| 1528 1484 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007-2012 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Sergey Lapin <slapin@ossfans.org> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/netdevice.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ieee802154.h> #include <net/nl802154.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "driver-ops.h" int mac802154_wpan_update_llsec(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; int rc = 0; if (ops->llsec) { struct ieee802154_llsec_params params; int changed = 0; params.pan_id = wpan_dev->pan_id; changed |= IEEE802154_LLSEC_PARAM_PAN_ID; params.hwaddr = wpan_dev->extended_addr; changed |= IEEE802154_LLSEC_PARAM_HWADDR; rc = ops->llsec->set_params(dev, ¶ms, changed); } return rc; } static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct sockaddr_ieee802154 *sa = (struct sockaddr_ieee802154 *)&ifr->ifr_addr; int err = -ENOIOCTLCMD; if (cmd != SIOCGIFADDR && cmd != SIOCSIFADDR) return err; rtnl_lock(); switch (cmd) { case SIOCGIFADDR: { u16 pan_id, short_addr; pan_id = le16_to_cpu(wpan_dev->pan_id); short_addr = le16_to_cpu(wpan_dev->short_addr); if (pan_id == IEEE802154_PANID_BROADCAST || short_addr == IEEE802154_ADDR_BROADCAST) { err = -EADDRNOTAVAIL; break; } sa->family = AF_IEEE802154; sa->addr.addr_type = IEEE802154_ADDR_SHORT; sa->addr.pan_id = pan_id; sa->addr.short_addr = short_addr; err = 0; break; } case SIOCSIFADDR: if (netif_running(dev)) { rtnl_unlock(); return -EBUSY; } dev_warn(&dev->dev, "Using DEBUGing ioctl SIOCSIFADDR isn't recommended!\n"); if (sa->family != AF_IEEE802154 || sa->addr.addr_type != IEEE802154_ADDR_SHORT || sa->addr.pan_id == IEEE802154_PANID_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_UNDEF) { err = -EINVAL; break; } wpan_dev->pan_id = cpu_to_le16(sa->addr.pan_id); wpan_dev->short_addr = cpu_to_le16(sa->addr.short_addr); err = mac802154_wpan_update_llsec(dev); break; } rtnl_unlock(); return err; } static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct sockaddr *addr = p; __le64 extended_addr; if (netif_running(dev)) return -EBUSY; /* lowpan need to be down for update * SLAAC address after ifup */ if (sdata->wpan_dev.lowpan_dev) { if (netif_running(sdata->wpan_dev.lowpan_dev)) return -EBUSY; } ieee802154_be64_to_le64(&extended_addr, addr->sa_data); if (!ieee802154_is_valid_extended_unicast_addr(extended_addr)) return -EINVAL; dev_addr_set(dev, addr->sa_data); sdata->wpan_dev.extended_addr = extended_addr; /* update lowpan interface mac address when * wpan mac has been changed */ if (sdata->wpan_dev.lowpan_dev) dev_addr_set(sdata->wpan_dev.lowpan_dev, dev->dev_addr); return mac802154_wpan_update_llsec(dev); } static int ieee802154_setup_hw(struct ieee802154_sub_if_data *sdata) { struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; sdata->required_filtering = sdata->iface_default_filtering; if (local->hw.flags & IEEE802154_HW_AFILT) { local->addr_filt.pan_id = wpan_dev->pan_id; local->addr_filt.ieee_addr = wpan_dev->extended_addr; local->addr_filt.short_addr = wpan_dev->short_addr; } if (local->hw.flags & IEEE802154_HW_LBT) { ret = drv_set_lbt_mode(local, wpan_dev->lbt); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { ret = drv_set_csma_params(local, wpan_dev->min_be, wpan_dev->max_be, wpan_dev->csma_retries); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { ret = drv_set_max_frame_retries(local, wpan_dev->frame_retries); if (ret < 0) return ret; } return 0; } static int mac802154_slave_open(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; ASSERT_RTNL(); set_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) { res = ieee802154_setup_hw(sdata); if (res) goto err; res = drv_start(local, sdata->required_filtering, &local->addr_filt); if (res) goto err; } local->open_count++; netif_start_queue(dev); return 0; err: /* might already be clear but that doesn't matter */ clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } static int ieee802154_check_mac_settings(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct ieee802154_sub_if_data *nsdata) { struct wpan_dev *nwpan_dev = &nsdata->wpan_dev; struct wpan_dev *wpan_dev = &sdata->wpan_dev; ASSERT_RTNL(); if (sdata->iface_default_filtering != nsdata->iface_default_filtering) return -EBUSY; if (local->hw.flags & IEEE802154_HW_AFILT) { if (wpan_dev->pan_id != nwpan_dev->pan_id || wpan_dev->short_addr != nwpan_dev->short_addr || wpan_dev->extended_addr != nwpan_dev->extended_addr) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { if (wpan_dev->min_be != nwpan_dev->min_be || wpan_dev->max_be != nwpan_dev->max_be || wpan_dev->csma_retries != nwpan_dev->csma_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { if (wpan_dev->frame_retries != nwpan_dev->frame_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_LBT) { if (wpan_dev->lbt != nwpan_dev->lbt) return -EBUSY; } return 0; } static int ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype iftype) { struct ieee802154_local *local = sdata->local; struct ieee802154_sub_if_data *nsdata; /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee802154_sdata_running(nsdata)) { int ret; /* TODO currently we don't support multiple node/coord * types we need to run skb_clone at rx path. Check if * there exist really an use case if we need to support * multiple node/coord types at the same time. */ if (sdata->wpan_dev.iftype != NL802154_IFTYPE_MONITOR && nsdata->wpan_dev.iftype != NL802154_IFTYPE_MONITOR) return -EBUSY; /* check all phy mac sublayer settings are the same. * We have only one phy, different values makes trouble. */ ret = ieee802154_check_mac_settings(local, sdata, nsdata); if (ret < 0) return ret; } } return 0; } static int mac802154_wpan_open(struct net_device *dev) { int rc; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; rc = ieee802154_check_concurrent_iface(sdata, wpan_dev->iftype); if (rc < 0) return rc; return mac802154_slave_open(dev); } static int mac802154_slave_close(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; ASSERT_RTNL(); if (mac802154_is_scanning(local)) mac802154_abort_scan_locked(local, sdata); if (mac802154_is_beaconing(local)) mac802154_stop_beacons_locked(local, sdata); netif_stop_queue(dev); local->open_count--; clear_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) ieee802154_stop_device(local); return 0; } static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata, struct ieee802154_hdr *hdr, const struct ieee802154_mac_cb *cb) { struct ieee802154_llsec_params params; u8 level; mac802154_llsec_get_params(&sdata->sec, ¶ms); if (!params.enabled && cb->secen_override && cb->secen) return -EINVAL; if (!params.enabled || (cb->secen_override && !cb->secen) || !params.out_level) return 0; if (cb->seclevel_override && !cb->seclevel) return -EINVAL; level = cb->seclevel_override ? cb->seclevel : params.out_level; hdr->fc.security_enabled = 1; hdr->sec.level = level; hdr->sec.key_id_mode = params.out_key.mode; if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX) hdr->sec.short_src = params.out_key.short_source; else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX) hdr->sec.extended_src = params.out_key.extended_source; hdr->sec.key_id = params.out_key.id; return 0; } static int ieee802154_header_create(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, const struct ieee802154_addr *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb *cb = mac_cb(skb); int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = cb->type; hdr.fc.security_enabled = cb->secen; hdr.fc.ack_request = cb->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; if (mac802154_set_header_security(sdata, &hdr, cb) < 0) return -EINVAL; if (!saddr) { if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { hdr.source.mode = IEEE802154_ADDR_LONG; hdr.source.extended_addr = wpan_dev->extended_addr; } else { hdr.source.mode = IEEE802154_ADDR_SHORT; hdr.source.short_addr = wpan_dev->short_addr; } hdr.source.pan_id = wpan_dev->pan_id; } else { hdr.source = *(const struct ieee802154_addr *)saddr; } hdr.dest = *(const struct ieee802154_addr *)daddr; hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static const struct wpan_dev_header_ops ieee802154_header_ops = { .create = ieee802154_header_create, }; /* This header create functionality assumes a 8 byte array for * source and destination pointer at maximum. To adapt this for * the 802.15.4 dataframe header we use extended address handling * here only and intra pan connection. fc fields are mostly fallback * handling. For provide dev_hard_header for dgram sockets. */ static int mac802154_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb cb = { }; int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = IEEE802154_FC_TYPE_DATA; hdr.fc.ack_request = wpan_dev->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; /* TODO currently a workaround to give zero cb block to set * security parameters defaults according MIB. */ if (mac802154_set_header_security(sdata, &hdr, &cb) < 0) return -EINVAL; hdr.dest.pan_id = wpan_dev->pan_id; hdr.dest.mode = IEEE802154_ADDR_LONG; ieee802154_be64_to_le64(&hdr.dest.extended_addr, daddr); hdr.source.pan_id = hdr.dest.pan_id; hdr.source.mode = IEEE802154_ADDR_LONG; if (!saddr) hdr.source.extended_addr = wpan_dev->extended_addr; else ieee802154_be64_to_le64(&hdr.source.extended_addr, saddr); hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static int mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) { struct ieee802154_hdr hdr; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { pr_debug("malformed packet\n"); return 0; } if (hdr.source.mode == IEEE802154_ADDR_LONG) { ieee802154_le64_to_be64(haddr, &hdr.source.extended_addr); return IEEE802154_EXTENDED_ADDR_LEN; } return 0; } static const struct header_ops mac802154_header_ops = { .create = mac802154_header_create, .parse = mac802154_header_parse, }; static const struct net_device_ops mac802154_wpan_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_subif_start_xmit, .ndo_do_ioctl = mac802154_wpan_ioctl, .ndo_set_mac_address = mac802154_wpan_mac_addr, }; static const struct net_device_ops mac802154_monitor_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_monitor_start_xmit, }; static