ieee80211_queue_delayed_work(&local->hw, &local->scan_work, next_delay); return 0; } else { /* Do normal software scan */ __set_bit(SCAN_SW_SCANNING, &local->scanning); } ieee80211_recalc_idle(local); if (hw_scan) { WARN_ON(!ieee80211_prep_hw_scan(sdata)); rc = drv_hw_scan(local, sdata, local->hw_scan_req); } else { rc = ieee80211_start_sw_scan(local, sdata); } if (rc) { kfree(local->hw_scan_req); local->hw_scan_req = NULL; local->scanning = 0; ieee80211_recalc_idle(local); local->scan_req = NULL; RCU_INIT_POINTER(local->scan_sdata, NULL); } if (hw_scan && rc == 1) { /* * we can't fall back to software for P2P-GO * as it must update NoA etc. */ if (ieee80211_vif_type_p2p(&sdata->vif) == NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; hw_scan = false; goto again; } return rc; } static unsigned long ieee80211_scan_get_channel_time(struct ieee80211_channel *chan) { /* * TODO: channel switching also consumes quite some time, * add that delay as well to get a better estimation */ if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) return IEEE80211_PASSIVE_CHANNEL_TIME; return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME; } static void ieee80211_scan_state_decision(struct ieee80211_local *local, unsigned long *next_delay) { bool associated = false; bool tx_empty = true; bool bad_latency; struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *next_chan; enum mac80211_scan_state next_scan_state; struct cfg80211_scan_request *scan_req; /* * check if at least one STA interface is associated, * check if at least one STA interface has pending tx frames * and grab the lowest used beacon interval */ mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) { associated = true; if (!qdisc_all_tx_empty(sdata->dev)) { tx_empty = false; break; } } } } mutex_unlock(&local->iflist_mtx); scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); next_chan = scan_req->channels[local->scan_channel_idx]; /* * we're currently scanning a different channel, let's * see if we can scan another channel without interfering * with the current traffic situation. * * Keep good latency, do not stay off-channel more than 125 ms. */ bad_latency = time_after(jiffies + ieee80211_scan_get_channel_time(next_chan), local->leave_oper_channel_time + HZ / 8); if (associated && !tx_empty) { if (scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) next_scan_state = SCAN_ABORT; else next_scan_state = SCAN_SUSPEND; } else if (associated && bad_latency) { next_scan_state = SCAN_SUSPEND; } else { next_scan_state = SCAN_SET_CHANNEL; } local->next_scan_state = next_scan_state; *next_delay = 0; } static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, unsigned long *next_delay) { int skip; struct ieee80211_channel *chan; enum nl80211_bss_scan_width oper_scan_width; struct cfg80211_scan_request *scan_req; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); skip = 0; chan = scan_req->channels[local->scan_channel_idx]; local->scan_chandef.chan = chan; local->scan_chandef.center_freq1 = chan->center_freq; local->scan_chandef.freq1_offset = chan->freq_offset; local->scan_chandef.center_freq2 = 0; /* For scanning on the S1G band, ignore scan_width (which is constant * across all channels) for now since channel width is specific to each * channel. Detect the required channel width here and likely revisit * later. Maybe scan_width could be used to build the channel scan list? */ if (chan->band == NL80211_BAND_S1GHZ) { local->scan_chandef.width = ieee80211_s1g_channel_width(chan); goto set_channel; } switch (scan_req->scan_width) { case NL80211_BSS_CHAN_WIDTH_5: local->scan_chandef.width = NL80211_CHAN_WIDTH_5; break; case NL80211_BSS_CHAN_WIDTH_10: local->scan_chandef.width = NL80211_CHAN_WIDTH_10; break; default: case NL80211_BSS_CHAN_WIDTH_20: /* If scanning on oper channel, use whatever channel-type * is currently in use. */ oper_scan_width = cfg80211_chandef_to_scan_width( &local->_oper_chandef); if (chan == local->_oper_chandef.chan && oper_scan_width == scan_req->scan_width) local->scan_chandef = local->_oper_chandef; else local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; break; case NL80211_BSS_CHAN_WIDTH_1: case NL80211_BSS_CHAN_WIDTH_2: /* shouldn't get here, S1G handled above */ WARN_ON(1); break; } set_channel: if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) skip = 1; /* advance state machine to next channel/band */ local->scan_channel_idx++; if (skip) { /* if we skip this channel return to the decision state */ local->next_scan_state = SCAN_DECISION; return; } /* * Probe delay is used to update the NAV, cf. 11.1.3.2.2 * (which unfortunately doesn't say _why_ step a) is done, * but it waits for the probe delay or until a frame is * received - and the received frame would update the NAV). * For now, we do not support waiting until a frame is * received. * * In any case, it is not necessary for a passive scan. */ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !scan_req->n_ssids) { *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; if (scan_req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); return; } /* active scan, send probes */ *next_delay = IEEE80211_PROBE_DELAY; local->next_scan_state = SCAN_SEND_PROBE; } static void ieee80211_scan_state_suspend(struct ieee80211_local *local, unsigned long *next_delay) { /* switch back to the operating channel */ local->scan_chandef.chan = NULL; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); /* disable PS */ ieee80211_offchannel_return(local); *next_delay = HZ / 5; /* afterwards, resume scan & go to next channel */ local->next_scan_state = SCAN_RESUME; } static void ieee80211_scan_state_resume(struct ieee80211_local *local, unsigned long *next_delay) { ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { ieee80211_flush_queues(local, NULL, false); *next_delay = 0; } else *next_delay = HZ / 10; /* remember when we left the operating channel */ local->leave_oper_channel_time = jiffies; /* advance to the next channel to be scanned */ local->next_scan_state = SCAN_SET_CHANNEL; } void ieee80211_scan_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; unsigned long next_delay = 0; bool aborted; mutex_lock(&local->mtx); if (!ieee80211_can_run_worker(local)) { aborted = true; goto out_complete; } sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)); scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); /* When scanning on-channel, the first-callback means completed. */ if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (!sdata || !scan_req) goto out; if (!local->scanning) { int rc; RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); rc = __ieee80211_start_scan(sdata, scan_req); if (rc) { /* need to complete scan in cfg80211 */ rcu_assign_pointer(local->scan_req, scan_req); aborted = true; goto out_complete; } else goto out; } clear_bit(SCAN_BEACON_WAIT, &local->scanning); /* * as long as no delay is required advance immediately * without scheduling a new work */ do { if (!ieee80211_sdata_running(sdata)) { aborted = true; goto out_complete; } if (test_and_clear_bit(SCAN_BEACON_DONE, &local->scanning) && local->next_scan_state == SCAN_DECISION) local->next_scan_state = SCAN_SEND_PROBE; switch (local->next_scan_state) { case SCAN_DECISION: /* if no more bands/channels left, complete scan */ if (local->scan_channel_idx >= scan_req->n_channels) { aborted = false; goto out_complete; } ieee80211_scan_state_decision(local, &next_delay); break; case SCAN_SET_CHANNEL: ieee80211_scan_state_set_channel(local, &next_delay); break; case SCAN_SEND_PROBE: ieee80211_scan_state_send_probe(local, &next_delay); break; case SCAN_SUSPEND: ieee80211_scan_state_suspend(local, &next_delay); break; case SCAN_RESUME: ieee80211_scan_state_resume(local, &next_delay); break; case SCAN_ABORT: aborted = true; goto out_complete; } } while (next_delay == 0); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, next_delay); goto out; out_complete: __ieee80211_scan_completed(&local->hw, aborted); out: mutex_unlock(&local->mtx); } int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { int res; mutex_lock(&sdata->local->mtx); res = __ieee80211_start_scan(sdata, req); mutex_unlock(&sdata->local->mtx); return res; } int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, struct ieee80211_channel **channels, unsigned int n_channels, enum nl80211_bss_scan_width scan_width) { struct ieee80211_local *local = sdata->local; int ret = -EBUSY, i, n_ch = 0; enum nl80211_band band; mutex_lock(&local->mtx); /* busy scanning */ if (local->scan_req) goto unlock; /* fill internal scan request */ if (!channels) { int max_n; for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!local->hw.wiphy->bands[band] || band == NL80211_BAND_6GHZ) continue; max_n = local->hw.wiphy->bands[band]->n_channels; for (i = 0; i < max_n; i++) { struct ieee80211_channel *tmp_ch = &local->hw.wiphy->bands[band]->channels[i]; if (tmp_ch->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED)) continue; local->int_scan_req->channels[n_ch] = tmp_ch; n_ch++; } } if (WARN_ON_ONCE(n_ch == 0)) goto unlock; local->int_scan_req->n_channels = n_ch; } else { for (i = 0; i < n_channels; i++) { if (channels[i]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED)) continue; local->int_scan_req->channels[n_ch] = channels[i]; n_ch++; } if (WARN_ON_ONCE(n_ch == 0)) goto unlock; local->int_scan_req->n_channels = n_ch; } local->int_scan_req->ssids = &local->scan_ssid; local->int_scan_req->n_ssids = 1; local->int_scan_req->scan_width = scan_width; memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); local->int_scan_req->ssids[0].ssid_len = ssid_len; ret = __ieee80211_start_scan(sdata, sdata->local->int_scan_req); unlock: mutex_unlock(&local->mtx); return ret; } /* * Only call this function when a scan can't be queued -- under RTNL. */ void ieee80211_scan_cancel(struct ieee80211_local *local) { /* * We are canceling software scan, or deferred scan that was not * yet really started (see __ieee80211_start_scan ). * * Regarding hardware scan: * - we can not call __ieee80211_scan_completed() as when * SCAN_HW_SCANNING bit is set this function change * local->hw_scan_req to operate on 5G band, what race with * driver which can use local->hw_scan_req * * - we can not cancel scan_work since driver can schedule it * by ieee80211_scan_completed(..., true) to finish scan * * Hence we only call the cancel_hw_scan() callback, but the low-level * driver is still responsible for calling ieee80211_scan_completed() * after the scan was completed/aborted. */ mutex_lock(&local->mtx); if (!local->scan_req) goto out; /* * We have a scan running and the driver already reported completion, * but the worker hasn't run yet or is stuck on the mutex - mark it as * cancelled. */ if (test_bit(SCAN_HW_SCANNING, &local->scanning) && test_bit(SCAN_COMPLETED, &local->scanning)) { set_bit(SCAN_HW_CANCELLED, &local->scanning); goto out; } if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { /* * Make sure that __ieee80211_scan_completed doesn't trigger a * scan on another band. */ set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx))); goto out; } /* * If the work is currently running, it must be blocked on * the mutex, but we'll set scan_sdata = NULL and it'll * simply exit once it acquires the mutex. */ cancel_delayed_work(&local->scan_work); /* and clean up */ memset(&local->scan_info, 0, sizeof(local->scan_info)); __ieee80211_scan_completed(&local->hw, true); out: mutex_unlock(&local->mtx); } int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_scan_ies sched_scan_ies = {}; struct cfg80211_chan_def chandef; int ret, i, iebufsz, num_bands = 0; u32 rate_masks[NUM_NL80211_BANDS] = {}; u8 bands_used = 0; u8 *ie; u32 flags = 0; iebufsz = local->scan_ies_len + req->ie_len; lockdep_assert_held(&local->mtx); if (!local->ops->sched_scan_start) return -ENOTSUPP; for (i = 0; i < NUM_NL80211_BANDS; i++) { if (local->hw.wiphy->bands[i]) { bands_used |= BIT(i); rate_masks[i] = (u32) -1; num_bands++; } } if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ie = kcalloc(iebufsz, num_bands, GFP_KERNEL); if (!ie) { ret = -ENOMEM; goto out; } ieee80211_prepare_scan_chandef(&chandef, req->scan_width); ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, &sched_scan_ies, req->ie, req->ie_len, bands_used, rate_masks, &chandef, flags); ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { rcu_assign_pointer(local->sched_scan_sdata, sdata); rcu_assign_pointer(local->sched_scan_req, req); } kfree(ie); out: if (ret) { /* Clean in case of failure after HW restart or upon resume. */ RCU_INIT_POINTER(local->sched_scan_sdata, NULL); RCU_INIT_POINTER(local->sched_scan_req, NULL); } return ret; } int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; int ret; mutex_lock(&local->mtx); if (rcu_access_pointer(local->sched_scan_sdata)) { mutex_unlock(&local->mtx); return -EBUSY; } ret = __ieee80211_request_sched_scan_start(sdata, req); mutex_unlock(&local->mtx); return ret; } int ieee80211_request_sched_scan_stop(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sched_scan_sdata; int ret = -ENOENT; mutex_lock(&local->mtx); if (!local->ops->sched_scan_stop) { ret = -ENOTSUPP; goto out; } /* We don't want to restart sched scan anymore. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, lockdep_is_held(&local->mtx)); if (sched_scan_sdata) { ret = drv_sched_scan_stop(local, sched_scan_sdata); if (!ret) RCU_INIT_POINTER(local->sched_scan_sdata, NULL); } out: mutex_unlock(&local->mtx); return ret; } void ieee80211_sched_scan_results(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_results(local); cfg80211_sched_scan_results(hw->wiphy, 0); } EXPORT_SYMBOL(ieee80211_sched_scan_results); void ieee80211_sched_scan_end(struct ieee80211_local *local) { mutex_lock(&local->mtx); if (!rcu_access_pointer(local->sched_scan_sdata)) { mutex_unlock(&local->mtx); return; } RCU_INIT_POINTER(local->sched_scan_sdata, NULL); /* If sched scan was aborted by the driver. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); mutex_unlock(&local->mtx); cfg80211_sched_scan_stopped(local->hw.wiphy, 0); } void ieee80211_sched_scan_stopped_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, sched_scan_stopped_work); ieee80211_sched_scan_end(local); } void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_stopped(local); /* * this shouldn't really happen, so for simplicity * simply ignore it, and let mac80211 reconfigure * the sched scan later on. */ if (local->in_reconfig) return; schedule_work(&local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); |