void mac802154_wpan_free(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); mac802154_llsec_destroy(&sdata->sec); } static void ieee802154_if_setup(struct net_device *dev) { dev->addr_len = IEEE802154_EXTENDED_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN); /* Let hard_header_len set to IEEE802154_MIN_HEADER_LEN. AF_PACKET * will not send frames without any payload, but ack frames * has no payload, so substract one that we can send a 3 bytes * frame. The xmit callback assumes at least a hard header where two * bytes fc and sequence field are set. */ dev->hard_header_len = IEEE802154_MIN_HEADER_LEN - 1; /* The auth_tag header is for security and places in private payload * room of mac frame which stucks between payload and FCS field. */ dev->needed_tailroom = IEEE802154_MAX_AUTH_TAG_LEN + IEEE802154_FCS_LEN; /* The mtu size is the payload without mac header in this case. * We have a dynamic length header with a minimum header length * which is hard_header_len. In this case we let mtu to the size * of maximum payload which is IEEE802154_MTU - IEEE802154_FCS_LEN - * hard_header_len. The FCS which is set by hardware or ndo_start_xmit * and the minimum mac header which can be evaluated inside driver * layer. The rest of mac header will be part of payload if greater * than hard_header_len. */ dev->mtu = IEEE802154_MTU - IEEE802154_FCS_LEN - dev->hard_header_len; dev->tx_queue_len = 300; dev->flags = IFF_NOARP | IFF_BROADCAST; } static int ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; u8 tmp; /* set some type-dependent values */ sdata->wpan_dev.iftype = type; get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->bsn, tmp); get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->dsn, tmp); /* defaults per 802.15.4-2011 */ wpan_dev->min_be = 3; wpan_dev->max_be = 5; wpan_dev->csma_retries = 4; wpan_dev->frame_retries = 3; wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); switch (type) { case NL802154_IFTYPE_COORD: case NL802154_IFTYPE_NODE: ieee802154_be64_to_le64(&wpan_dev->extended_addr, sdata->dev->dev_addr); sdata->dev->header_ops = &mac802154_header_ops; sdata->dev->needs_free_netdev = true; sdata->dev->priv_destructor = mac802154_wpan_free; sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; sdata->iface_default_filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); ret = mac802154_wpan_update_llsec(sdata->dev); if (ret < 0) return ret; break; case NL802154_IFTYPE_MONITOR: sdata->dev->needs_free_netdev = true; sdata->dev->netdev_ops = &mac802154_monitor_ops; sdata->iface_default_filtering = IEEE802154_FILTERING_NONE; break; default: BUG(); } return 0; } struct net_device * ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { u8 addr[IEEE802154_EXTENDED_ADDR_LEN]; struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; int ret; ASSERT_RTNL(); ndev = alloc_netdev(sizeof(*sdata), name, name_assign_type, ieee802154_if_setup); if (!ndev) return ERR_PTR(-ENOMEM); ndev->needed_headroom = local->hw.extra_tx_headroom + IEEE802154_MAX_HEADER_LEN; ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) goto err; ieee802154_le64_to_be64(ndev->perm_addr, &local->hw.phy->perm_extended_addr); switch (type) { case NL802154_IFTYPE_COORD: case NL802154_IFTYPE_NODE: ndev->type = ARPHRD_IEEE802154; if (ieee802154_is_valid_extended_unicast_addr(extended_addr)) { ieee802154_le64_to_be64(addr, &extended_addr); dev_addr_set(ndev, addr); } else { dev_addr_set(ndev, ndev->perm_addr); } break; case NL802154_IFTYPE_MONITOR: ndev->type = ARPHRD_IEEE802154_MONITOR; break; default: ret = -EINVAL; goto err; } /* TODO check this */ SET_NETDEV_DEV(ndev, &local->phy->dev); dev_net_set(ndev, wpan_phy_net(local->hw.phy)); sdata = netdev_priv(ndev); ndev->ieee802154_ptr = &sdata->wpan_dev; memcpy(sdata->name, ndev->name, IFNAMSIZ); sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; INIT_LIST_HEAD(&sdata->wpan_dev.list); /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); if (ret) goto err; ret = register_netdevice(ndev); if (ret < 0) goto err; mutex_lock(&local->iflist_mtx); list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); return ndev; err: free_netdev(ndev); return ERR_PTR(ret); } void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) { ASSERT_RTNL(); mutex_lock(&sdata->local->iflist_mtx); list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); synchronize_rcu(); unregister_netdevice(sdata->dev); } void ieee802154_remove_interfaces(struct ieee802154_local *local) { struct ieee802154_sub_if_data *sdata, *tmp; mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); unregister_netdevice(sdata->dev); } mutex_unlock(&local->iflist_mtx); } static int netdev_notify(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee802154_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) return NOTIFY_DONE; if (!dev->ieee802154_ptr || !dev->ieee802154_ptr->wpan_phy) return NOTIFY_DONE; if (dev->ieee802154_ptr->wpan_phy->privid != mac802154_wpan_phy_privid) return NOTIFY_DONE; sdata = IEEE802154_DEV_TO_SUB_IF(dev); memcpy(sdata->name, dev->name, IFNAMSIZ); return NOTIFY_OK; } static struct notifier_block mac802154_netdev_notifier = { .notifier_call = netdev_notify, }; int ieee802154_iface_init(void) { return register_netdevice_notifier(&mac802154_netdev_notifier); } void ieee802154_iface_exit(void) { unregister_netdevice_notifier(&mac802154_netdev_notifier); } |
| 369 1700 1559 1559 1342 1342 1370 2312 1461 1559 1559 1559 1559 1559 1559 3250 3251 3250 5 5 5 5 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 1558 1558 1559 1559 1556 1558 1559 1559 1559 1559 1550 1550 1550 1550 266 266 267 266 267 266 266 266 3 3 3 5 5 5 5 5 5 5 5 1559 1559 1559 1559 107 1559 1559 1559 1559 1559 107 107 107 112 5 107 1559 1559 1559 5 5 52 52 1559 1550 1559 1559 1559 88 1472 1559 491 1163 1559 1559 1559 1559 865 865 865 1 119 1 117 865 865 1569 2 5 2 1560 1560 1 1559 1559 1559 1559 1559 1559 1559 1558 1559 1559 1559 1559 1559 12 955 2 952 839 1 117 866 865 866 2 30 837 865 865 833 33 865 865 865 838 27 2 93 95 107 1570 1570 371 127 1095 10 865 835 32 811 56 865 865 811 52 52 1570 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL) continue; return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; int nr_charged = 0; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; #ifdef CONFIG_PER_VMA_LOCK /* SLAB cache for vm_area_struct.lock */ static struct kmem_cache *vma_lock_cachep; static bool vma_lock_alloc(struct vm_area_struct *vma) { vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); if (!vma->vm_lock) return false; init_rwsem(&vma->vm_lock->lock); vma->vm_lock_seq = -1; return true; } static inline void vma_lock_free(struct vm_area_struct *vma) { kmem_cache_free(vma_lock_cachep, vma->vm_lock); } #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } static inline void vma_lock_free(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!vma) return NULL; vma_init(vma, mm); if (!vma_lock_alloc(vma)) { kmem_cache_free(vm_area_cachep, vma); return NULL; } return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); if (!vma_lock_alloc(new)) { kmem_cache_free(vm_area_cachep, new); return NULL; } INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; } void __vm_area_free(struct vm_area_struct *vma) { vma_numab_state_free(vma); free_anon_vma_name(vma); vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } #ifdef CONFIG_PER_VMA_LOCK static void vm_area_free_rcu_cb(struct rcu_head *head) { struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); /* The vma should not be locked while being destroyed. */ VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); __vm_area_free(vma); } #endif void vm_area_free(struct vm_area_struct *vma) { #ifdef CONFIG_PER_VMA_LOCK call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); #else __vm_area_free(vma); #endif } static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm; int i; vm = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && deny_write_access(exe_file)) pr_warn_once("deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { retval = -EINTR; goto fail_uprobe_end; } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; retval = ksm_fork(mm, oldmm); if (retval) goto out; khugepaged_fork(mm, oldmm); /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); } else if (mpnt) { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); dup_userfaultfd_complete(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_CPU_SUP_INTEL tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); #ifdef CONFIG_PER_VMA_LOCK mm->mm_lock_seq = 0; #endif mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (!(task->flags & PF_KTHREAD)) exe_file = get_mm_exe_file(mm); } task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (task->flags & PF_KTHREAD) mm = NULL; else mmget(mm); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (mm && mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; sched_mm_cid_fork(tsk); return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) goto out; if (no_files) { tsk->files = NULL; goto out; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); goto out; } newf = dup_fd(oldf, NR_OPEN_MAX, &error); if (!newf) goto out; tsk->files = newf; error = 0; out: return error; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } struct pid *pidfd_pid(const struct file *file) { if (file->f_op == &pidfd_fops) return file->private_data; return ERR_PTR(-EBADF); } static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); return 0; } #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = f->private_data; struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Inform pollers only when the whole thread group exits. * If the thread group leader exits before all other threads in the * group, then poll(2) should block, similar to the wait(2) family. */ if (thread_group_exited(pid)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } const struct file_operations pidfd_fops = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the file for the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper doesn't perform checks on @pid which makes it useful for pidfds * created via CLONE_PIDFD where @pid has no task attached when the pidfd and * pidfd file are prepared. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { int pidfd; struct file *pidfd_file; if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) return -EINVAL; pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, flags | O_RDWR | O_CLOEXEC); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } get_pid(pid); /* held by pidfd_file now */ *ret = pidfd_file; return pidfd; } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is used as a thread group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { int i; for (i = 0; i < RV_PER_TASK_MONITORS; i++) p->rv[i].da_mon.monitoring = false; } #else #define rv_task_fork(p) do {} while (0) #endif /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. * - CLONE_THREAD is blocked until someone really needs it. */ if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ sched_cgroup_fork(p, args); /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_cancel_cgroup; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_cancel_cgroup; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_cancel_cgroup: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((args->flags & CLONE_PIDFD) && (args->flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } #endif void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); #ifdef CONFIG_PER_VMA_LOCK vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT); #endif mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp) { struct files_struct *fd = current->files; int error = 0; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { *new_fdp = dup_fd(fd, max_fds, &error); if (!*new_fdp) return error; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 1544 1543 1544 1543 30 98 98 98 1362 1362 4 4 4 472 3 3 68 68 71 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/file.c - sysfs regular (text) file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/module.h> #include <linux/kobject.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/mm.h> #include "sysfs.h" /* * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { struct kobject *kobj = kn->parent->priv; if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kobj->ktype ? kobj->ktype->sysfs_ops : NULL; } /* * Reads on sysfs are handled through seq_file, which takes care of hairy * details like buffering and seeking. The following function pipes * sysfs_ops->show() result through seq_file. */ static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; struct kobject *kobj = of->kn->parent->priv; const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; char *buf; if (WARN_ON_ONCE(!ops->show)) return -EINVAL; /* acquire buffer and ensure that it's >= PAGE_SIZE and clear */ count = seq_get_buf(sf, &buf); if (count < PAGE_SIZE) { seq_commit(sf, -1); return 0; } memset(buf, 0, PAGE_SIZE); count = ops->show(kobj, of->kn->priv, buf); if (count < 0) return count; /* * The code works fine with PAGE_SIZE return but it's likely to * indicate truncated result or overflow in normal use cases. */ if (count >= (ssize_t)PAGE_SIZE) { printk("fill_read_buffer: %pS returned bad count\n", ops->show); /* Try to struggle along */ count = PAGE_SIZE - 1; } seq_commit(sf, count); return 0; } static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; loff_t size = file_inode(of->file)->i_size; if (!count) return 0; if (size) { if (pos >= size) return 0; if (pos + count > size) count = size - pos; } if (!battr->read) return -EIO; return battr->read(of->file, kobj, battr, buf, pos, count); } /* kernfs read callback for regular sysfs files with pre-alloc */ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; ssize_t len; /* * If buf != of->prealloc_buf, we don't know how * large it is, so cannot safely pass it to ->show */ if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); if (len < 0) return len; if (pos) { if (len <= pos) return 0; len -= pos; memmove(buf, buf + pos, len); } return min_t(ssize_t, count, len); } /* kernfs write callback for regular sysfs files */ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; if (!count) return 0; return ops->store(kobj, of->kn->priv, buf, count); } /* kernfs write callback for bin sysfs files */ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; loff_t size = file_inode(of->file)->i_size; if (size) { if (size <= pos) return -EFBIG; count = min_t(ssize_t, count, size - pos); } if (!count) return 0; if (!battr->write) return -EIO; return battr->write(of->file, kobj, battr, buf, pos, count); } static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, struct vm_area_struct *vma) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; return battr->mmap(of->file, kobj, battr, vma); } static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, int whence) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; if (battr->llseek) return battr->llseek(of->file, kobj, battr, offset, whence); else return generic_file_llseek(of->file, offset, whence); } static int sysfs_kf_bin_open(struct kernfs_open_file *of) { struct bin_attribute *battr = of->kn->priv; if (battr->f_mapping) of->file->f_mapping = battr->f_mapping(); return 0; } void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { struct kernfs_node *kn = kobj->sd, *tmp; if (kn && dir) kn = kernfs_find_and_get(kn, dir); else kernfs_get(kn); if (kn && attr) { tmp = kernfs_find_and_get(kn, attr); kernfs_put(kn); kn = tmp; } if (kn) { kernfs_notify(kn); kernfs_put(kn); } } EXPORT_SYMBOL_GPL(sysfs_notify); static const struct kernfs_ops sysfs_file_kfops_empty = { }; static const struct kernfs_ops sysfs_file_kfops_ro = { .seq_show = sysfs_kf_seq_show, }; static const struct kernfs_ops sysfs_file_kfops_wo = { .write = sysfs_kf_write, }; static const struct kernfs_ops sysfs_file_kfops_rw = { .seq_show = sysfs_kf_seq_show, .write = sysfs_kf_write, }; static const struct kernfs_ops sysfs_prealloc_kfops_ro = { .read = sysfs_kf_read, .prealloc = true, }; static const struct kernfs_ops sysfs_prealloc_kfops_wo = { .write = sysfs_kf_write, .prealloc = true, }; static const struct kernfs_ops sysfs_prealloc_kfops_rw = { .read = sysfs_kf_read, .write = sysfs_kf_write, .prealloc = true, }; static const struct kernfs_ops sysfs_bin_kfops_ro = { .read = sysfs_kf_bin_read, }; static const struct kernfs_ops sysfs_bin_kfops_wo = { .write = sysfs_kf_bin_write, }; static const struct kernfs_ops sysfs_bin_kfops_rw = { .read = sysfs_kf_bin_read, .write = sysfs_kf_bin_write, }; static const struct kernfs_ops sysfs_bin_kfops_mmap = { .read = sysfs_kf_bin_read, .write = sysfs_kf_bin_write, .mmap = sysfs_kf_bin_mmap, .open = sysfs_kf_bin_open, .llseek = sysfs_kf_bin_llseek, }; int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, umode_t mode, kuid_t uid, kgid_t gid, const void *ns) { struct kobject *kobj = parent->priv; const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops; struct lock_class_key *key = NULL; const struct kernfs_ops *ops = NULL; struct kernfs_node *kn; /* every kobject with an attribute needs a ktype assigned */ if (WARN(!sysfs_ops, KERN_ERR "missing sysfs attribute operations for kobject: %s\n", kobject_name(kobj))) return -EINVAL; if (mode & SYSFS_PREALLOC) { if (sysfs_ops->show && sysfs_ops->store) ops = &sysfs_prealloc_kfops_rw; else if (sysfs_ops->show) ops = &sysfs_prealloc_kfops_ro; else if (sysfs_ops->store) ops = &sysfs_prealloc_kfops_wo; } else { if (sysfs_ops->show && sysfs_ops->store) ops = &sysfs_file_kfops_rw; else if (sysfs_ops->show) ops = &sysfs_file_kfops_ro; else if (sysfs_ops->store) ops = &sysfs_file_kfops_wo; } if (!ops) ops = &sysfs_file_kfops_empty; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, PAGE_SIZE, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, attr->name); return PTR_ERR(kn); } return 0; } int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, const struct bin_attribute *battr, umode_t mode, kuid_t uid, kgid_t gid, const void *ns) { const struct attribute *attr = &battr->attr; struct lock_class_key *key = NULL; const struct kernfs_ops *ops; struct kernfs_node *kn; if (battr->mmap) ops = &sysfs_bin_kfops_mmap; else if (battr->read && battr->write) ops = &sysfs_bin_kfops_rw; else if (battr->read) ops = &sysfs_bin_kfops_ro; else if (battr->write) ops = &sysfs_bin_kfops_wo; else ops = &sysfs_file_kfops_empty; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, battr->size, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, attr->name); return PTR_ERR(kn); } return 0; } /** * sysfs_create_file_ns - create an attribute file for an object with custom ns * @kobj: object we're creating for * @attr: attribute descriptor * @ns: namespace the new file should belong to */ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { kuid_t uid; kgid_t gid; if (WARN_ON(!kobj || !kobj->sd || !attr)) return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, attr, attr->mode, uid, gid, ns); } EXPORT_SYMBOL_GPL(sysfs_create_file_ns); int sysfs_create_files(struct kobject *kobj, const struct attribute * const *ptr) { int err = 0; int i; for (i = 0; ptr[i] && !err; i++) err = sysfs_create_file(kobj, ptr[i]); if (err) while (--i >= 0) sysfs_remove_file(kobj, ptr[i]); return err; } EXPORT_SYMBOL_GPL(sysfs_create_files); /** * sysfs_add_file_to_group - add an attribute file to a pre-existing group. * @kobj: object we're acting for. * @attr: attribute descriptor. * @group: group name. */ int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { struct kernfs_node *parent; kuid_t uid; kgid_t gid; int error; if (group) { parent = kernfs_find_and_get(kobj->sd, group); } else { parent = kobj->sd; kernfs_get(parent); } if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); error = sysfs_add_file_mode_ns(parent, attr, attr->mode, uid, gid, NULL); kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); /** * sysfs_chmod_file - update the modified mode value on an object attribute. * @kobj: object we're acting for. * @attr: attribute descriptor. * @mode: file permissions. * */ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode) { struct kernfs_node *kn; struct iattr newattrs; int rc; kn = kernfs_find_and_get(kobj->sd, attr->name); if (!kn) return -ENOENT; newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE; rc = kernfs_setattr(kn, &newattrs); kernfs_put(kn); return rc; } EXPORT_SYMBOL_GPL(sysfs_chmod_file); /** * sysfs_break_active_protection - break "active" protection * @kobj: The kernel object @attr is associated with. * @attr: The attribute to break the "active" protection for. * * With sysfs, just like kernfs, deletion of an attribute is postponed until * all active .show() and .store() callbacks have finished unless this function * is called. Hence this function is useful in methods that implement self * deletion. */ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, const struct attribute *attr) { struct kernfs_node *kn; kobject_get(kobj); kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); /** * sysfs_unbreak_active_protection - restore "active" protection * @kn: Pointer returned by sysfs_break_active_protection(). * * Undo the effects of sysfs_break_active_protection(). Since this function * calls kernfs_put() on the kernfs node that corresponds to the 'attr' * argument passed to sysfs_break_active_protection() that attribute may have * been removed between the sysfs_break_active_protection() and * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after * this function has returned. */ void sysfs_unbreak_active_protection(struct kernfs_node *kn) { struct kobject *kobj = kn->parent->priv; kernfs_unbreak_active_protection(kn); kernfs_put(kn); kobject_put(kobj); } EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); /** * sysfs_remove_file_ns - remove an object attribute with a custom ns tag * @kobj: object we're acting for * @attr: attribute descriptor * @ns: namespace tag of the file to remove * * Hash the attribute name and namespace tag and kill the victim. */ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { struct kernfs_node *parent = kobj->sd; kernfs_remove_by_name_ns(parent, attr->name, ns); } EXPORT_SYMBOL_GPL(sysfs_remove_file_ns); /** * sysfs_remove_file_self - remove an object attribute from its own method * @kobj: object we're acting for * @attr: attribute descriptor * * See kernfs_remove_self() for details. */ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) { struct kernfs_node *parent = kobj->sd; struct kernfs_node *kn; bool ret; kn = kernfs_find_and_get(parent, attr->name); if (WARN_ON_ONCE(!kn)) return false; ret = kernfs_remove_self(kn); kernfs_put(kn); return ret; } EXPORT_SYMBOL_GPL(sysfs_remove_file_self); void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } EXPORT_SYMBOL_GPL(sysfs_remove_files); /** * sysfs_remove_file_from_group - remove an attribute file from a group. * @kobj: object we're acting for. * @attr: attribute descriptor. * @group: group name. */ void sysfs_remove_file_from_group(struct kobject *kobj, const struct attribute *attr, const char *group) { struct kernfs_node *parent; if (group) { parent = kernfs_find_and_get(kobj->sd, group); } else { parent = kobj->sd; kernfs_get(parent); } if (parent) { kernfs_remove_by_name(parent, attr->name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); /** * sysfs_create_bin_file - create binary file for object. * @kobj: object. * @attr: attribute descriptor. */ int sysfs_create_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { kuid_t uid; kgid_t gid; if (WARN_ON(!kobj || !kobj->sd || !attr)) return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_bin_file_mode_ns(kobj->sd, attr, attr->attr.mode, uid, gid, NULL); } EXPORT_SYMBOL_GPL(sysfs_create_bin_file); /** * sysfs_remove_bin_file - remove binary file for object. * @kobj: object. * @attr: attribute descriptor. */ void sysfs_remove_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); static int internal_change_owner(struct kernfs_node *kn, kuid_t kuid, kgid_t kgid) { struct iattr newattrs = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = kuid, .ia_gid = kgid, }; return kernfs_setattr(kn, &newattrs); } /** * sysfs_link_change_owner - change owner of a sysfs file. * @kobj: object of the kernfs_node the symlink is located in. * @targ: object of the kernfs_node the symlink points to. * @name: name of the link. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This function looks up the sysfs symlink entry @name under @kobj and changes * the ownership to @kuid/@kgid. The symlink is looked up in the namespace of * @targ. * * Returns 0 on success or error code on failure. */ int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, const char *name, kuid_t kuid, kgid_t kgid) { struct kernfs_node *kn = NULL; int error; if (!name || !kobj->state_in_sysfs || !targ->state_in_sysfs) return -EINVAL; error = -ENOENT; kn = kernfs_find_and_get_ns(kobj->sd, name, targ->sd->ns); if (!kn) goto out; error = -EINVAL; if (kernfs_type(kn) != KERNFS_LINK) goto out; if (kn->symlink.target_kn->priv != targ) goto out; error = internal_change_owner(kn, kuid, kgid); out: kernfs_put(kn); return error; } /** * sysfs_file_change_owner - change owner of a sysfs file. * @kobj: object. * @name: name of the file to change. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This function looks up the sysfs entry @name under @kobj and changes the * ownership to @kuid/@kgid. * * Returns 0 on success or error code on failure. */ int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, kgid_t kgid) { struct kernfs_node *kn; int error; if (!name) return -EINVAL; if (!kobj->state_in_sysfs) return -EINVAL; kn = kernfs_find_and_get(kobj->sd, name); if (!kn) return -ENOENT; error = internal_change_owner(kn, kuid, kgid); kernfs_put(kn); return error; } EXPORT_SYMBOL_GPL(sysfs_file_change_owner); /** * sysfs_change_owner - change owner of the given object. * @kobj: object. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Change the owner of the default directory, files, groups, and attributes of * @kobj to @kuid/@kgid. Note that sysfs_change_owner mirrors how the sysfs * entries for a kobject are added by driver core. In summary, * sysfs_change_owner() takes care of the default directory entry for @kobj, * the default attributes associated with the ktype of @kobj and the default * attributes associated with the ktype of @kobj. * Additional properties not added by driver core have to be changed by the * driver or subsystem which created them. This is similar to how * driver/subsystem specific entries are removed. * * Returns 0 on success or error code on failure. */ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) { int error; const struct kobj_type *ktype; if (!kobj->state_in_sysfs) return -EINVAL; /* Change the owner of the kobject itself. */ error = internal_change_owner(kobj->sd, kuid, kgid); if (error) return error; ktype = get_ktype(kobj); if (ktype) { /* * Change owner of the default groups associated with the * ktype of @kobj. */ error = sysfs_groups_change_owner(kobj, ktype->default_groups, kuid, kgid); if (error) return error; } return 0; } EXPORT_SYMBOL_GPL(sysfs_change_owner); /** * sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer. * @buf: start of PAGE_SIZE buffer. * @fmt: format * @...: optional arguments to @format * * * Returns number of characters written to @buf. */ int sysfs_emit(char *buf, const char *fmt, ...) { va_list args; int len; if (WARN(!buf || offset_in_page(buf), "invalid sysfs_emit: buf:%p\n", buf)) return 0; va_start(args, fmt); len = vscnprintf(buf, PAGE_SIZE, fmt, args); va_end(args); return len; } EXPORT_SYMBOL_GPL(sysfs_emit); /** * sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer. * @buf: start of PAGE_SIZE buffer. * @at: offset in @buf to start write in bytes * @at must be >= 0 && < PAGE_SIZE * @fmt: format * @...: optional arguments to @fmt * * * Returns number of characters written starting at &@buf[@at]. */ int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { va_list args; int len; if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE, "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at)) return 0; va_start(args, fmt); len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args); va_end(args); return len; } EXPORT_SYMBOL_GPL(sysfs_emit_at); |
| 185 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_UNALIGNED_H #define __ASM_GENERIC_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses * and should work almost anywhere. */ #include <linux/unaligned/packed_struct.h> #include <asm/byteorder.h> #define __get_unaligned_t(type, ptr) ({ \ const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ __pptr->x; \ }) #define __put_unaligned_t(type, val, ptr) do { \ struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ __pptr->x = (val); \ } while (0) #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) static inline u16 get_unaligned_le16(const void *p) { return le16_to_cpu(__get_unaligned_t(__le16, p)); } static inline u32 get_unaligned_le32(const void *p) { return le32_to_cpu(__get_unaligned_t(__le32, p)); } static inline u64 get_unaligned_le64(const void *p) { return le64_to_cpu(__get_unaligned_t(__le64, p)); } static inline void put_unaligned_le16(u16 val, void *p) { __put_unaligned_t(__le16, cpu_to_le16(val), p); } static inline void put_unaligned_le32(u32 val, void *p) { __put_unaligned_t(__le32, cpu_to_le32(val), p); } static inline void put_unaligned_le64(u64 val, void *p) { __put_unaligned_t(__le64, cpu_to_le64(val), p); } static inline u16 get_unaligned_be16(const void *p) { return be16_to_cpu(__get_unaligned_t(__be16, p)); } static inline u32 get_unaligned_be32(const void *p) { return be32_to_cpu(__get_unaligned_t(__be32, p)); } static inline u64 get_unaligned_be64(const void *p) { return be64_to_cpu(__get_unaligned_t(__be64, p)); } static inline void put_unaligned_be16(u16 val, void *p) { __put_unaligned_t(__be16, cpu_to_be16(val), p); } static inline void put_unaligned_be32(u32 val, void *p) { __put_unaligned_t(__be32, cpu_to_be32(val), p); } static inline void put_unaligned_be64(u64 val, void *p) { __put_unaligned_t(__be64, cpu_to_be64(val), p); } static inline u32 __get_unaligned_be24(const u8 *p) { return p[0] << 16 | p[1] << 8 | p[2]; } static inline u32 get_unaligned_be24(const void *p) { return __get_unaligned_be24(p); } static inline u32 __get_unaligned_le24(const u8 *p) { return p[0] | p[1] << 8 | p[2] << 16; } static inline u32 get_unaligned_le24(const void *p) { return __get_unaligned_le24(p); } static inline void __put_unaligned_be24(const u32 val, u8 *p) { *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) { __put_unaligned_be24(val, p); } static inline void __put_unaligned_le24(const u32 val, u8 *p) { *p++ = val & 0xff; *p++ = (val >> 8) & 0xff; *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) { __put_unaligned_le24(val, p); } static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = (val >> 40) & 0xff; *p++ = (val >> 32) & 0xff; *p++ = (val >> 24) & 0xff; *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) { __put_unaligned_be48(val, p); } static inline u64 __get_unaligned_be48(const u8 *p) { return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } static inline u64 get_unaligned_be48(const void *p) { return __get_unaligned_be48(p); } #endif /* __ASM_GENERIC_UNALIGNED_H */ |