| 263 263 263 263 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> int sysctl_unprivileged_userfaultfd __read_mostly; static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) { struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; mmap_assert_locked(mm); ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. */ if (huge_pte_none(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, unsigned long address, unsigned long flags, unsigned long reason) { struct mm_struct *mm = ctx->mm; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; bool ret = true; mmap_assert_locked(mm); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * READ_ONCE must function as a barrier with narrower scope * and it must be equivalent to: * _pmd = *pmd; barrier(); * * This is to deal with the instability (as in * pmd_trans_unstable) of the pmd. */ _pmd = READ_ONCE(*pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } /* * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it * and use the standard pte_offset_map() instead of parsing _pmd. */ pte = pte_offset_map(pmd, address); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. */ if (pte_none(*pte)) ret = true; if (!pte_write(*pte) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = vmf->vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update. * * We also don't do userfault handling during * coredumping. hugetlbfs has the special * follow_hugetlb_page() to skip missing pages in the * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with * the no_page_table() helper in follow_page_mask(), but the * shmem_vm_ops->fault method is invoked even during * coredumping without mmap_lock and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* * Coredumping runs without mmap_lock so we can only check that * the mmap_lock is held, if PF_DUMPCORE was not set. */ mmap_assert_locked(mm); ctx = vmf->vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if ((vmf->flags & FAULT_FLAG_USER) == 0 && ctx->flags & UFFD_USER_MODE_ONLY) { printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd " "sysctl knob to 1 if kernel faults must be handled " "without obtaining CAP_SYS_PTRACE capability\n"); goto out; } /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the * last UFFDIO_COPY, without risking to trigger an * involuntary SIGBUS if the process was starting the * userfaultfd while the userfaultfd was still armed * (but after the last UFFDIO_COPY). If the uffd * wasn't already closed when the userfault reached * this point, that would normally be solved by * userfaultfd_must_wait returning 'false'. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd. */ ret = VM_FAULT_NOPAGE; goto out; } /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { printk(KERN_WARNING "FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vmf->vma)) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, vmf->address, vmf->flags, reason); mmap_read_unlock(mm); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { struct vm_area_struct *vma; struct mm_struct *mm = release_new_ctx->mm; /* the various vma->vm_userfaultfd_ctx still points to it */ mmap_write_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; vma->vm_flags &= ~__VM_UFFD_FLAGS; } mmap_write_unlock(mm); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; vma->vm_flags &= ~__VM_UFFD_FLAGS; return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); atomic_inc(&octx->mmap_changing); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } vma->vm_userfaultfd_ctx.ctx = ctx; return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; vma->vm_flags &= ~__VM_UFFD_FLAGS; } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; if (to & ~PAGE_MASK) { userfaultfd_ctx_put(ctx); return; } msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { for ( ; vma && vma->vm_start < end; vma = vma->vm_next) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) continue; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); } return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; WRITE_ONCE(ctx->released, true); if (!mmget_not_zero(mm)) goto wakeup; /* * Flush page faults out of all CPUs. NOTE: all page faults * must be retried without returning VM_FAULT_SIGBUS if * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx * changes while handle_userfault released the mmap_lock. So * it's critical that released is set to true (above), before * taking the mmap_lock for writing. */ mmap_write_lock(mm); prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ !!(vma->vm_flags & __VM_UFFD_FLAGS)); if (vma->vm_userfaultfd_ctx.ctx != ctx) { prev = vma; continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX); if (prev) vma = prev; else prev = vma; vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } mmap_write_unlock(mm); mmput(mm); wakeup: /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; int no_wait = file->f_flags & O_NONBLOCK; struct inode *inode = file_inode(file); if (!userfaultfd_is_initialized(ctx)) return -EINVAL; for (;;) { if (count < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg))) return ret ? ret : -EFAULT; ret += sizeof(msg); buf += sizeof(msg); count -= sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = O_NONBLOCK; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; return 0; } static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { /* FIXME: add WP support to hugetlbfs and shmem */ if (vm_flags & VM_UFFD_WP) { if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) return false; } if (vm_flags & VM_UFFD_MINOR) { if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma))) return false; } return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; bool basic_ioctls; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } BUG_ON(!found); if (vma->vm_start < start) prev = vma; ret = 0; do { cond_resched(); BUG_ON(!vma_can_userfault(vma, vm_flags)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (vma->vm_userfaultfd_ctx.ctx == ctx && (vma->vm_flags & vm_flags) == vm_flags) goto skip; if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx })); if (prev) { vma = prev; goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx.ctx = ctx; if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) hugetlb_unshare_all_pmds(vma); skip: prev = vma; start = vma->vm_end; vma = vma->vm_next; } while (vma && vma->vm_start < end); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; unsigned long new_flags; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; ret = -EINVAL; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags)) goto out_unlock; found = true; } BUG_ON(!found); if (vma->vm_start < start) prev = vma; ret = 0; do { cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (!vma->vm_userfaultfd_ctx.ctx) goto skip; WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX); if (prev) { vma = prev; goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; skip: prev = vma; start = vma->vm_end; vma = vma->vm_next; } while (vma && vma->vm_start < end); out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_BUG_ON(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* * double check for wraparound just in case. copy_from_user() * will later check uffdio_copy.src + uffdio_copy.len to fit * in the userland range. */ ret = -EINVAL; if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src) goto out; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, &ctx->mmap_changing, uffdio_copy.mode); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; BUG_ON(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; /* double check for wraparound just in case. */ if (uffdio_continue.range.start + uffdio_continue.range.len <= uffdio_continue.range.start) { goto out; } if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_continue(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif ret = -EINVAL; if (features & ~uffdio_api.features) goto err_out; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read = userfaultfd_read, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } SYSCALL_DEFINE1(userfaultfd, int, flags) { struct userfaultfd_ctx *ctx; int fd; if (!sysctl_unprivileged_userfaultfd && (flags & UFFD_USER_MODE_ONLY) == 0 && !capable(CAP_SYS_PTRACE)) { printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd " "sysctl knob to 1 if kernel faults must be handled " "without obtaining CAP_SYS_PTRACE capability\n"); return -EPERM; } BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } return fd; } static int __init userfaultfd_init(void) { userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); return 0; } __initcall(userfaultfd_init); |
| 11 3 64 4 | 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM bridge #if !defined(_TRACE_BRIDGE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BRIDGE_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include "../../../net/bridge/br_private.h" TRACE_EVENT(br_fdb_add, TP_PROTO(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags), TP_ARGS(ndm, dev, addr, vid, nlh_flags), TP_STRUCT__entry( __field(u8, ndm_flags) __string(dev, dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(u16, nlh_flags) ), TP_fast_assign( __assign_str(dev, dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->nlh_flags = nlh_flags; __entry->ndm_flags = ndm->ndm_flags; ), TP_printk("dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u nlh_flags %04x ndm_flags %02x", __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->nlh_flags, __entry->ndm_flags) ); TRACE_EVENT(br_fdb_external_learn_add, TP_PROTO(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid), TP_ARGS(br, p, addr, vid), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, p ? p->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, p ? p->dev->name : "null"); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; ), TP_printk("br_dev %s port %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(fdb_delete, TP_PROTO(struct net_bridge *br, struct net_bridge_fdb_entry *f), TP_ARGS(br, f), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, f->dst ? f->dst->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, f->dst ? f->dst->dev->name : "null"); memcpy(__entry->addr, f->key.addr.addr, ETH_ALEN); __entry->vid = f->key.vlan_id; ), TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(br_fdb_update, TP_PROTO(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, unsigned long flags), TP_ARGS(br, source, addr, vid, flags), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, source->dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(unsigned long, flags) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, source->dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->flags = flags; ), TP_printk("br_dev %s source %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u flags 0x%lx", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->flags) ); #endif /* _TRACE_BRIDGE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/srcu.h> #include <linux/lockdep.h> struct blk_mq_tags; struct blk_flush_queue; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @queued: Number of queued requests. */ unsigned long queued; /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; /** * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also * blk_mq_hw_ctx_size(). */ struct srcu_struct srcu[]; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_type - Type of hardware queue * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. * @HCTX_TYPE_READ: Just for READ I/O. * @HCTX_TYPE_POLL: Polled I/O of any kind. * @HCTX_MAX_TYPES: Number of types of hctx. */ enum hctx_type { HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; /** * struct blk_mq_tag_set - tag set that can be shared between request queues * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the * same size, and it's perfectly legal to share maps between * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. * @ops: Pointers to functions that implement block driver behavior. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag * allocations. * @cmd_size: Number of additional bytes to allocate per request. The block * driver owns these additional bytes. * @numa_node: NUMA node the storage adapter has been connected to. * @timeout: Request processing timeout in jiffies. * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. * @active_queues_shared_sbitmap: * number of active request queues per tag set. * @__bitmap_tags: A shared tags sbitmap, used over all hctx's * @__breserved_tags: * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. */ struct blk_mq_tag_set { struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; const struct blk_mq_ops *ops; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; unsigned int cmd_size; int numa_node; unsigned int timeout; unsigned int flags; void *driver_data; atomic_t active_queues_shared_sbitmap; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; struct mutex tag_list_lock; struct list_head tag_list; }; /** * struct blk_mq_queue_data - Data about a request inserted in a queue * * @rq: Request pointer. * @last: If it is the last request in the queue. */ struct blk_mq_queue_data { struct request *rq; bool last; }; typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); /** * struct blk_mq_ops - Callback functions that implements block driver * behaviour. */ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit * requests to hardware, it must define this function. In case of errors * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ int (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ void (*put_budget)(struct request_queue *, int); /** * @set_rq_budget_token: store rq's budget token */ void (*set_rq_budget_token)(struct request *, int); /** * @get_rq_budget_token: retrieve rq's budget token */ int (*get_rq_budget_token)(struct request *); /** * @timeout: Called on request timeout. */ enum blk_eh_timer_return (*timeout)(struct request *, bool); /** * @poll: Called to poll for completion of a specific tag. */ int (*poll)(struct blk_mq_hw_ctx *); /** * @complete: Mark the request as complete. */ void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. */ int (*init_request)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); /** * @initialize_rq_fn: Called from inside blk_get_request(). */ void (*initialize_rq_fn)(struct request *rq); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ int (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); #endif }; enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, /* Do not allow an I/O scheduler to be configured. */ BLK_MQ_F_NO_SCHED = 1 << 6, /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, /* hw queue is inactive after all its CPUs become offline */ BLK_MQ_S_INACTIVE = 3, BLK_MQ_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, }; #define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) #define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, queuedata) \ ({ \ static struct lock_class_key __key; \ \ __blk_mq_alloc_disk(set, queuedata, &__key); \ }) struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); bool blk_mq_queue_inflight(struct request_queue *q); enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), /* set RQF_PM */ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { BLK_MQ_UNIQUE_TAG_BITS = 16, BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1, }; u32 blk_mq_unique_tag(struct request *rq); static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag) { return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS; } static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) { return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } /** * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { return READ_ONCE(rq->state); } static inline int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } static inline int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } /* * * Set the state to complete when completing a request from inside ->queue_rq. * This is used by drivers that want to ensure special complete actions that * need access to the request are called on failure, e.g. by nvme for * multipathing. */ static inline void blk_mq_set_request_complete(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); int blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); bool __blk_should_fake_timeout(struct request_queue *q); static inline bool blk_should_fake_timeout(struct request_queue *q) { if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return __blk_should_fake_timeout(q); return false; } /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted * * Return: request * * Driver command data is immediately after the request. So subtract request * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } /** * blk_mq_rq_to_pdu - cast a request to a PDU * @rq: the request to be casted * * Return: pointer to the PDU * * Driver command data is immediately after the request. So add request to get * the PDU. */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; } #define queue_for_each_hw_ctx(q, hctx, i) \ for ((i) = 0; (i) < (q)->nr_hw_queues && \ ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq) { if (rq->tag != -1) return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT); return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) | BLK_QC_T_INTERNAL; } static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) rq->q->mq_ops->cleanup_rq(rq); } static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, unsigned int nr_segs) { rq->nr_phys_segments = nr_segs; rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); if (bio->bi_bdev) rq->rq_disk = bio->bi_bdev->bd_disk; } blk_qc_t blk_mq_submit_bio(struct bio *bio); void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); #endif |
| 6 6 4 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); } |
| 17 72 19 54 41 17 6 66 55 6 19 54 54 54 54 54 49 66 66 255 243 17 255 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/fs.h> #include <net/af_unix.h> #include <net/scm.h> #include <linux/init.h> #include <linux/io_uring.h> #include "scm.h" unsigned int unix_tot_inflight; EXPORT_SYMBOL(unix_tot_inflight); LIST_HEAD(gc_inflight_list); EXPORT_SYMBOL(gc_inflight_list); DEFINE_SPINLOCK(unix_gc_lock); EXPORT_SYMBOL(unix_gc_lock); struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = file_inode(filp); /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; } return u_sock; } EXPORT_SYMBOL(unix_get_socket); /* Keep the number of times in flight count for the file * descriptor if it is for an AF_UNIX socket. */ void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); spin_lock(&unix_gc_lock); if (s) { struct unix_sock *u = unix_sk(s); if (!u->inflight) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { BUG_ON(list_empty(&u->link)); } u->inflight++; /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); spin_unlock(&unix_gc_lock); } void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); spin_lock(&unix_gc_lock); if (s) { struct unix_sock *u = unix_sk(s); BUG_ON(!u->inflight); BUG_ON(list_empty(&u->link)); u->inflight--; if (!u->inflight) list_del_init(&u->link); /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); } WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); spin_unlock(&unix_gc_lock); } /* * The "user->unix_inflight" variable is protected by the garbage * collection lock, and we just read it locklessly here. If you go * over the limit, there might be a tiny race in actually noticing * it across threads. Tough. */ static inline bool too_many_unix_fds(struct task_struct *p) { struct user_struct *user = current_user(); if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); return false; } int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; if (too_many_unix_fds(current)) return -ETOOMANYREFS; /* * Need to duplicate file references for the sake of garbage * collection. Otherwise a socket in the fps might become a * candidate for GC while the skb is not yet queued. */ UNIXCB(skb).fp = scm_fp_dup(scm->fp); if (!UNIXCB(skb).fp) return -ENOMEM; for (i = scm->fp->count - 1; i >= 0; i--) unix_inflight(scm->fp->user, scm->fp->fp[i]); return 0; } EXPORT_SYMBOL(unix_attach_fds); void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; scm->fp = UNIXCB(skb).fp; UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) unix_notinflight(scm->fp->user, scm->fp->fp[i]); } EXPORT_SYMBOL(unix_detach_fds); void unix_destruct_scm(struct sk_buff *skb) { struct scm_cookie scm; memset(&scm, 0, sizeof(scm)); scm.pid = UNIXCB(skb).pid; if (UNIXCB(skb).fp) unix_detach_fds(&scm, skb); /* Alas, it calls VFS */ /* So fscking what? fput() had been SMP-safe since the last Summer */ scm_destroy(&scm); sock_wfree(skb); } EXPORT_SYMBOL(unix_destruct_scm); |
| 4578 4580 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM workqueue #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WORKQUEUE_H #include <linux/tracepoint.h> #include <linux/workqueue.h> struct pool_workqueue; /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a * delayed work is actually queued on a workqueue (ie: once the delay * has been reached). */ TRACE_EVENT(workqueue_queue_work, TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) __field( unsigned int, req_cpu ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __assign_str(workqueue, pwq->wq->name); __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); /** * workqueue_activate_work - called when a work gets activated * @work: pointer to struct work_struct * * This event occurs when a queued work is put on the active queue, * which happens immediately after queueing unless @max_active limit * is reached. */ TRACE_EVENT(workqueue_activate_work, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) ), TP_fast_assign( __entry->work = work; ), TP_printk("work struct %p", __entry->work) ); /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_end, TP_PROTO(struct work_struct *work, work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); #endif /* _TRACE_WORKQUEUE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 4 4 4 4 4 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CCM: Counter with CBC-MAC * * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com> */ #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> struct ccm_instance_ctx { struct crypto_skcipher_spawn ctr; struct crypto_ahash_spawn mac; }; struct crypto_ccm_ctx { struct crypto_ahash *mac; struct crypto_skcipher *ctr; }; struct crypto_rfc4309_ctx { struct crypto_aead *child; u8 nonce[3]; }; struct crypto_rfc4309_req_ctx { struct scatterlist src[3]; struct scatterlist dst[3]; struct aead_request subreq; }; struct crypto_ccm_req_priv_ctx { u8 odata[16]; u8 idata[16]; u8 auth_tag[16]; u32 flags; struct scatterlist src[3]; struct scatterlist dst[3]; union { struct ahash_request ahreq; struct skcipher_request skreq; }; }; struct cbcmac_tfm_ctx { struct crypto_cipher *child; }; struct cbcmac_desc_ctx { unsigned int len; }; static inline struct crypto_ccm_req_priv_ctx *crypto_ccm_reqctx( struct aead_request *req) { unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req)); return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1); } static int set_msg_len(u8 *block, unsigned int msglen, int csize) { __be32 data; memset(block, 0, csize); block += csize; if (csize >= 4) csize = 4; else if (msglen > (1 << (8 * csize))) return -EOVERFLOW; data = cpu_to_be32(msglen); memcpy(block - csize, (u8 *)&data + 4 - csize, csize); return 0; } static int crypto_ccm_setkey(struct crypto_aead *aead, const u8 *key, unsigned int keylen) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_skcipher *ctr = ctx->ctr; struct crypto_ahash *mac = ctx->mac; int err; crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); err = crypto_skcipher_setkey(ctr, key, keylen); if (err) return err; crypto_ahash_clear_flags(mac, CRYPTO_TFM_REQ_MASK); crypto_ahash_set_flags(mac, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); return crypto_ahash_setkey(mac, key, keylen); } static int crypto_ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) { switch (authsize) { case 4: case 6: case 8: case 10: case 12: case 14: case 16: break; default: return -EINVAL; } return 0; } static int format_input(u8 *info, struct aead_request *req, unsigned int cryptlen) { struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int lp = req->iv[0]; unsigned int l = lp + 1; unsigned int m; m = crypto_aead_authsize(aead); memcpy(info, req->iv, 16); /* format control info per RFC 3610 and * NIST Special Publication 800-38C */ *info |= (8 * ((m - 2) / 2)); if (req->assoclen) *info |= 64; return set_msg_len(info + 16 - l, cryptlen, l); } static int format_adata(u8 *adata, unsigned int a) { int len = 0; /* add control info for associated data * RFC 3610 and NIST Special Publication 800-38C */ if (a < 65280) { *(__be16 *)adata = cpu_to_be16(a); len = 2; } else { *(__be16 *)adata = cpu_to_be16(0xfffe); *(__be32 *)&adata[2] = cpu_to_be32(a); len = 6; } return len; } static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain, unsigned int cryptlen) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct ahash_request *ahreq = &pctx->ahreq; unsigned int assoclen = req->assoclen; struct scatterlist sg[3]; u8 *odata = pctx->odata; u8 *idata = pctx->idata; int ilen, err; /* format control data for input */ err = format_input(odata, req, cryptlen); if (err) goto out; sg_init_table(sg, 3); sg_set_buf(&sg[0], odata, 16); /* format associated data and compute into mac */ if (assoclen) { ilen = format_adata(idata, assoclen); sg_set_buf(&sg[1], idata, ilen); sg_chain(sg, 3, req->src); } else { ilen = 0; sg_chain(sg, 2, req->src); } ahash_request_set_tfm(ahreq, ctx->mac); ahash_request_set_callback(ahreq, pctx->flags, NULL, NULL); ahash_request_set_crypt(ahreq, sg, NULL, assoclen + ilen + 16); err = crypto_ahash_init(ahreq); if (err) goto out; err = crypto_ahash_update(ahreq); if (err) goto out; /* we need to pad the MAC input to a round multiple of the block size */ ilen = 16 - (assoclen + ilen) % 16; if (ilen < 16) { memset(idata, 0, ilen); sg_init_table(sg, 2); sg_set_buf(&sg[0], idata, ilen); if (plain) sg_chain(sg, 2, plain); plain = sg; cryptlen += ilen; } ahash_request_set_crypt(ahreq, plain, pctx->odata, cryptlen); err = crypto_ahash_finup(ahreq); out: return err; } static void crypto_ccm_encrypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); u8 *odata = pctx->odata; if (!err) scatterwalk_map_and_copy(odata, req->dst, req->assoclen + req->cryptlen, crypto_aead_authsize(aead), 1); aead_request_complete(req, err); } static inline int crypto_ccm_check_iv(const u8 *iv) { /* 2 <= L <= 8, so 1 <= L' <= 7. */ if (1 > iv[0] || iv[0] > 7) return -EINVAL; return 0; } static int crypto_ccm_init_crypt(struct aead_request *req, u8 *tag) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct scatterlist *sg; u8 *iv = req->iv; int err; err = crypto_ccm_check_iv(iv); if (err) return err; pctx->flags = aead_request_flags(req); /* Note: rfc 3610 and NIST 800-38C require counter of * zero to encrypt auth tag. */ memset(iv + 15 - iv[0], 0, iv[0] + 1); sg_init_table(pctx->src, 3); sg_set_buf(pctx->src, tag, 16); sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen); if (sg != pctx->src + 1) sg_chain(pctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(pctx->dst, 3); sg_set_buf(pctx->dst, tag, 16); sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen); if (sg != pctx->dst + 1) sg_chain(pctx->dst, 2, sg); } return 0; } static int crypto_ccm_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int cryptlen = req->cryptlen; u8 *odata = pctx->odata; u8 *iv = req->iv; int err; err = crypto_ccm_init_crypt(req, odata); if (err) return err; err = crypto_ccm_auth(req, sg_next(pctx->src), cryptlen); if (err) return err; dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_encrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_encrypt(skreq); if (err) return err; /* copy authtag to end of dst */ scatterwalk_map_and_copy(odata, sg_next(dst), cryptlen, crypto_aead_authsize(aead), 1); return err; } static void crypto_ccm_decrypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen - authsize; struct scatterlist *dst; pctx->flags = 0; dst = sg_next(req->src == req->dst ? pctx->src : pctx->dst); if (!err) { err = crypto_ccm_auth(req, dst, cryptlen); if (!err && crypto_memneq(pctx->auth_tag, pctx->odata, authsize)) err = -EBADMSG; } aead_request_complete(req, err); } static int crypto_ccm_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen; u8 *authtag = pctx->auth_tag; u8 *odata = pctx->odata; u8 *iv = pctx->idata; int err; cryptlen -= authsize; err = crypto_ccm_init_crypt(req, authtag); if (err) return err; scatterwalk_map_and_copy(authtag, sg_next(pctx->src), cryptlen, authsize, 0); dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; memcpy(iv, req->iv, 16); skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_decrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_decrypt(skreq); if (err) return err; err = crypto_ccm_auth(req, sg_next(dst), cryptlen); if (err) return err; /* verify */ if (crypto_memneq(authtag, odata, authsize)) return -EBADMSG; return err; } static int crypto_ccm_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct ccm_instance_ctx *ictx = aead_instance_ctx(inst); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_ahash *mac; struct crypto_skcipher *ctr; unsigned long align; int err; mac = crypto_spawn_ahash(&ictx->mac); if (IS_ERR(mac)) return PTR_ERR(mac); ctr = crypto_spawn_skcipher(&ictx->ctr); err = PTR_ERR(ctr); if (IS_ERR(ctr)) goto err_free_mac; ctx->mac = mac; ctx->ctr = ctr; align = crypto_aead_alignmask(tfm); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, align + sizeof(struct crypto_ccm_req_priv_ctx) + max(crypto_ahash_reqsize(mac), crypto_skcipher_reqsize(ctr))); return 0; err_free_mac: crypto_free_ahash(mac); return err; } static void crypto_ccm_exit_tfm(struct crypto_aead *tfm) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_ahash(ctx->mac); crypto_free_skcipher(ctx->ctr); } static void crypto_ccm_free(struct aead_instance *inst) { struct ccm_instance_ctx *ctx = aead_instance_ctx(inst); crypto_drop_ahash(&ctx->mac); crypto_drop_skcipher(&ctx->ctr); kfree(inst); } static int crypto_ccm_create_common(struct crypto_template *tmpl, struct rtattr **tb, const char *ctr_name, const char *mac_name) { u32 mask; struct aead_instance *inst; struct ccm_instance_ctx *ictx; struct skcipher_alg *ctr; struct hash_alg_common *mac; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL); if (!inst) return -ENOMEM; ictx = aead_instance_ctx(inst); err = crypto_grab_ahash(&ictx->mac, aead_crypto_instance(inst), mac_name, 0, mask | CRYPTO_ALG_ASYNC); if (err) goto err_free_inst; mac = crypto_spawn_ahash_alg(&ictx->mac); err = -EINVAL; if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 || mac->digestsize != 16) goto err_free_inst; err = crypto_grab_skcipher(&ictx->ctr, aead_crypto_instance(inst), ctr_name, 0, mask); if (err) goto err_free_inst; ctr = crypto_spawn_skcipher_alg(&ictx->ctr); /* The skcipher algorithm must be CTR mode, using 16-byte blocks. */ err = -EINVAL; if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 || crypto_skcipher_alg_ivsize(ctr) != 16 || ctr->base.cra_blocksize != 1) goto err_free_inst; /* ctr and cbcmac must use the same underlying block cipher. */ if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)", ctr->base.cra_driver_name, mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = (mac->base.cra_priority + ctr->base.cra_priority) / 2; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = mac->base.cra_alignmask | ctr->base.cra_alignmask; inst->alg.ivsize = 16; inst->alg.chunksize = crypto_skcipher_alg_chunksize(ctr); inst->alg.maxauthsize = 16; inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx); inst->alg.init = crypto_ccm_init_tfm; inst->alg.exit = crypto_ccm_exit_tfm; inst->alg.setkey = crypto_ccm_setkey; inst->alg.setauthsize = crypto_ccm_setauthsize; inst->alg.encrypt = crypto_ccm_encrypt; inst->alg.decrypt = crypto_ccm_decrypt; inst->free = crypto_ccm_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_ccm_free(inst); } return err; } static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *cipher_name; char ctr_name[CRYPTO_MAX_ALG_NAME]; char mac_name[CRYPTO_MAX_ALG_NAME]; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) return PTR_ERR(cipher_name); if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; if (snprintf(mac_name, CRYPTO_MAX_ALG_NAME, "cbcmac(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_ccm_base_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *ctr_name; const char *mac_name; ctr_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(ctr_name)) return PTR_ERR(ctr_name); mac_name = crypto_attr_alg_name(tb[2]); if (IS_ERR(mac_name)) return PTR_ERR(mac_name); return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_rfc4309_setkey(struct crypto_aead *parent, const u8 *key, unsigned int keylen) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); struct crypto_aead *child = ctx->child; if (keylen < 3) return -EINVAL; keylen -= 3; memcpy(ctx->nonce, key + keylen, 3); crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_aead_set_flags(child, crypto_aead_get_flags(parent) & CRYPTO_TFM_REQ_MASK); return crypto_aead_setkey(child, key, keylen); } static int crypto_rfc4309_setauthsize(struct crypto_aead *parent, unsigned int authsize) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); switch (authsize) { case 8: case 12: case 16: break; default: return -EINVAL; } return crypto_aead_setauthsize(ctx->child, authsize); } static struct aead_request *crypto_rfc4309_crypt(struct aead_request *req) { struct crypto_rfc4309_req_ctx *rctx = aead_request_ctx(req); struct aead_request *subreq = &rctx->subreq; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(aead); struct crypto_aead *child = ctx->child; struct scatterlist *sg; u8 *iv = PTR_ALIGN((u8 *)(subreq + 1) + crypto_aead_reqsize(child), crypto_aead_alignmask(child) + 1); /* L' */ iv[0] = 3; memcpy(iv + 1, ctx->nonce, 3); memcpy(iv + 4, req->iv, 8); scatterwalk_map_and_copy(iv + 16, req->src, 0, req->assoclen - 8, 0); sg_init_table(rctx->src, 3); sg_set_buf(rctx->src, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->src + 1, req->src, req->assoclen); if (sg != rctx->src + 1) sg_chain(rctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(rctx->dst, 3); sg_set_buf(rctx->dst, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->dst + 1, req->dst, req->assoclen); if (sg != rctx->dst + 1) sg_chain(rctx->dst, 2, sg); } aead_request_set_tfm(subreq, child); aead_request_set_callback(subreq, req->base.flags, req->base.complete, req->base.data); aead_request_set_crypt(subreq, rctx->src, req->src == req->dst ? rctx->src : rctx->dst, req->cryptlen, iv); aead_request_set_ad(subreq, req->assoclen - 8); return subreq; } static int crypto_rfc4309_encrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_encrypt(req); } static int crypto_rfc4309_decrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_decrypt(req); } static int crypto_rfc4309_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct crypto_aead_spawn *spawn = aead_instance_ctx(inst); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *aead; unsigned long align; aead = crypto_spawn_aead(spawn); if (IS_ERR(aead)) return PTR_ERR(aead); ctx->child = aead; align = crypto_aead_alignmask(aead); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, sizeof(struct crypto_rfc4309_req_ctx) + ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) + align + 32); return 0; } static void crypto_rfc4309_exit_tfm(struct crypto_aead *tfm) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_aead(ctx->child); } static void crypto_rfc4309_free(struct aead_instance *inst) { crypto_drop_aead(aead_instance_ctx(inst)); kfree(inst); } static int crypto_rfc4309_create(struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; struct aead_instance *inst; struct crypto_aead_spawn *spawn; struct aead_alg *alg; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = aead_instance_ctx(inst); err = crypto_grab_aead(spawn, aead_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_aead_alg(spawn); err = -EINVAL; /* We only support 16-byte blocks. */ if (crypto_aead_alg_ivsize(alg) != 16) goto err_free_inst; /* Not a stream cipher? */ if (alg->base.cra_blocksize != 1) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME || snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = alg->base.cra_priority; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = alg->base.cra_alignmask; inst->alg.ivsize = 8; inst->alg.chunksize = crypto_aead_alg_chunksize(alg); inst->alg.maxauthsize = 16; inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx); inst->alg.init = crypto_rfc4309_init_tfm; inst->alg.exit = crypto_rfc4309_exit_tfm; inst->alg.setkey = crypto_rfc4309_setkey; inst->alg.setauthsize = crypto_rfc4309_setauthsize; inst->alg.encrypt = crypto_rfc4309_encrypt; inst->alg.decrypt = crypto_rfc4309_decrypt; inst->free = crypto_rfc4309_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_rfc4309_free(inst); } return err; } static int crypto_cbcmac_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct cbcmac_tfm_ctx *ctx = crypto_shash_ctx(parent); return crypto_cipher_setkey(ctx->child, inkey, keylen); } static int crypto_cbcmac_digest_init(struct shash_desc *pdesc) { struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); int bs = crypto_shash_digestsize(pdesc->tfm); u8 *dg = (u8 *)ctx + crypto_shash_descsize(pdesc->tfm) - bs; ctx->len = 0; memset(dg, 0, bs); return 0; } static int crypto_cbcmac_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); u8 *dg = (u8 *)ctx + crypto_shash_descsize(parent) - bs; while (len > 0) { unsigned int l = min(len, bs - ctx->len); crypto_xor(dg + ctx->len, p, l); ctx->len +=l; len -= l; p += l; if (ctx->len == bs) { crypto_cipher_encrypt_one(tfm, dg, dg); ctx->len = 0; } } return 0; } static int crypto_cbcmac_digest_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); u8 *dg = (u8 *)ctx + crypto_shash_descsize(parent) - bs; if (ctx->len) crypto_cipher_encrypt_one(tfm, dg, dg); memcpy(out, dg, bs); return 0; } static int cbcmac_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 cbcmac_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 cbcmac_exit_tfm(struct crypto_tfm *tfm) { struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm); crypto_free_cipher(ctx->child); } static int cbcmac_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 = 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 = 1; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = ALIGN(sizeof(struct cbcmac_desc_ctx), alg->cra_alignmask + 1) + alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct cbcmac_tfm_ctx); inst->alg.base.cra_init = cbcmac_init_tfm; inst->alg.base.cra_exit = cbcmac_exit_tfm; inst->alg.init = crypto_cbcmac_digest_init; inst->alg.update = crypto_cbcmac_digest_update; inst->alg.final = crypto_cbcmac_digest_final; inst->alg.setkey = crypto_cbcmac_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_ccm_tmpls[] = { { .name = "cbcmac", .create = cbcmac_create, .module = THIS_MODULE, }, { .name = "ccm_base", .create = crypto_ccm_base_create, .module = THIS_MODULE, }, { .name = "ccm", .create = crypto_ccm_create, .module = THIS_MODULE, }, { .name = "rfc4309", .create = crypto_rfc4309_create, .module = THIS_MODULE, }, }; static int __init crypto_ccm_module_init(void) { return crypto_register_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } static void __exit crypto_ccm_module_exit(void) { crypto_unregister_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } subsys_initcall(crypto_ccm_module_init); module_exit(crypto_ccm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Counter with CBC MAC"); MODULE_ALIAS_CRYPTO("ccm_base"); MODULE_ALIAS_CRYPTO("rfc4309"); MODULE_ALIAS_CRYPTO("ccm"); MODULE_ALIAS_CRYPTO("cbcmac"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); |
| 7 3264 1826 803 847 266 3 234 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long expires, unsigned int flags), TP_ARGS(timer, expires, flags), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = expires; __entry->now = jiffies; __entry->flags = flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 46 46 46 46 46 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. * * Changes: * Paul `Rusty' Russell properly handle non-linear skbs * Harald Welte don't use nfcache */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/gue.h> #include <net/gre.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip6_route.h> #endif #include <net/ip_vs.h> #include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); EXPORT_SYMBOL(unregister_ip_vs_scheduler); EXPORT_SYMBOL(ip_vs_proto_name); EXPORT_SYMBOL(ip_vs_conn_new); EXPORT_SYMBOL(ip_vs_conn_in_get); EXPORT_SYMBOL(ip_vs_conn_out_get); #ifdef CONFIG_IP_VS_PROTO_TCP EXPORT_SYMBOL(ip_vs_tcp_conn_listen); #endif EXPORT_SYMBOL(ip_vs_conn_put); #ifdef CONFIG_IP_VS_DEBUG EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_TCP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) #else #define SNAT_CALL(f, ...) f(__VA_ARGS__) #endif static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; switch (proto) { case IPPROTO_IP: return "IP"; case IPPROTO_UDP: return "UDP"; case IPPROTO_TCP: return "TCP"; case IPPROTO_SCTP: return "SCTP"; case IPPROTO_ICMP: return "ICMP"; #ifdef CONFIG_IP_VS_IPV6 case IPPROTO_ICMPV6: return "ICMPv6"; #endif default: sprintf(buf, "IP_%u", proto); return buf; } } void ip_vs_init_hash_table(struct list_head *table, int rows) { while (--rows >= 0) INIT_LIST_HEAD(&table[rows]); } static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; local_bh_disable(); s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); local_bh_enable(); } static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (likely(pd->pp->state_transition)) pd->pp->state_transition(cp, direction, skb, pd); } static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) return p->pe->fill_param(p, skb); return 0; } /* * IPVS persistent scheduling function * It creates a connection entry according to its template if exists, * or selects a server and creates a connection entry plus a template. * Locking: we are svc user (svc->refcnt), so we hold all dests too * Protocols supported: TCP, UDP */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, __be16 src_port, __be16 dst_port, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ const union nf_inet_addr *src_addr, *dst_addr; if (likely(!ip_vs_iph_inverse(iph))) { src_addr = &iph->saddr; dst_addr = &iph->daddr; } else { src_addr = &iph->daddr; dst_addr = &iph->saddr; } /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and * it uses control connection and data connections. For active FTP, * FTP server initialize data connection to the client, its source port * is often 20. For passive FTP, FTP server tells the clients the port * that it passively listens to, and the client issues the data * connection. In the tunneling or direct routing mode, the load * balancer is on the client-to-server half of connection, the port * number is unknown to the load balancer. So, a conn template like * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP * service, and a template like <caddr, 0, vaddr, vport, daddr, dport> * is created for other persistent services. */ { int protocol = iph->protocol; const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. * fwmark template: * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: * <protocol,caddr,0,vaddr,0,daddr,0> */ if (svc->fwmark) { protocol = IPPROTO_IP; vaddr = &fwmark; } } /* return *ignored = -1 so NF_DROP can be used */ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, vaddr, vport, ¶m) < 0) { *ignored = -1; return NULL; } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct, NULL)) { struct ip_vs_scheduler *sched; /* * No template found or the dest of the connection * template is not available. * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); *ignored = 0; return NULL; } if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template * This adds param.pe_data to the template, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); *ignored = -1; return NULL; } ct->timeout = svc->timeout; } else { /* set destination with the found template */ dest = ct->dest; kfree(param.pe_data); } dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); *ignored = -1; return NULL; } /* * Add its control */ ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); ip_vs_conn_stats(cp, svc); return cp; } /* * IPVS main scheduling function * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP * * Usage of *ignored * * 1 : protocol tried to schedule (eg. on SYN), found svc but the * svc/scheduler decides that this packet should be accepted with * NF_ACCEPT because it must not be scheduled. * * 0 : scheduler can not find destination, so try bypass or * return ICMP and then NF_DROP (ip_vs_leave). * * -1 : scheduler tried to schedule but fatal error occurred, eg. * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param * failure such as missing Call-ID, ENOMEM on skb_linearize * or pe_data. In this case we should return NF_DROP without * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; __be16 _ports[2], *pptr, cport, vport; const void *caddr, *vaddr; unsigned int flags; *ignored = 1; /* * IPv6 frags, only the first hit here. */ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!ip_vs_iph_inverse(iph))) { cport = pptr[0]; caddr = &iph->saddr; vport = pptr[1]; vaddr = &iph->daddr; } else { cport = pptr[1]; caddr = &iph->daddr; vport = pptr[0]; vaddr = &iph->saddr; } /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ if (cport == FTPDATA) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } /* * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing" " connection"); __ip_vs_conn_put(cp); return NULL; } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; /* * Non-persistent service */ if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " "check your ipvs configuration\n"); return NULL; } sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a connection entry. */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; return NULL; } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; } static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } /* * Pass or drop the packet. * Called by ip_vs_in, when the virtual service is available but * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; struct netns_ipvs *ipvs = svc->ipvs; struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); if (!cp) return NF_DROP; } /* statistics */ ip_vs_in_stats(cp, skb); /* set state */ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) atomic_inc(&cp->control->in_pkts); else atomic_inc(&cp->in_pkts); ip_vs_conn_put(cp); return ret; } /* * When the virtual ftp service is presented, packets destined * for other services on the VIP may get here (except services * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; if (unlikely(ip_vs_iph_icmp(iph))) return NF_DROP; /* * Notify the client that the destination is unreachable, and * release the socket buffer. * Since it is in IP layer, the TCP socket is not actually * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { if (!skb->dev) skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } #ifdef CONFIG_SYSCTL static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return ipvs->sysctl_snat_reroute; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return ipvs->sysctl_nat_icmp_send; } #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) { if (NF_INET_LOCAL_IN == hooknum) return IP_DEFRAG_VS_IN; if (NF_INET_FORWARD == hooknum) return IP_DEFRAG_VS_FWD; return IP_DEFRAG_VS_OUT; } static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); return err; } static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, unsigned int hooknum) { if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; } /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct iphdr *iph = ip_hdr(skb); unsigned int icmp_offset = iph->ihl*4; struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + icmp_offset); struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } /* the TCP/UDP/SCTP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || IPPROTO_SCTP == ciph->protocol) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->checksum = 0; icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int icmp_offset = 0; unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; struct ipv6hdr *ciph; unsigned short fragoffs; ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); offs = icmp_offset + sizeof(struct icmp6hdr); ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; ciph->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; ciph->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol)) { __be16 *ports = (void *)(skb_network_header(skb) + offs); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, skb->len - icmp_offset, IPPROTO_ICMPV6, 0); skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMPv6"); else IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMPv6"); } #endif /* Handle relevant response ICMP messages - forward to the right * destination host. */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl, unsigned int hooknum) { unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); else #endif ip_vs_nat_icmp(skb, pp, cp, 1); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: __ip_vs_conn_put(cp); return verdict; } /* * Handle ICMP messages in the inside-to-outside direction (outgoing). * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; unsigned int offset, ihl; union nf_inet_addr snet; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); if (!pp) return NF_ACCEPT; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (ipvsh->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif /* * Check if sctp chunc is ABORT chunk */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) return 1; return 0; } static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } static inline bool is_new_conn(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { switch (iph->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) return false; return th->syn; } case IPPROTO_SCTP: { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; return sch->type == SCTP_CID_INIT; } default: return false; } } static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, int conn_reuse_mode) { /* Controlled (FTP DATA or persistence)? */ if (cp->control) return false; switch (cp->protocol) { case IPPROTO_TCP: return (cp->state == IP_VS_TCP_S_TIME_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || ((conn_reuse_mode & 2) && (cp->state == IP_VS_TCP_S_FIN_WAIT) && (cp->flags & IP_VS_CONN_F_NOOUTPUT)); case IPPROTO_SCTP: return cp->state == IP_VS_SCTP_S_CLOSED; default: return false; } } /* Generic function to create new connections for outgoing RS packets * * Pre-requisites for successful connection creation: * 1) Virtual Service is NOT fwmark based: * In fwmark-VS actual vaddr and vport are unknown to IPVS * 2) Real Server and Virtual Service were NOT configured without port: * This is to allow match of different VS to the same RS ip-addr */ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct sk_buff *skb, const struct ip_vs_iphdr *iph, __be16 dport, __be16 cport) { struct ip_vs_conn_param param; struct ip_vs_conn *ct = NULL, *cp = NULL; const union nf_inet_addr *vaddr, *daddr, *caddr; union nf_inet_addr snet; __be16 vport; unsigned int flags; EnterFunction(12); vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; caddr = &iph->daddr; /* check pre-requisites are satisfied */ if (svc->fwmark) return NULL; if (!vport || !dport) return NULL; /* for persistent service first create connection template */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) { /* apply netmask the same way ingress-side does */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &caddr->in6, (__force __u32)svc->netmask); else #endif snet.ip = caddr->ip & svc->netmask; /* fill params and create template if not existent */ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol, &snet, 0, vaddr, vport, ¶m) < 0) return NULL; ct = ip_vs_ct_in_get(¶m); /* check if template exists and points to the same dest */ if (!ct || !ip_vs_check_template(ct, dest)) { ct = ip_vs_conn_new(¶m, dest->af, daddr, dport, IP_VS_CONN_F_TEMPLATE, dest, 0); if (!ct) { kfree(param.pe_data); return NULL; } ct->timeout = svc->timeout; } else { kfree(param.pe_data); } } /* connection flags */ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* create connection */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, ¶m); cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0); if (!cp) { if (ct) ip_vs_conn_put(ct); return NULL; } if (ct) { ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); } ip_vs_conn_stats(cp, svc); /* return connection (will be used to handle outgoing packet) */ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); LeaveFunction(12); return cp; } /* Handle outgoing packets which are considered requests initiated by * real servers, so that subsequent responses from external client can be * routed to the right real server. * Used also for outgoing responses in OPS mode. * * Connection management is handled by persistent-engine specific callback. */ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum, struct netns_ipvs *ipvs, int af, struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_conn *cp = NULL; __be16 _ports[2], *pptr; if (hooknum == NF_INET_LOCAL_IN) return NULL; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NULL; dest = ip_vs_find_real_service(ipvs, af, iph->protocol, &iph->saddr, pptr[0]); if (dest) { struct ip_vs_service *svc; struct ip_vs_pe *pe; svc = rcu_dereference(dest->svc); if (svc) { pe = rcu_dereference(svc->pe); if (pe && pe->conn_out) cp = pe->conn_out(svc, dest, skb, iph, pptr[0], pptr[1]); } } return cp; } /* Handle response packets: rewrite addresses and send away... */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ if (pp->snat_handler && !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ipv6_hdr(skb)->saddr = cp->vaddr.in6; else #endif { ip_hdr(skb)->saddr = cp->vaddr.ip; ip_send_check(ip_hdr(skb)); } /* * nf_iterate does not expect change in the skb->dst->dev. * It looks like it is not fatal to enable this code for hooks * where our handlers are at the end of the chain list and * when all next handlers use skb->dst->dev and not outdev. * It will definitely route properly the inout NAT traffic * when multiple paths are used. */ /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); LeaveFunction(11); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); LeaveFunction(11); return NF_STOLEN; } /* * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; struct sock *sk; EnterFunction(11); /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } if (unlikely(!skb_dst(skb))) return NF_ACCEPT; if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { /* Currently only for UDP: * connection oriented protocols typically use * ephemeral ports for outgoing connections, so * related incoming responses would not match any VS */ if (pp->protocol == IPPROTO_UDP) { cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); } } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no * existing entry if it is not RST * packet or not TCP packet. */ if ((iph.protocol != IPPROTO_TCP && iph.protocol != IPPROTO_SCTP) || ((iph.protocol == IPPROTO_TCP && !is_tcp_reset(skb, iph.len)) || (iph.protocol == IPPROTO_SCTP && !is_sctp_abort(skb, iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } } } IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; if (!iph->fragoffs) { /* No (second) fragments need to enter here, as nf_defrag_ipv6 * replayed fragment zero will already have created the cp */ /* Schedule and create new connection entry into cpp */ if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } if (unlikely(!*cpp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); /* Fragment couldn't be mapped to a conn entry */ if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); *verdict = NF_ACCEPT; return 0; } return 1; } /* Check the UDP tunnel and return its header length */ static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct udphdr _udph, *udph; struct ip_vs_dest *dest; udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (!udph) goto unk; offset += sizeof(struct udphdr); dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { struct guehdr _gueh, *gueh; gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); if (!gueh) goto unk; if (gueh->control != 0 || gueh->version != 0) goto unk; /* Later we can support also IPPROTO_IPV6 */ if (gueh->proto_ctype != IPPROTO_IPIP) goto unk; *proto = gueh->proto_ctype; return sizeof(struct udphdr) + sizeof(struct guehdr) + (gueh->hlen << 2); } unk: return 0; } /* Check the GRE tunnel and return its header length */ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct gre_base_hdr _greh, *greh; struct ip_vs_dest *dest; greh = skb_header_pointer(skb, offset, sizeof(_greh), &_greh); if (!greh) goto unk; dest = ip_vs_find_tunnel(ipvs, af, daddr, 0); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { __be16 type; /* Only support version 0 and C (csum) */ if ((greh->flags & ~GRE_CSUM) != 0) goto unk; type = greh->protocol; /* Later we can support also IPPROTO_IPV6 */ if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); } unk: return 0; } /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, * forward to the right destination host if relevant. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; if (cih->protocol == IPPROTO_IPIP) { struct ip_vs_dest *dest; if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; offset2 = offset + cih->ihl * 4; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "UDP"; } else { ulen = ipvs_gre_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "GRE"; } if (ulen > 0) { /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih && cih->version == 4 && cih->ihl >= 5 && iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) { int v; if (tunnel || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } verdict = NF_DROP; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); goto out; } if (tunnel) { __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP/UDP/GRE header */ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) goto ignore_tunnel; /* Prefer the resulting PMTU */ if (dest) { struct ip_vs_dest_dst *dest_dst; dest_dst = rcu_dereference(dest->dest_dst); if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } if (mtu > 68 + sizeof(struct iphdr)) mtu -= sizeof(struct iphdr); info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of * original request. */ if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); ignore_tunnel: consume_skb(skb); verdict = NF_STOLEN; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; bool new_cp = false; *related = 1; ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (iph->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Cannot handle fragmented embedded protocol */ if (ciph.fragoffs) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { verdict = NF_ACCEPT; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #endif /* * Check if it's for virtual services, look it up, * and send it on its way... */ static unsigned int ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; /* * Big tappo: * - remote client: only PACKET_HOST * - route: used for struct net when skb->dev is unset */ if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ sk = skb_to_full_sk(skb); if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } /* Protocol supported? */ pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we * skip it if we're ignoring tunneled packets */ if (sysctl_ignore_tunneled(ipvs)) skb->ipvs_property = 1; return NF_ACCEPT; } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (conn_reuse_mode && is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { /* Do not reschedule controlling connection * that uses conntrack while it is still * referenced by controlled connection(s). */ resched = !old_ct; } } if (resched) { if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } } /* Check the server status */ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } else { __ip_vs_conn_put(cp); return NF_DROP; } } if (unlikely(!cp)) { int v; if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); ret = NF_ACCEPT; } /* Increase its packet counter and check if it is needed * to be synchronized * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout * * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_inc_return(&cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, pkts); else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) /* increment is done inside ip_vs_sync_conn too */ atomic_inc(&cp->control->in_pkts); ip_vs_conn_put(cp); return ret; } /* * AF_INET handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * AF_INET handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * AF_INET6 handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent * cache cluster, TCP packets can be marked and routed to ip_vs_in, * but ICMP destined for 0.0.0.0/0 cannot not be easily marked and * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain * and send them to ip_vs_in_icmp. */ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); } #endif static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #ifdef CONFIG_IP_VS_IPV6 static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp_v6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #endif int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; int ret = 0; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return -EINVAL; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (!(ipvs->hooks_afmask & afmask)) { ret = nf_register_net_hooks(ipvs->net, ops, count); if (ret >= 0) ipvs->hooks_afmask |= afmask; } return ret; } void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (ipvs->hooks_afmask & afmask) { nf_unregister_net_hooks(ipvs->net, ops, count); ipvs->hooks_afmask &= ~afmask; } } /* * Initialize IP Virtual Server netns mem. */ static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) return -ENOMEM; /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; return 0; /* * Error handling */ sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; } static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */ list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } } static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; EnterFunction(2); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit_batch = __ip_vs_cleanup_batch, .id = &ip_vs_net_id, .size = sizeof(struct netns_ipvs), }; static struct pernet_operations ipvs_core_dev_ops = { .exit_batch = __ip_vs_dev_cleanup_batch, }; /* * Initialize IP Virtual Server */ static int __init ip_vs_init(void) { int ret; ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); goto exit; } ip_vs_protocol_init(); ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) goto cleanup_sub; ret = ip_vs_register_nl_ioctl(); if (ret < 0) { pr_err("can't register netlink/ioctl.\n"); goto cleanup_dev; } pr_info("ipvs loaded.\n"); return ret; cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); cleanup_conn: ip_vs_conn_cleanup(); cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); exit: return ret; } static void __exit ip_vs_cleanup(void) { ip_vs_unregister_nl_ioctl(); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); module_exit(ip_vs_cleanup); MODULE_LICENSE("GPL"); |
| 182 197 | 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 | /* * net/tipc/core.h: Include file for TIPC global declarations * * Copyright (c) 2005-2006, 2013-2018 Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems * Copyright (c) 2020, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. 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. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_CORE_H #define _TIPC_CORE_H #include <linux/tipc.h> #include <linux/tipc_config.h> #include <linux/tipc_netlink.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> #include <net/genetlink.h> #include <net/netns/hash.h> #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt struct tipc_node; struct tipc_bearer; struct tipc_bc_base; struct tipc_link; struct tipc_name_table; struct tipc_topsrv; struct tipc_monitor; #ifdef CONFIG_TIPC_CRYPTO struct tipc_crypto; #endif #define TIPC_MOD_VER "2.0.0" #define NODE_HTABLE_SIZE 512 #define MAX_BEARERS 3 #define TIPC_DEF_MON_THRESHOLD 32 #define NODE_ID_LEN 16 #define NODE_ID_STR_LEN (NODE_ID_LEN * 2 + 1) extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; u32 trial_addr; unsigned long addr_trial_end; char node_id_string[NODE_ID_STR_LEN]; int net_id; int random; bool legacy_addr_format; /* Node table and node list */ spinlock_t node_list_lock; struct hlist_head node_htable[NODE_HTABLE_SIZE]; struct list_head node_list; u32 num_nodes; u32 num_links; /* Neighbor monitoring list */ struct tipc_monitor *monitors[MAX_BEARERS]; int mon_threshold; /* Bearer list */ struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1]; /* Broadcast link */ spinlock_t bclock; struct tipc_bc_base *bcbase; struct tipc_link *bcl; /* Socket hash table */ struct rhashtable sk_rht; /* Name table */ spinlock_t nametbl_lock; struct name_table *nametbl; /* Topology subscription server */ struct tipc_topsrv *topsrv; atomic_t subscription_count; /* Cluster capabilities */ u16 capabilities; /* Tracing of node internal messages */ struct packet_type loopback_pt; #ifdef CONFIG_TIPC_CRYPTO /* TX crypto handler */ struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ struct work_struct work; /* The numbers of work queues in schedule */ atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) { return net_generic(net, tipc_net_id); } static inline int tipc_netid(struct net *net) { return tipc_net(net)->net_id; } static inline struct list_head *tipc_nodes(struct net *net) { return &tipc_net(net)->node_list; } static inline struct name_table *tipc_name_table(struct net *net) { return tipc_net(net)->nametbl; } static inline struct tipc_topsrv *tipc_topsrv(struct net *net) { return tipc_net(net)->topsrv; } static inline unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); } static inline u16 mod(u16 x) { return x & 0xffffu; } static inline int less_eq(u16 left, u16 right) { return mod(right - left) < 32768u; } static inline int more(u16 left, u16 right) { return !less_eq(left, right); } static inline int less(u16 left, u16 right) { return less_eq(left, right) && (mod(right) != mod(left)); } static inline int in_range(u16 val, u16 min, u16 max) { return !less(val, min) && !more(val, max); } static inline u32 tipc_net_hash_mixes(struct net *net, int tn_rand) { return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand; } static inline u32 hash128to32(char *bytes) { __be32 *tmp = (__be32 *)bytes; u32 res; res = ntohl(tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]); if (likely(res)) return res; return ntohl(tmp[0] | tmp[1] | tmp[2] | tmp[3]); } #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); #else #define tipc_register_sysctl() 0 #define tipc_unregister_sysctl() #endif #endif |
| 9 104 16 95 102 1 101 100 1 99 1 1 98 100 99 1 1 101 100 7 3 3 1 7 4 103 104 159 160 160 160 1 160 102 103 160 159 160 158 115 91 160 7 3 103 94 140 73 118 80 103 79 63 10 150 2 147 1 3 147 115 1 73 30 11 13 10 18 2 166 1 120 121 5 102 13 112 187 6 182 186 165 161 159 101 103 1 4 19 3 3 3 2 1 160 160 159 158 11 160 161 6 80 119 136 61 153 1 102 13 75 68 46 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2002-2013 Jozsef Kadlecsik <kadlec@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ static const char *const tcp_conntrack_names[] = { "NONE", "SYN_SENT", "SYN_RECV", "ESTABLISHED", "FIN_WAIT", "CLOSE_WAIT", "LAST_ACK", "TIME_WAIT", "CLOSE", "SYN_SENT2", }; #define SECS * HZ #define MINS * 60 SECS #define HOURS * 60 MINS #define DAYS * 24 HOURS static const unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] = { [TCP_CONNTRACK_SYN_SENT] = 2 MINS, [TCP_CONNTRACK_SYN_RECV] = 60 SECS, [TCP_CONNTRACK_ESTABLISHED] = 5 DAYS, [TCP_CONNTRACK_FIN_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE_WAIT] = 60 SECS, [TCP_CONNTRACK_LAST_ACK] = 30 SECS, [TCP_CONNTRACK_TIME_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE] = 10 SECS, [TCP_CONNTRACK_SYN_SENT2] = 2 MINS, /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ [TCP_CONNTRACK_RETRANS] = 5 MINS, [TCP_CONNTRACK_UNACK] = 5 MINS, }; #define sNO TCP_CONNTRACK_NONE #define sSS TCP_CONNTRACK_SYN_SENT #define sSR TCP_CONNTRACK_SYN_RECV #define sES TCP_CONNTRACK_ESTABLISHED #define sFW TCP_CONNTRACK_FIN_WAIT #define sCW TCP_CONNTRACK_CLOSE_WAIT #define sLA TCP_CONNTRACK_LAST_ACK #define sTW TCP_CONNTRACK_TIME_WAIT #define sCL TCP_CONNTRACK_CLOSE #define sS2 TCP_CONNTRACK_SYN_SENT2 #define sIV TCP_CONNTRACK_MAX #define sIG TCP_CONNTRACK_IGNORE /* What TCP flags are set from RST/SYN/FIN/ACK. */ enum tcp_bit_set { TCP_SYN_SET, TCP_SYNACK_SET, TCP_FIN_SET, TCP_ACK_SET, TCP_RST_SET, TCP_NONE_SET, }; /* * The TCP state transition table needs a few words... * * We are the man in the middle. All the packets go through us * but might get lost in transit to the destination. * It is assumed that the destinations can't receive segments * we haven't seen. * * The checked segment is in window, but our windows are *not* * equivalent with the ones of the sender/receiver. We always * try to guess the state of the current sender. * * The meaning of the states are: * * NONE: initial state * SYN_SENT: SYN-only packet seen * SYN_SENT2: SYN-only packet seen from reply dir, simultaneous open * SYN_RECV: SYN-ACK packet seen * ESTABLISHED: ACK packet seen * FIN_WAIT: FIN packet seen * CLOSE_WAIT: ACK seen (after FIN) * LAST_ACK: FIN seen (after FIN) * TIME_WAIT: last ACK seen * CLOSE: closed connection (RST) * * Packets marked as IGNORED (sIG): * if they may be either invalid or valid * and the receiver may send back a connection * closing RST or a SYN/ACK. * * Packets marked as INVALID (sIV): * if we regard them as truly invalid packets */ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 }, /* * sNO -> sSS Initialize a new connection * sSS -> sSS Retransmitted SYN * sS2 -> sS2 Late retransmitted SYN * sSR -> sIG * sES -> sIG Error: SYNs in window outside the SYN_SENT state * are errors. Receiver will reply with RST * and close the connection. * Or we are not in sync and hold a dead connection. * sFW -> sIG * sCW -> sIG * sLA -> sIG * sTW -> sSS Reopened connection (RFC 1122). * sCL -> sSS */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*synack*/ { sIV, sIV, sSR, sIV, sIV, sIV, sIV, sIV, sIV, sSR }, /* * sNO -> sIV Too late and no reason to do anything * sSS -> sIV Client can't send SYN and then SYN/ACK * sS2 -> sSR SYN/ACK sent to SYN2 in simultaneous open * sSR -> sSR Late retransmitted SYN/ACK in simultaneous open * sES -> sIV Invalid SYN/ACK packets sent by the client * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sIV * sCL -> sIV */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sNO -> sIV Too late and no reason to do anything... * sSS -> sIV Client migth not send FIN in this state: * we enforce waiting for a SYN/ACK reply first. * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions, waiting for * the last ACK. * Migth be a retransmitted FIN as well... * sCW -> sLA * sLA -> sLA Retransmitted FIN. Remain in the same state. * sTW -> sTW * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV }, /* * sNO -> sES Assumed. * sSS -> sIV ACK is invalid: we haven't seen a SYN/ACK yet. * sS2 -> sIV * sSR -> sES Established state is reached. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } }, { /* REPLY */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sSS, sIV, sS2 }, /* * sNO -> sIV Never reached. * sSS -> sS2 Simultaneous open * sS2 -> sS2 Retransmitted simultaneous SYN * sSR -> sIV Invalid SYN packets sent by the server * sES -> sIV * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sSS Reopened connection, but server may have switched role * sCL -> sIV */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*synack*/ { sIV, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* * sSS -> sSR Standard open. * sS2 -> sSR Simultaneous open * sSR -> sIG Retransmitted SYN/ACK, ignore it. * sES -> sIG Late retransmitted SYN/ACK? * sFW -> sIG Might be SYN/ACK answering ignored SYN * sCW -> sIG * sLA -> sIG * sTW -> sIG * sCL -> sIG */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sSS -> sIV Server might not send FIN in this state. * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions. * sCW -> sLA * sLA -> sLA Retransmitted FIN. * sTW -> sTW * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG }, /* * sSS -> sIG Might be a half-open connection. * sS2 -> sIG * sSR -> sSR Might answer late resent SYN. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ /* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } } }; #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) return; seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]); } #endif static unsigned int get_conntrack_index(const struct tcphdr *tcph) { if (tcph->rst) return TCP_RST_SET; else if (tcph->syn) return (tcph->ack ? TCP_SYNACK_SET : TCP_SYN_SET); else if (tcph->fin) return TCP_FIN_SET; else if (tcph->ack) return TCP_ACK_SET; else return TCP_NONE_SET; } /* TCP connection tracking based on 'Real Stateful TCP Packet Filtering in IP Filter' by Guido van Rooij. http://www.sane.nl/events/sane2000/papers.html http://www.darkart.com/mirrors/www.obfuscation.org/ipf/ The boundaries and the conditions are changed according to RFC793: the packet must intersect the window (i.e. segments may be after the right or before the left edge) and thus receivers may ACK segments after the right edge of the window. td_maxend = max(sack + max(win,1)) seen in reply packets td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets td_maxwin += seq + len - sender.td_maxend if seq + len > sender.td_maxend td_end = max(seq + len) seen in sent packets I. Upper bound for valid data: seq <= sender.td_maxend II. Lower bound for valid data: seq + len >= sender.td_end - receiver.td_maxwin III. Upper bound for valid (s)ack: sack <= receiver.td_end IV. Lower bound for valid (s)ack: sack >= receiver.td_end - MAXACKWINDOW where sack is the highest right edge of sack block found in the packet or ack in the case of packet without SACK option. The upper bound limit for a valid (s)ack is not ignored - we doesn't have to deal with fragments. */ static inline __u32 segment_seq_plus_len(__u32 seq, size_t len, unsigned int dataoff, const struct tcphdr *tcph) { /* XXX Should I use payload length field in IP/IPv6 header ? * - YK */ return (seq + len - dataoff - tcph->doff*4 + (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0)); } /* Fixme: what about big packets? */ #define MAXACKWINCONST 66000 #define MAXACKWINDOW(sender) \ ((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin \ : MAXACKWINCONST) /* * Simplified tcp_parse_options routine from tcp_input.c */ static void tcp_options(const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, struct ip_ct_tcp_state *state) { unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; const unsigned char *ptr; int length = (tcph->doff*4) - sizeof(struct tcphdr); if (!length) return; ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr), length, buff); if (!ptr) return; state->td_scale = 0; state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; while (length > 0) { int opcode=*ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: if (length < 2) return; opsize=*ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_SACK_PERM && opsize == TCPOLEN_SACK_PERM) state->flags |= IP_CT_TCP_FLAG_SACK_PERM; else if (opcode == TCPOPT_WINDOW && opsize == TCPOLEN_WINDOW) { state->td_scale = *(u_int8_t *)ptr; if (state->td_scale > TCP_MAX_WSCALE) state->td_scale = TCP_MAX_WSCALE; state->flags |= IP_CT_TCP_FLAG_WINDOW_SCALE; } ptr += opsize - 2; length -= opsize; } } } static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, __u32 *sack) { unsigned char buff[(15 * 4) - sizeof(struct tcphdr)]; const unsigned char *ptr; int length = (tcph->doff*4) - sizeof(struct tcphdr); __u32 tmp; if (!length) return; ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr), length, buff); if (!ptr) return; /* Fast path for timestamp-only option */ if (length == TCPOLEN_TSTAMP_ALIGNED && *(__be32 *)ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) return; while (length > 0) { int opcode = *ptr++; int opsize, i; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: if (length < 2) return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_SACK && opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK) && !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK)) { for (i = 0; i < (opsize - TCPOLEN_SACK_BASE); i += TCPOLEN_SACK_PERBLOCK) { tmp = get_unaligned_be32((__be32 *)(ptr+i)+1); if (after(tmp, *sack)) *sack = tmp; } return; } ptr += opsize - 2; length -= opsize; } } } static bool tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, const struct nf_hook_state *hook_state) { struct ip_ct_tcp *state = &ct->proto.tcp; struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; u16 win_raw; s32 receiver_offset; bool res, in_recv_win; /* * Get the required data from the packet. */ seq = ntohl(tcph->seq); ack = sack = ntohl(tcph->ack_seq); win_raw = ntohs(tcph->window); win = win_raw; end = segment_seq_plus_len(seq, skb->len, dataoff, tcph); if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ receiver_offset = nf_ct_seq_offset(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; pr_debug("tcp_in_window: START\n"); pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); if (sender->td_maxwin == 0) { /* * Initialize sender data. */ if (tcph->syn) { /* * SYN-ACK in reply to a SYN * or SYN from reply direction in simultaneous open. */ sender->td_end = sender->td_maxend = end; sender->td_maxwin = (win == 0 ? 1 : win); tcp_options(skb, dataoff, tcph, sender); /* * RFC 1323: * Both sides must send the Window Scale option * to enable window scaling in either direction. */ if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) sender->td_scale = receiver->td_scale = 0; if (!tcph->ack) /* Simultaneous open */ return true; } else { /* * We are in the middle of a connection, * its history is lost for us. * Let's try to use the data from the packet. */ sender->td_end = end; swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; if (receiver->td_maxwin == 0) { /* We haven't seen traffic in the other * direction yet but we have to tweak window * tracking to pass III and IV until that * happens. */ receiver->td_end = receiver->td_maxend = sack; } else if (sack == receiver->td_end + 1) { /* Likely a reply to a keepalive. * Needed for III. */ receiver->td_end++; } } } else if (((state->state == TCP_CONNTRACK_SYN_SENT && dir == IP_CT_DIR_ORIGINAL) || (state->state == TCP_CONNTRACK_SYN_RECV && dir == IP_CT_DIR_REPLY)) && after(end, sender->td_end)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." */ sender->td_end = sender->td_maxend = end; sender->td_maxwin = (win == 0 ? 1 : win); tcp_options(skb, dataoff, tcph, sender); } if (!(tcph->ack)) { /* * If there is no ACK, just pretend it was set and OK. */ ack = sack = receiver->td_end; } else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) == (TCP_FLAG_ACK|TCP_FLAG_RST)) && (ack == 0)) { /* * Broken TCP stacks, that set ACK in RST packets as well * with zero ack value. */ ack = sack = receiver->td_end; } if (tcph->rst && seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT) /* * RST sent answering SYN. */ seq = end = sender->td_end; pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); /* Is the ending sequence in the receive window (if available)? */ in_recv_win = !receiver->td_maxwin || after(end, sender->td_end - receiver->td_maxwin - 1); pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n", before(seq, sender->td_maxend + 1), (in_recv_win ? 1 : 0), before(sack, receiver->td_end + 1), after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)); if (before(seq, sender->td_maxend + 1) && in_recv_win && before(sack, receiver->td_end + 1) && after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) { /* * Take into account window scaling (RFC 1323). */ if (!tcph->syn) win <<= sender->td_scale; /* * Update sender data. */ swin = win + (sack - ack); if (sender->td_maxwin < swin) sender->td_maxwin = swin; if (after(end, sender->td_end)) { sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; } if (tcph->ack) { if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) { sender->td_maxack = ack; sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET; } else if (after(ack, sender->td_maxack)) sender->td_maxack = ack; } /* * Update receiver data. */ if (receiver->td_maxwin != 0 && after(end, sender->td_maxend)) receiver->td_maxwin += end - sender->td_maxend; if (after(sack + win, receiver->td_maxend - 1)) { receiver->td_maxend = sack + win; if (win == 0) receiver->td_maxend++; } if (ack == receiver->td_end) receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; /* * Check retransmissions. */ if (index == TCP_ACK_SET) { if (state->last_dir == dir && state->last_seq == seq && state->last_ack == ack && state->last_end == end && state->last_win == win_raw) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; state->last_win = win_raw; state->retrans = 0; } } res = true; } else { res = false; if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal) res = true; if (!res) { bool seq_ok = before(seq, sender->td_maxend + 1); if (!seq_ok) { u32 overshot = end - sender->td_maxend + 1; bool ack_ok; ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1); if (in_recv_win && ack_ok && overshot <= receiver->td_maxwin && before(sack, receiver->td_end + 1)) { /* Work around TCPs that send more bytes than allowed by * the receive window. * * If the (marked as invalid) packet is allowed to pass by * the ruleset and the peer acks this data, then its possible * all future packets will trigger 'ACK is over upper bound' check. * * Thus if only the sequence check fails then do update td_end so * possible ACK for this data can update internal state. */ sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%u bytes more than expected", overshot); return res; } } nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ? in_recv_win ? before(sack, receiver->td_end + 1) ? after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" : "SEQ is over the upper bound (over the window of the receiver)"); } } pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u " "receiver end=%u maxend=%u maxwin=%u\n", res, sender->td_end, sender->td_maxend, sender->td_maxwin, receiver->td_end, receiver->td_maxend, receiver->td_maxwin); return res; } /* table of valid flag combinations - PUSH, ECE and CWR are always valid */ static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK| TCPHDR_URG) + 1] = { [TCPHDR_SYN] = 1, [TCPHDR_SYN|TCPHDR_URG] = 1, [TCPHDR_SYN|TCPHDR_ACK] = 1, [TCPHDR_RST] = 1, [TCPHDR_RST|TCPHDR_ACK] = 1, [TCPHDR_FIN|TCPHDR_ACK] = 1, [TCPHDR_FIN|TCPHDR_ACK|TCPHDR_URG] = 1, [TCPHDR_ACK] = 1, [TCPHDR_ACK|TCPHDR_URG] = 1, }; static void tcp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_TCP, "%s", msg); } /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ static bool tcp_error(const struct tcphdr *th, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { unsigned int tcplen = skb->len - dataoff; u8 tcpflags; /* Not whole TCP header or malformed packet */ if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) { tcp_error_log(skb, state, "truncated packet"); return true; } /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path * because the checksum is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_checksum(skb, state->hook, dataoff, IPPROTO_TCP, state->pf)) { tcp_error_log(skb, state, "bad checksum"); return true; } /* Check TCP flags. */ tcpflags = (tcp_flag_byte(th) & ~(TCPHDR_ECE|TCPHDR_CWR|TCPHDR_PSH)); if (!tcp_valid_flags[tcpflags]) { tcp_error_log(skb, state, "invalid tcp flag combination"); return true; } return false; } static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *th) { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; /* Don't need lock here: this conntrack not in circulation yet */ new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE]; /* Invalid: delete conntrack */ if (new_state >= TCP_CONNTRACK_MAX) { pr_debug("nf_ct_tcp: invalid new deleting.\n"); return false; } if (new_state == TCP_CONNTRACK_SYN_SENT) { memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* SYN packet */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window); if (ct->proto.tcp.seen[0].td_maxwin == 0) ct->proto.tcp.seen[0].td_maxwin = 1; ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end; tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]); } else if (tn->tcp_loose == 0) { /* Don't try to pick up connections. */ return false; } else { memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* * We are in the middle of a connection, * its history is lost for us. * Let's try to use the data from the packet. */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window); if (ct->proto.tcp.seen[0].td_maxwin == 0) ct->proto.tcp.seen[0].td_maxwin = 1; ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end + ct->proto.tcp.seen[0].td_maxwin; /* We assume SACK and liberal window checking to handle * window scaling */ ct->proto.tcp.seen[0].flags = ct->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM | IP_CT_TCP_FLAG_BE_LIBERAL; } /* tcp_packet will set them */ ct->proto.tcp.last_index = TCP_NONE_SET; pr_debug("%s: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", __func__, sender->td_end, sender->td_maxend, sender->td_maxwin, sender->td_scale, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); return true; } static bool tcp_can_early_drop(const struct nf_conn *ct) { switch (ct->proto.tcp.state) { case TCP_CONNTRACK_FIN_WAIT: case TCP_CONNTRACK_LAST_ACK: case TCP_CONNTRACK_TIME_WAIT: case TCP_CONNTRACK_CLOSE: case TCP_CONNTRACK_CLOSE_WAIT: return true; default: break; } return false; } void nf_conntrack_tcp_set_closing(struct nf_conn *ct) { enum tcp_conntrack old_state; const unsigned int *timeouts; u32 timeout; if (!nf_ct_is_confirmed(ct)) return; spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; ct->proto.tcp.state = TCP_CONNTRACK_CLOSE; if (old_state == TCP_CONNTRACK_CLOSE || test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { spin_unlock_bh(&ct->lock); return; } timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) { const struct nf_tcp_net *tn; tn = nf_tcp_pernet(nf_ct_net(ct)); timeouts = tn->timeouts; } timeout = timeouts[TCP_CONNTRACK_CLOSE]; WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); spin_unlock_bh(&ct->lock); nf_conntrack_event_cache(IPCT_PROTOINFO, ct); } static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) { state->td_end = 0; state->td_maxend = 0; state->td_maxwin = 0; state->td_maxack = 0; state->td_scale = 0; state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; enum ip_conntrack_dir dir; const struct tcphdr *th; struct tcphdr _tcph; unsigned long timeout; th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); if (th == NULL) return -NF_ACCEPT; if (tcp_error(th, skb, dataoff, state)) return -NF_ACCEPT; if (!nf_ct_is_confirmed(ct) && !tcp_new(ct, skb, dataoff, th)) return -NF_ACCEPT; spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; dir = CTINFO2DIR(ctinfo); index = get_conntrack_index(th); new_state = tcp_conntracks[dir][index][old_state]; tuple = &ct->tuplehash[dir].tuple; switch (new_state) { case TCP_CONNTRACK_SYN_SENT: if (old_state < TCP_CONNTRACK_TIME_WAIT) break; /* RFC 1122: "When a connection is closed actively, * it MUST linger in TIME-WAIT state for a time 2xMSL * (Maximum Segment Lifetime). However, it MAY accept * a new SYN from the remote TCP to reopen the connection * directly from TIME-WAIT state, if..." * We ignore the conditions because we are in the * TIME-WAIT state anyway. * * Handle aborted connections: we and the server * think there is an existing connection but the client * aborts it and starts a new one. */ if (((ct->proto.tcp.seen[dir].flags | ct->proto.tcp.seen[!dir].flags) & IP_CT_TCP_FLAG_CLOSE_INIT) || (ct->proto.tcp.last_dir == dir && ct->proto.tcp.last_index == TCP_RST_SET)) { /* Attempt to reopen a closed/aborted connection. * Delete this connection and look up again. */ spin_unlock_bh(&ct->lock); /* Only repeat if we can actually remove the timer. * Destruction may already be in progress in process * context and we must give it a chance to terminate. */ if (nf_ct_kill(ct)) return -NF_REPEAT; return NF_DROP; } fallthrough; case TCP_CONNTRACK_IGNORE: /* Ignored packets: * * Our connection entry may be out of sync, so ignore * packets which may signal the real connection between * the client and the server. * * a) SYN in ORIGINAL * b) SYN/ACK in REPLY * c) ACK in reply direction after initial SYN in original. * * If the ignored packet is invalid, the receiver will send * a RST we'll catch below. */ if (index == TCP_SYNACK_SET && ct->proto.tcp.last_index == TCP_SYN_SET && ct->proto.tcp.last_dir != dir && ntohl(th->ack_seq) == ct->proto.tcp.last_end) { /* b) This SYN/ACK acknowledges a SYN that we earlier * ignored as invalid. This means that the client and * the server are both in sync, while the firewall is * not. We get in sync from the previously annotated * values. */ old_state = TCP_CONNTRACK_SYN_SENT; new_state = TCP_CONNTRACK_SYN_RECV; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end = ct->proto.tcp.last_end; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend = ct->proto.tcp.last_end; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin = ct->proto.tcp.last_win == 0 ? 1 : ct->proto.tcp.last_win; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = ct->proto.tcp.last_wscale; ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; nf_ct_tcp_state_reset(&ct->proto.tcp.seen[dir]); break; } ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; ct->proto.tcp.last_seq = ntohl(th->seq); ct->proto.tcp.last_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); ct->proto.tcp.last_win = ntohs(th->window); /* a) This is a SYN in ORIGINAL. The client and the server * may be in sync but we are not. In that case, we annotate * the TCP options and let the packet go through. If it is a * valid SYN packet, the server will reply with a SYN/ACK, and * then we'll get in sync. Otherwise, the server potentially * responds with a challenge ACK if implementing RFC5961. */ if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { struct ip_ct_tcp_state seen = {}; ct->proto.tcp.last_flags = ct->proto.tcp.last_wscale = 0; tcp_options(skb, dataoff, th, &seen); if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) { ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_WINDOW_SCALE; ct->proto.tcp.last_wscale = seen.td_scale; } if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) { ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_SACK_PERM; } /* Mark the potential for RFC5961 challenge ACK, * this pose a special problem for LAST_ACK state * as ACK is intrepretated as ACKing last FIN. */ if (old_state == TCP_CONNTRACK_LAST_ACK) ct->proto.tcp.last_flags |= IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", index, dir, tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Special case for SYN proxy: when the SYN to the server or * the SYN/ACK from the server is lost, the client may transmit * a keep-alive packet while in SYN_SENT state. This needs to * be associated with the original conntrack entry in order to * generate a new SYN with the correct sequence number. */ if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT && index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL && ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL && ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) { pr_debug("nf_ct_tcp: SYN proxy client keep alive\n"); spin_unlock_bh(&ct->lock); return NF_ACCEPT; } /* Invalid packet */ pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid state"); return -NF_ACCEPT; case TCP_CONNTRACK_TIME_WAIT: /* RFC5961 compliance cause stack to send "challenge-ACK" * e.g. in response to spurious SYNs. Conntrack MUST * not believe this ACK is acking last FIN. */ if (old_state == TCP_CONNTRACK_LAST_ACK && index == TCP_ACK_SET && ct->proto.tcp.last_dir != dir && ct->proto.tcp.last_index == TCP_SYN_SET && (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) { /* Detected RFC5961 challenge ACK */ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "challenge-ack ignored"); return NF_ACCEPT; /* Don't change state */ } break; case TCP_CONNTRACK_SYN_SENT2: /* tcp_conntracks table is not smart enough to handle * simultaneous open. */ ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN; break; case TCP_CONNTRACK_SYN_RECV: if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET && ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN) new_state = TCP_CONNTRACK_ESTABLISHED; break; case TCP_CONNTRACK_CLOSE: if (index != TCP_RST_SET) break; /* If we are closing, tuple might have been re-used already. * last_index, last_ack, and all other ct fields used for * sequence/window validation are outdated in that case. * * As the conntrack can already be expired by GC under pressure, * just skip validation checks. */ if (tcp_can_early_drop(ct)) goto in_window; /* td_maxack might be outdated if we let a SYN through earlier */ if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && ct->proto.tcp.last_index != TCP_SYN_SET) { u32 seq = ntohl(th->seq); /* If we are not in established state and SEQ=0 this is most * likely an answer to a SYN we let go through above (last_index * can be updated due to out-of-order ACKs). */ if (seq == 0 && !nf_conntrack_tcp_established(ct)) break; if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) && !tn->tcp_ignore_invalid_rst) { /* Invalid RST */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); return -NF_ACCEPT; } if (!nf_conntrack_tcp_established(ct) || seq == ct->proto.tcp.seen[!dir].td_maxack) break; /* Check if rst is part of train, such as * foo:80 > bar:4379: P, 235946583:235946602(19) ack 42 * foo:80 > bar:4379: R, 235946602:235946602(0) ack 42 */ if (ct->proto.tcp.last_index == TCP_ACK_SET && ct->proto.tcp.last_dir == dir && seq == ct->proto.tcp.last_end) break; /* ... RST sequence number doesn't match exactly, keep * established state to allow a possible challenge ACK. */ new_state = old_state; } if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) || (!test_bit(IPS_ASSURED_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_ACK_SET)) && ntohl(th->ack_seq) == ct->proto.tcp.last_end) { /* RST sent to invalid SYN or ACK we had let through * at a) and c) above: * * a) SYN was in window then * c) we hold a half-open connection. * * Delete our connection entry. * We skip window checking, because packet might ACK * segments we ignored. */ goto in_window; } break; default: /* Keep compilers happy. */ break; } if (!tcp_in_window(ct, dir, index, skb, dataoff, th, state)) { spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } in_window: /* From now on we have got in-window packets */ ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; pr_debug("tcp_conntracks: "); nf_ct_dump_tuple(tuple); pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n", (th->syn ? 1 : 0), (th->ack ? 1 : 0), (th->fin ? 1 : 0), (th->rst ? 1 : 0), old_state, new_state); ct->proto.tcp.state = new_state; if (old_state != new_state && new_state == TCP_CONNTRACK_FIN_WAIT) ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = tn->timeouts; if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; else if (unlikely(index == TCP_RST_SET)) timeout = timeouts[TCP_CONNTRACK_CLOSE]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; else if (ct->proto.tcp.last_win == 0 && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; else timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { /* If only reply is a RST, we can consider ourselves not to have an established connection: this is a fairly common problem case, so we can delete the conntrack immediately. --RR */ if (th->rst) { nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { /* do not renew timeout on SYN retransmit. * * Else port reuse by client or NAT middlebox can keep * entry alive indefinitely (including nat info). */ return NF_ACCEPT; } /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ if (new_state == TCP_CONNTRACK_ESTABLISHED && timeout > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; } else if (!test_bit(IPS_ASSURED_BIT, &ct->status) && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { /* Set ASSURED if we see valid ack in ESTABLISHED after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); nf_conntrack_event_cache(IPCT_ASSURED, ct); } nf_ct_refresh_acct(ct, ctinfo, skb, timeout); return NF_ACCEPT; } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy) { struct nlattr *nest_parms; struct nf_ct_tcp_flags tmp = {}; spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state)) goto nla_put_failure; if (destroy) goto skip_state; if (nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL, ct->proto.tcp.seen[0].td_scale) || nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY, ct->proto.tcp.seen[1].td_scale)) goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[0].flags; if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL, sizeof(struct nf_ct_tcp_flags), &tmp)) goto nla_put_failure; tmp.flags = ct->proto.tcp.seen[1].flags; if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, sizeof(struct nf_ct_tcp_flags), &tmp)) goto nla_put_failure; skip_state: spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { [CTA_PROTOINFO_TCP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) }, [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, }; #define TCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags))) static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) { struct nlattr *pattr = cda[CTA_PROTOINFO_TCP]; struct nlattr *tb[CTA_PROTOINFO_TCP_MAX+1]; int err; /* updates could not contain anything about the private * protocol info, in that case skip the parsing */ if (!pattr) return 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_TCP_MAX, pattr, tcp_nla_policy, NULL); if (err < 0) return err; if (tb[CTA_PROTOINFO_TCP_STATE] && nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) return -EINVAL; spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); if (tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]) { struct nf_ct_tcp_flags *attr = nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]); ct->proto.tcp.seen[0].flags &= ~attr->mask; ct->proto.tcp.seen[0].flags |= attr->flags & attr->mask; } if (tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]) { struct nf_ct_tcp_flags *attr = nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]); ct->proto.tcp.seen[1].flags &= ~attr->mask; ct->proto.tcp.seen[1].flags |= attr->flags & attr->mask; } if (tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] && tb[CTA_PROTOINFO_TCP_WSCALE_REPLY] && ct->proto.tcp.seen[0].flags & IP_CT_TCP_FLAG_WINDOW_SCALE && ct->proto.tcp.seen[1].flags & IP_CT_TCP_FLAG_WINDOW_SCALE) { ct->proto.tcp.seen[0].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL]); ct->proto.tcp.seen[1].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]); } spin_unlock_bh(&ct->lock); return 0; } static unsigned int tcp_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; if (!timeouts) timeouts = tn->timeouts; /* set default TCP timeouts. */ for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++) timeouts[i] = tn->timeouts[i]; if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) { timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; } if (tb[CTA_TIMEOUT_TCP_ESTABLISHED]) { timeouts[TCP_CONNTRACK_ESTABLISHED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_ESTABLISHED]))*HZ; } if (tb[CTA_TIMEOUT_TCP_FIN_WAIT]) { timeouts[TCP_CONNTRACK_FIN_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_FIN_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]) { timeouts[TCP_CONNTRACK_CLOSE_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_LAST_ACK]) { timeouts[TCP_CONNTRACK_LAST_ACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_LAST_ACK]))*HZ; } if (tb[CTA_TIMEOUT_TCP_TIME_WAIT]) { timeouts[TCP_CONNTRACK_TIME_WAIT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_TIME_WAIT]))*HZ; } if (tb[CTA_TIMEOUT_TCP_CLOSE]) { timeouts[TCP_CONNTRACK_CLOSE] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE]))*HZ; } if (tb[CTA_TIMEOUT_TCP_SYN_SENT2]) { timeouts[TCP_CONNTRACK_SYN_SENT2] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT2]))*HZ; } if (tb[CTA_TIMEOUT_TCP_RETRANS]) { timeouts[TCP_CONNTRACK_RETRANS] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_RETRANS]))*HZ; } if (tb[CTA_TIMEOUT_TCP_UNACK]) { timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } static int tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; if (nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT, htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_RECV, htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_LAST_ACK, htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_CLOSE, htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_RETRANS, htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_TCP_UNACK, htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_SYN_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_SYN_RECV] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_ESTABLISHED] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_FIN_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_CLOSE_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_LAST_ACK] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_TIME_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_CLOSE] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_SYN_SENT2] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_tcp_init_net(struct net *net) { struct nf_tcp_net *tn = nf_tcp_pernet(net); int i; for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; /* timeouts[0] is unused, make it same as SYN_SENT so * ->timeouts[0] contains 'new' timeout, like udp or icmp. */ tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; /* If it is set to zero, we disable picking up already established * connections. */ tn->tcp_loose = 1; /* "Be conservative in what you do, * be liberal in what you accept from others." * If it's non-zero, we mark only out of window RST segments as INVALID. */ tn->tcp_be_liberal = 0; /* If it's non-zero, we turn off RST sequence number check */ tn->tcp_ignore_invalid_rst = 0; /* Max number of the retransmitted packets without receiving an (acceptable) * ACK from the destination. If this number is reached, a shorter timer * will be started. */ tn->tcp_max_retrans = 3; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; #endif } const struct nf_conntrack_l4proto nf_conntrack_l4prot |