| 597 1124 1118 345 333 314 7 281 4 7 162 128 967 472 472 472 470 139 141 471 4 220 193 472 190 472 185 500 500 472 162 139 139 139 162 4 162 12 155 125 151 8 138 138 366 337 336 137 996 997 337 337 778 597 597 597 5 5 1 25 25 60 29 32 143 143 161 162 130 130 339 339 778 2 2 708 704 704 4 4 2 469 470 470 1 1 143 143 162 162 130 130 339 339 777 | 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-or-later /* * net/core/dev_addr_lists.c - Functions for handling net device lists * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> * * This file contains functions for working with unicast, multicast and device * addresses lists. */ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/export.h> #include <linux/list.h> #include "dev.h" /* * General list handling functions */ static int __hw_addr_insert(struct netdev_hw_addr_list *list, struct netdev_hw_addr *new, int addr_len) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(new->addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&new->type, &ha->type, sizeof(new->type)); parent = *ins_point; if (diff < 0) ins_point = &parent->rb_left; else if (diff > 0) ins_point = &parent->rb_right; else return -EEXIST; } rb_link_node_rcu(&new->node, parent, ins_point); rb_insert_color(&new->node, &list->tree); return 0; } static struct netdev_hw_addr* __hw_addr_create(const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, int sync_count, bool exclusive) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); parent = *ins_point; if (diff < 0) { ins_point = &parent->rb_left; } else if (diff > 0) { ins_point = &parent->rb_right; } else { if (exclusive) return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) return 0; else ha->global_use = true; } if (sync) { if (ha->synced && sync_count) return -EEXIST; else ha->synced++; } ha->refcount++; return 0; } } ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); if (!ha) return -ENOMEM; rb_link_node(&ha->node, parent, ins_point); rb_insert_color(&ha->node, &list->tree); list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, struct netdev_hw_addr *ha, bool global, bool sync) { if (global && !ha->global_use) return -ENOENT; if (sync && !ha->synced) return -ENOENT; if (global) ha->global_use = false; if (sync) ha->synced--; if (--ha->refcount) return 0; rb_erase(&ha->node, &list->tree); list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { struct rb_node *node; node = list->tree.rb_node; while (node) { struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); int diff = memcmp(addr, ha->addr, addr_len); if (diff == 0 && addr_type) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); if (diff < 0) node = node->rb_left; else if (diff > 0) node = node->rb_right; else return ha; } return NULL; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); if (!ha) return -ENOENT; return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; if (!err) { ha->sync_cnt++; ha->refcount++; } return 0; } static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, false, true); if (err) return; ha->sync_cnt--; /* address on from list is not marked synced */ __hw_addr_del_entry(from_list, ha, false, false); } static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt == ha->refcount) { __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } else { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } } return err; } /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (!ha->sync_cnt) { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } else if (ha->refcount == 1) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } EXPORT_SYMBOL(__hw_addr_sync); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); /** * __hw_addr_sync_dev - Synchonize device's multicast list * @list: address list to syncronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address add/remove * notifications. The unsync function may be NULL in which case * the addresses requiring removal will simply be removed without * any notification to the device. **/ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; int err; /* first go through and flush out any stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt || ha->refcount != 1) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (ha->sync_cnt) continue; err = sync(dev, ha->addr); if (err) return err; ha->sync_cnt++; ha->refcount++; } return 0; } EXPORT_SYMBOL(__hw_addr_sync_dev); /** * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking * into account references * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address or reference on it should be added * @unsync: function to call if address or some reference on it should removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address or references on it * add/remove notifications. The unsync function may be NULL in which case * the addresses or references on it requiring removal will simply be * removed without any notification to the device. That is responsibility of * the driver to identify and distribute address or references on it between * internal address tables. **/ int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; int err, ref_cnt; /* first go through and flush out any unsynced/stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address is not used */ if ((ha->sync_cnt << 1) <= ha->refcount) continue; /* if fails defer unsyncing address */ ref_cnt = ha->refcount - ha->sync_cnt; if (unsync && unsync(dev, ha->addr, ref_cnt)) continue; ha->refcount = (ref_cnt << 1) + 1; ha->sync_cnt = ref_cnt; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync updated/new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address added or reused */ if ((ha->sync_cnt << 1) >= ha->refcount) continue; ref_cnt = ha->refcount - ha->sync_cnt; err = sync(dev, ha->addr, ref_cnt); if (err) return err; ha->refcount = ref_cnt << 1; ha->sync_cnt = ref_cnt; } return 0; } EXPORT_SYMBOL(__hw_addr_ref_sync_dev); /** * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on * it from device * @list: address list to remove synchronized addresses (references on it) from * @dev: device to sync * @unsync: function to call if address and references on it should be removed * * Remove all addresses that were added to the device by * __hw_addr_ref_sync_dev(). This function is intended to be called from the * ndo_stop or ndo_open functions on devices that require explicit address (or * references on it) add/remove notifications. If the unsync function pointer * is NULL then this function can be used to just reset the sync_cnt for the * addresses in the list. **/ void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr, ha->sync_cnt)) continue; ha->refcount -= ha->sync_cnt - 1; ha->sync_cnt = 0; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_ref_unsync_dev); /** * __hw_addr_unsync_dev - Remove synchronized addresses from device * @list: address list to remove synchronized addresses from * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by __hw_addr_sync_dev(). * This function is intended to be called from the ndo_stop or ndo_open * functions on devices that require explicit address add/remove * notifications. If the unsync function pointer is NULL then this function * can be used to just reset the sync_cnt for the addresses in the list. **/ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_unsync_dev); static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); } list->count = 0; } void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions */ /* Check that netdev->dev_addr is not written to directly as this would * break the rbtree layout. All changes should go thru dev_addr_set() and co. * Remove this check in mid-2024. */ void dev_addr_check(struct net_device *dev) { if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) return; netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); netdev_warn(dev, "Expected addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr_shadow); netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); } /** * dev_addr_flush - Flush device address list * @dev: device * * Flush device address list and reset ->dev_addr. * * The caller must hold the rtnl_mutex. */ void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; } /** * dev_addr_init - Init device address list * @dev: device * * Init device address list and create the first element, * used by ->dev_addr. * * The caller must hold the rtnl_mutex. */ int dev_addr_init(struct net_device *dev) { unsigned char addr[MAX_ADDR_LEN]; struct netdev_hw_addr *ha; int err; /* rtnl_mutex must be held here */ __hw_addr_init(&dev->dev_addrs); memset(addr, 0, sizeof(addr)); err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* * Get the first (previously created) address from the list * and set dev_addr pointer to this location. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); dev->dev_addr = ha->addr; } return err; } void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len) { struct netdev_hw_addr *ha; dev_addr_check(dev); ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); rb_erase(&ha->node, &dev->dev_addrs.tree); memcpy(&ha->addr[offset], addr, len); memcpy(&dev->dev_addr_shadow[offset], addr, len); WARN_ON(__hw_addr_insert(&dev->dev_addrs, ha, dev->addr_len)); } EXPORT_SYMBOL(dev_addr_mod); /** * dev_addr_add - Add a device address * @dev: device * @addr: address to add * @addr_type: address type * * Add a device address to the device or increase the reference count if * it already exists. * * The caller must hold the rtnl_mutex. */ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; ASSERT_RTNL(); err = dev_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_add); /** * dev_addr_del - Release a device address. * @dev: device * @addr: address to delete * @addr_type: address type * * Release reference to a device address and remove it from the device * if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; struct netdev_hw_addr *ha; ASSERT_RTNL(); /* * We can not remove the first address from the list because * dev->dev_addr points to that. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); if (!memcmp(ha->addr, addr, dev->addr_len) && ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_del); /* * Unicast list handling functions */ /** * dev_uc_add_excl - Add a global secondary unicast address * @dev: device * @addr: address to add */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add * * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add); /** * dev_uc_del - Release secondary unicast address. * @dev: device * @addr: address to delete * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_del); /** * dev_uc_sync - Synchronize device's unicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. This function assumes that * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** * dev_uc_sync_multiple - Synchronize device's unicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have been deleted from the source. The source device * must be locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. It allows for a single source * device to be synced to multiple destination devices. */ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync_multiple); /** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_uc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_uc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two * reasons: * 1) This is always called without any addr_list_lock, so as the * outermost one here, it must be 0. * 2) This is called by some callers after unlinking the upper device, * so the dev->lower_level becomes 1 again. * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or * larger. */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_uc_unsync); /** * dev_uc_flush - Flush unicast addresses * @dev: device * * Flush unicast addresses. */ void dev_uc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_uc_flush); /** * dev_uc_init - Init unicast address list * @dev: device * * Init unicast address list. */ void dev_uc_init(struct net_device *dev) { __hw_addr_init(&dev->uc); } EXPORT_SYMBOL(dev_uc_init); /* * Multicast list handling functions */ /** * dev_mc_add_excl - Add a global secondary multicast address * @dev: device * @addr: address to add */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_mc_add_excl); static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false, 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_add - Add a multicast address * @dev: device * @addr: address to add * * Add a multicast address to the device or increase * the reference count if it already exists. */ int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } EXPORT_SYMBOL(dev_mc_add); /** * dev_mc_add_global - Add a global multicast address * @dev: device * @addr: address to add * * Add a global multicast address to the device. */ int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_del - Delete a multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } EXPORT_SYMBOL(dev_mc_del); /** * dev_mc_del_global - Delete a global multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. It allows for a single * source device to be synced to multiple destination devices. */ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync_multiple); /** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_mc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_mc_unsync); /** * dev_mc_flush - Flush multicast addresses * @dev: device * * Flush multicast addresses. */ void dev_mc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->mc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_mc_flush); /** * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. */ void dev_mc_init(struct net_device *dev) { __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); |
| 33 33 1594 1594 1580 7012 7013 1594 233 1548 7013 7010 1589 7017 7017 1589 1589 1778 7017 1588 1589 1589 1559 1589 1589 1594 1594 1594 1594 7013 1589 7017 7014 2718 6468 33 1589 33 33 33 1589 1587 1544 1589 1589 7014 7016 7013 6751 5855 5859 7017 7017 7015 7011 1589 1559 1589 1589 1589 1588 1589 1589 1588 1559 1559 33 1559 1589 1559 1559 1559 1559 33 33 33 233 233 33 200 200 232 233 233 233 33 1592 33 1592 1592 1592 1592 1592 1592 1592 1592 1592 33 2353 2353 2354 1588 1588 2354 1594 2353 1592 2352 2354 2353 1594 1585 1139 1995 1588 1559 1559 1558 33 33 33 33 33 33 1580 1580 1580 33 33 33 33 232 233 33 33 233 233 1593 1594 1594 1594 1594 1594 1559 1558 1559 1559 1559 1559 1559 1559 1558 1559 1559 1559 6331 6329 6334 6330 9 946 948 6331 9 6331 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_BULK - Bulk insert mode * * MA_STATE_REBALANCE - Indicate a rebalance during bulk insert * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_BULK 1 #define MA_STATE_REBALANCE 2 #define MA_STATE_PREALLOC 4 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] #define MAPLE_BIG_NODE_SLOTS (MAPLE_RANGE64_SLOTS * 2 + 2) #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { struct maple_pnode *parent; unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; struct { unsigned long padding[MAPLE_BIG_NODE_GAPS]; unsigned long gap[MAPLE_BIG_NODE_GAPS]; }; }; unsigned char b_end; enum maple_type type; }; /* * The maple_subtree_state is used to build a tree to replace a segment of an * existing tree in a more atomic way. Any walkers of the older tree will hit a * dead node and restart on updates. */ struct maple_subtree_state { struct ma_state *orig_l; /* Original left side of subtree */ struct ma_state *orig_r; /* Original right side of subtree */ struct ma_state *l; /* New left side of subtree */ struct ma_state *m; /* New middle of subtree (rare) */ struct ma_state *r; /* New right side of subtree */ struct ma_topiary *free; /* nodes to be freed */ struct ma_topiary *destroy; /* Nodes to be destroyed (walked and freed) */ struct maple_big_node *bn; }; #ifdef CONFIG_KASAN_STACK /* Prevent mas_wr_bnode() from exceeding the stack frame limit */ #define noinline_for_kasan noinline_for_stack #else #define noinline_for_kasan inline #endif /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) { return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } static inline void mt_free_one(struct maple_node *node) { kmem_cache_free(maple_node_cache, node); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_free_rcu(struct rcu_head *head) { struct maple_node *node = container_of(head, struct maple_node, rcu); kmem_cache_free(maple_node_cache, node); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } static void mas_set_height(struct ma_state *mas) { unsigned int new_flags = mas->tree->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MAS_BUG_ON(mas, mas->depth > MAPLE_HEIGHT_MAX); new_flags |= mas->depth << MT_FLAGS_HEIGHT_OFFSET; mas->tree->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Note types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x04 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @node: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; node = mte_to_node(enode); /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = mte_parent(enode); return (parent == node); } /* * mas_allocated() - Get the number of nodes allocated in a maple state. * @mas: The maple state * * The ma_state alloc member is overloaded to hold a pointer to the first * allocated node or to the number of requested nodes to allocate. If bit 0 is * set, then the alloc contains the number of requested nodes. If there is an * allocated node, then the total allocated nodes is in that node. * * Return: The total number of nodes allocated */ static inline unsigned long mas_allocated(const struct ma_state *mas) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) return 0; return mas->alloc->total; } /* * mas_set_alloc_req() - Set the requested number of allocations. * @mas: the maple state * @count: the number of allocations. * * The requested number of allocations is either in the first allocated node, * located in @mas->alloc->request_count, or directly in @mas->alloc if there is * no allocated node. Set the request either in the node or do the necessary * encoding to store in @mas->alloc directly. */ static inline void mas_set_alloc_req(struct ma_state *mas, unsigned long count) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) { if (!count) mas->alloc = NULL; else mas->alloc = (struct maple_alloc *)(((count) << 1U) | 1U); return; } mas->alloc->request_count = count; } /* * mas_alloc_req() - get the requested number of allocations. * @mas: The maple state * * The alloc count is either stored directly in @mas, or in * @mas->alloc->request_count if there is at least one node allocated. Decode * the request count if it's stored directly in @mas->alloc. * * Return: The allocation request count. */ static inline unsigned int mas_alloc_req(const struct ma_state *mas) { if ((unsigned long)mas->alloc & 0x1) return (unsigned long)(mas->alloc) >> 1; else if (mas->alloc) return mas->alloc->request_count; return 0; } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node - the maple node * @type - the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node - the maple node * @type - the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mn: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat - the ma_topiary, a linked list of dead nodes. * @dead_enode - the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas - the maple state * @mat - the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas - the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mte_set_gap() - Set a maple node gap. * @mn: The encoded maple node * @gap: The offset of the gap to set * @val: The gap value */ static inline void mte_set_gap(const struct maple_enode *mn, unsigned char gap, unsigned long val) { switch (mte_node_type(mn)) { default: break; case maple_arange_64: mte_to_node(mn)->ma64.gap[gap] = val; break; } } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min to the correct values when walking up. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_alloc *ret, *node = mas->alloc; unsigned long total = mas_allocated(mas); unsigned int req = mas_alloc_req(mas); /* nothing or a request pending. */ if (WARN_ON(!total)) return NULL; if (total == 1) { /* single allocation in this ma_state */ mas->alloc = NULL; ret = node; goto single_node; } if (node->node_count == 1) { /* Single allocation in this node. */ mas->alloc = node->slot[0]; mas->alloc->total = node->total - 1; ret = node; goto new_head; } node->total--; ret = node->slot[--node->node_count]; node->slot[node->node_count] = NULL; single_node: new_head: if (req) { req++; mas_set_alloc_req(mas, req); } memset(ret, 0, sizeof(*ret)); return (struct maple_node *)ret; } /* * mas_push_node() - Push a node back on the maple state allocation. * @mas: The maple state * @used: The used maple node * * Stores the maple node back into @mas->alloc for reuse. Updates allocated and * requested node count as necessary. */ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) { struct maple_alloc *reuse = (struct maple_alloc *)used; struct maple_alloc *head = mas->alloc; unsigned long count; unsigned int requested = mas_alloc_req(mas); count = mas_allocated(mas); reuse->request_count = 0; reuse->node_count = 0; if (count && (head->node_count < MAPLE_ALLOC_SLOTS)) { head->slot[head->node_count++] = reuse; head->total++; goto done; } reuse->total = 1; if ((head) && !((unsigned long)head & 0x1)) { reuse->slot[0] = head; reuse->node_count = 1; reuse->total += head->total; } mas->alloc = reuse; done: if (requested > 1) mas_set_alloc_req(mas, requested - 1); } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { struct maple_alloc *node; unsigned long allocated = mas_allocated(mas); unsigned int requested = mas_alloc_req(mas); unsigned int count; void **slots = NULL; unsigned int max_req = 0; if (!requested) return; mas_set_alloc_req(mas, 0); if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; BUG_ON(!allocated); WARN_ON(!allocated); } if (!allocated || mas->alloc->node_count == MAPLE_ALLOC_SLOTS) { node = (struct maple_alloc *)mt_alloc_one(gfp); if (!node) goto nomem_one; if (allocated) { node->slot[0] = mas->alloc; node->node_count = 1; } else { node->node_count = 0; } mas->alloc = node; node->total = ++allocated; requested--; } node = mas->alloc; node->request_count = 0; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; max_req = min(requested, max_req); count = mt_alloc_bulk(gfp, max_req, slots); if (!count) goto nomem_bulk; if (node->node_count == 0) { node->slot[0]->node_count = 0; node->slot[0]->request_count = 0; } node->node_count += count; allocated += count; node = node->slot[0]; requested -= count; } mas->alloc->total = allocated; return; nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); nomem_one: mas_set_alloc_req(mas, requested); if (mas->alloc && !(((unsigned long)mas->alloc & 0x1))) mas->alloc->total = allocated; mas_set_err(mas, -ENOMEM); } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { struct maple_node *tmp = mte_to_node(used); if (mt_in_rcu(mas->tree)) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_node_count() - Check if enough nodes are allocated and request more if * there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * @gfp: the gfp flags */ static void mas_node_count_gfp(struct ma_state *mas, int count, gfp_t gfp) { unsigned long allocated = mas_allocated(mas); if (allocated < count) { mas_set_alloc_req(mas, count - allocated); mas_alloc_nodes(mas, gfp); } } /* * mas_node_count() - Check if enough nodes are allocated and request more if * there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * * Note: Uses GFP_NOWAIT | __GFP_NOWARN for gfp flags. */ static void mas_node_count(struct ma_state *mas, int count) { return mas_node_count_gfp(mas, count, GFP_NOWAIT | __GFP_NOWARN); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == mas_root * - If it's a tree: NULL & mas->status == safe root node. */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } /* empty tree */ if (unlikely(!root)) { mas->node = NULL; mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas - the maple state * * Return: The maximum gap in the leaf. */ static unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; unsigned long pstart, gap, max_gap; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; unsigned char i; unsigned char max_piv; mt = mte_node_type(mas->node); mn = mas_mn(mas); slots = ma_slots(mn, mt); max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ pivots = ma_pivots(mn, mt); if (likely(!slots[0])) { max_gap = pivots[0] - mas->min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, mas->max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(mas->max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - mas->min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @*off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas - the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas - the maple state (for the tree) * @parent - the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas - the maple state with the new node * @old_enode - The old maple encoded node to replace. */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mas_set_height(mas); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas - the ma_state with @mas->node pointing to the new node. * @old_enode - The old maple encoded node. */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mab_shift_right() - Shift the data in mab right. Note, does not clean out the * old data or set b_node->b_end. * @b_node: the maple_big_node * @shift: the shift count */ static inline void mab_shift_right(struct maple_big_node *b_node, unsigned char shift) { unsigned long size = b_node->b_end * sizeof(unsigned long); memmove(b_node->pivot + shift, b_node->pivot, size); memmove(b_node->slot + shift, b_node->slot, size); if (b_node->type == maple_arange_64) memmove(b_node->gap + shift, b_node->gap, size); } /* * mab_middle_node() - Check if a middle node is needed (unlikely) * @b_node: the maple_big_node that contains the data. * @size: the amount of data in the b_node * @split: the potential split location * @slot_count: the size that can be stored in a single node being considered. * * Return: true if a middle node is required. */ static inline bool mab_middle_node(struct maple_big_node *b_node, int split, unsigned char slot_count) { unsigned char size = b_node->b_end; if (size >= 2 * slot_count) return true; if (!b_node->slot[split] && (size >= 2 * slot_count - 1)) return true; return false; } /* * mab_no_null_split() - ensure the split doesn't fall on a NULL * @b_node: the maple_big_node with the data * @split: the suggested split location * @slot_count: the number of slots in the node being considered. * * Return: the split location. */ static inline int mab_no_null_split(struct maple_big_node *b_node, unsigned char split, unsigned char slot_count) { if (!b_node->slot[split]) { /* * If the split is less than the max slot && the right side will * still be sufficient, then increment the split on NULL. */ if ((split < slot_count - 1) && (b_node->b_end - split) > (mt_min_slots[b_node->type])) split++; else split--; } return split; } /* * mab_calc_split() - Calculate the split location and if there needs to be two * splits. * @bn: The maple_big_node with the data * @mid_split: The second split, if required. 0 otherwise. * * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ unsigned char slot_min, slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot * end on a NULL entry, with the exception of the left-most leaf. The * limitation means that the split of a node must be checked for this condition * and be able to put more data in one direction or the other. */ if (unlikely((mas->mas_flags & MA_STATE_BULK))) { *mid_split = 0; split = b_end - mt_min_slots[bn->type]; if (!ma_is_leaf(bn->type)) return split; mas->mas_flags |= MA_STATE_REBALANCE; if (!bn->slot[split]) split--; return split; } /* * Although extremely rare, it is possible to enter what is known as the 3-way * split scenario. The 3-way split comes about by means of a store of a range * that overwrites the end and beginning of two full nodes. The result is a set * of entries that cannot be stored in 2 nodes. Sometimes, these two nodes can * also be located in different parent nodes which are also full. This can * carry upwards all the way to the root in the worst case. */ if (unlikely(mab_middle_node(bn, split, slot_count))) { split = b_end / 3; *mid_split = split * 2; } else { slot_min = mt_min_slots[bn->type]; *mid_split = 0; /* * Avoid having a range less than the slot count unless it * causes one node to be deficient. * NOTE: mt_min_slots is 1 based, b_end and split are zero. */ while ((split < slot_count - 1) && ((bn->pivot[split] - min) < slot_count - 1) && (b_end - split > slot_min)) split++; } /* Avoid ending a node on a NULL entry */ split = mab_no_null_split(bn, split, slot_count); if (unlikely(*mid_split)) *mid_split = mab_no_null_split(bn, *mid_split, slot_count); return split; } /* * mas_mab_cp() - Copy data from a maple state inclusively to a maple_big_node * and set @b_node->b_end to the next free slot. * @mas: The maple state * @mas_start: The starting slot to copy * @mas_end: The end slot to copy (inclusively) * @b_node: The maple_big_node to place the data * @mab_start: The starting location in maple_big_node to store the data. */ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, unsigned char mas_end, struct maple_big_node *b_node, unsigned char mab_start) { enum maple_type mt; struct maple_node *node; void __rcu **slots; unsigned long *pivots, *gaps; int i = mas_start, j = mab_start; unsigned char piv_end; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); if (!i) { b_node->pivot[j] = pivots[i++]; if (unlikely(i > mas_end)) goto complete; j++; } piv_end = min(mas_end, mt_pivots[mt]); for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) break; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } if (likely(i <= mas_end)) b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; j -= mab_start; slots = ma_slots(node, mt); memcpy(b_node->slot + mab_start, slots + mas_start, sizeof(void *) * j); if (!ma_is_leaf(mt) && mt_is_alloc(mas->tree)) { gaps = ma_gaps(node, mt); memcpy(b_node->gap + mab_start, gaps + mas_start, sizeof(unsigned long) * j); } } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mab_mas_cp() - Copy data from maple_big_node to a maple encoded node. * @b_node: the maple_big_node that has the data * @mab_start: the start location in @b_node. * @mab_end: The end location in @b_node (inclusively) * @mas: The maple state with the maple encoded node. */ static inline void mab_mas_cp(struct maple_big_node *b_node, unsigned char mab_start, unsigned char mab_end, struct ma_state *mas, bool new_max) { int i, j = 0; enum maple_type mt = mte_node_type(mas->node); struct maple_node *node = mte_to_node(mas->node); void __rcu **slots = ma_slots(node, mt); unsigned long *pivots = ma_pivots(node, mt); unsigned long *gaps = NULL; unsigned char end; if (mab_end - mab_start > mt_pivots[mt]) mab_end--; if (!pivots[mt_pivots[mt] - 1]) slots[mt_pivots[mt]] = NULL; i = mab_start; do { pivots[j++] = b_node->pivot[i++]; } while (i <= mab_end && likely(b_node->pivot[i])); memcpy(slots, b_node->slot + mab_start, sizeof(void *) * (i - mab_start)); if (new_max) mas->max = b_node->pivot[i - 1]; end = j - 1; if (likely(!ma_is_leaf(mt) && mt_is_alloc(mas->tree))) { unsigned long max_gap = 0; unsigned char offset = 0; gaps = ma_gaps(node, mt); do { gaps[--j] = b_node->gap[--i]; if (gaps[j] > max_gap) { offset = j; max_gap = gaps[j]; } } while (j); ma_set_meta(node, mt, offset, end); } else { mas_leaf_set_meta(node, mt, end); } } /* * mas_bulk_rebalance() - Rebalance the end of a tree after a bulk insert. * @mas: The maple state * @end: The maple node end * @mt: The maple node type */ static inline void mas_bulk_rebalance(struct ma_state *mas, unsigned char end, enum maple_type mt) { if (!(mas->mas_flags & MA_STATE_BULK)) return; if (mte_is_root(mas->node)) return; if (end > mt_min_slots[mt]) { mas->mas_flags &= ~MA_STATE_REBALANCE; return; } } /* * mas_store_b_node() - Store an @entry into the b_node while also copying the * data from a maple encoded node. * @wr_mas: the maple write state * @b_node: the maple_big_node to fill with data * @offset_end: the offset to end copying * * Return: The actual end of the data stored in @b_node */ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node, unsigned char offset_end) { unsigned char slot; unsigned char b_end; /* Possible underflow of piv will wrap back to 0 before use. */ unsigned long piv; struct ma_state *mas = wr_mas->mas; b_node->type = wr_mas->type; b_end = 0; slot = mas->offset; if (slot) { /* Copy start data up to insert. */ mas_mab_cp(mas, 0, slot - 1, b_node, 0); b_end = b_node->b_end; piv = b_node->pivot[b_end - 1]; } else piv = mas->min - 1; if (piv + 1 < mas->index) { /* Handle range starting after old range */ b_node->slot[b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = mas->index - 1 - piv; b_node->pivot[b_end++] = mas->index - 1; } /* Store the new entry. */ mas->offset = b_end; b_node->slot[b_end] = wr_mas->entry; b_node->pivot[b_end] = mas->last; /* Appended. */ if (mas->last >= mas->max) goto b_end; /* Handle new range ending before old range ends */ piv = mas_safe_pivot(mas, wr_mas->pivots, offset_end, wr_mas->type); if (piv > mas->last) { if (piv == ULONG_MAX) mas_bulk_rebalance(mas, b_node->b_end, wr_mas->type); if (offset_end != slot) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, offset_end); b_node->slot[++b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = piv - mas->last + 1; b_node->pivot[b_end] = piv; } slot = offset_end + 1; if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; b_end: b_node->b_end = b_end; } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); if (mte_is_root(mas->node)) return false; if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mte_node_or_none() - Set the enode and state. * @enode: The encoded maple node. * * Set the node to the enode and the status. */ static inline void mas_node_or_none(struct ma_state *mas, struct maple_enode *enode) { if (enode) { mas->node = enode; mas->status = ma_active; } else { mas->node = NULL; mas->status = ma_none; } } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } /* * mast_rebalance_next() - Rebalance against the next node * @mast: The maple subtree state * @old_r: The encoded maple node to the right (next node). */ static inline void mast_rebalance_next(struct maple_subtree_state *mast) { unsigned char b_end = mast->bn->b_end; mas_mab_cp(mast->orig_r, 0, mt_slot_count(mast->orig_r->node), mast->bn, b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_rebalance_prev() - Rebalance against the previous node * @mast: The maple subtree state * @old_l: The encoded maple node to the left (previous node) */ static inline void mast_rebalance_prev(struct maple_subtree_state *mast) { unsigned char end = mas_data_end(mast->orig_l) + 1; unsigned char b_end = mast->bn->b_end; mab_shift_right(mast->bn, end); mas_mab_cp(mast->orig_l, 0, end - 1, mast->bn, 0); mast->l->min = mast->orig_l->min; mast->orig_l->index = mast->orig_l->min; mast->bn->b_end = end + b_end; mast->l->offset += end; } /* * mast_spanning_rebalance() - Rebalance nodes with nearest neighbour favouring * the node to the right. Checking the nodes to the right then the left at each * level upwards until root is reached. * Data is copied into the @mast->bn. * @mast: The maple_subtree_state. */ static inline bool mast_spanning_rebalance(struct maple_subtree_state *mast) { struct ma_state r_tmp = *mast->orig_r; struct ma_state l_tmp = *mast->orig_l; unsigned char depth = 0; r_tmp = *mast->orig_r; l_tmp = *mast->orig_l; do { mas_ascend(mast->orig_r); mas_ascend(mast->orig_l); depth++; if (mast->orig_r->offset < mas_data_end(mast->orig_r)) { mast->orig_r->offset++; do { mas_descend(mast->orig_r); mast->orig_r->offset = 0; } while (--depth); mast_rebalance_next(mast); *mast->orig_l = l_tmp; return true; } else if (mast->orig_l->offset != 0) { mast->orig_l->offset--; do { mas_descend(mast->orig_l); mast->orig_l->offset = mas_data_end(mast->orig_l); } while (--depth); mast_rebalance_prev(mast); *mast->orig_r = r_tmp; return true; } } while (!mte_is_root(mast->orig_r->node)); *mast->orig_r = r_tmp; *mast->orig_l = l_tmp; return false; } /* * mast_ascend() - Ascend the original left and right maple states. * @mast: the maple subtree state. * * Ascend the original left and right sides. Set the offsets to point to the * data already in the new tree (@mast->l and @mast->r). */ static inline void mast_ascend(struct maple_subtree_state *mast) { MA_WR_STATE(wr_mas, mast->orig_r, NULL); mas_ascend(mast->orig_l); mas_ascend(mast->orig_r); mast->orig_r->offset = 0; mast->orig_r->index = mast->r->max; /* last should be larger than or equal to index */ if (mast->orig_r->last < mast->orig_r->index) mast->orig_r->last = mast->orig_r->index; wr_mas.type = mte_node_type(mast->orig_r->node); mas_wr_node_walk(&wr_mas); /* Set up the left side of things */ mast->orig_l->offset = 0; mast->orig_l->index = mast->l->min; wr_mas.mas = mast->orig_l; wr_mas.type = mte_node_type(mast->orig_l->node); mas_wr_node_walk(&wr_mas); mast->bn->type = wr_mas.type; } /* * mas_new_ma_node() - Create and return a new maple node. Helper function. * @mas: the maple state with the allocations. * @b_node: the maple_big_node with the type encoding. * * Use the node type from the maple_big_node to allocate a new node from the * ma_state. This function exists mainly for code readability. * * Return: A new maple encoded node */ static inline struct maple_enode *mas_new_ma_node(struct ma_state *mas, struct maple_big_node *b_node) { return mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), b_node->type); } /* * mas_mab_to_node() - Set up right and middle nodes * * @mas: the maple state that contains the allocations. * @b_node: the node which contains the data. * @left: The pointer which will have the left node * @right: The pointer which may have the right node * @middle: the pointer which may have the middle node (rare) * @mid_split: the split location for the middle node * * Return: the split of left. */ static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, unsigned char *mid_split, unsigned long min) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; *left = mas_new_ma_node(mas, b_node); *right = NULL; *middle = NULL; *mid_split = 0; if (b_node->b_end < slot_count) { split = b_node->b_end; } else { split = mab_calc_split(mas, b_node, mid_split, min); *right = mas_new_ma_node(mas, b_node); } if (*mid_split) *middle = mas_new_ma_node(mas, b_node); return split; } /* * mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end * pointer. * @b_node - the big node to add the entry * @mas - the maple state to get the pivot (mas->max) * @entry - the entry to add, if NULL nothing happens. */ static inline void mab_set_b_end(struct maple_big_node *b_node, struct ma_state *mas, void *entry) { if (!entry) return; b_node->slot[b_node->b_end] = entry; if (mt_is_alloc(mas->tree)) b_node->gap[b_node->b_end] = mas_max_gap(mas); b_node->pivot[b_node->b_end++] = mas->max; } /* * mas_set_split_parent() - combine_then_separate helper function. Sets the parent * of @mas->node to either @left or @right, depending on @slot and @split * * @mas - the maple state with the node that needs a parent * @left - possible parent 1 * @right - possible parent 2 * @slot - the slot the mas->node was placed * @split - the split location between @left and @right */ static inline void mas_set_split_parent(struct ma_state *mas, struct maple_enode *left, struct maple_enode *right, unsigned char *slot, unsigned char split) { if (mas_is_none(mas)) return; if ((*slot) <= split) mas_set_parent(mas, mas->node, left, *slot); else if (right) mas_set_parent(mas, mas->node, right, (*slot) - split - 1); (*slot)++; } /* * mte_mid_split_check() - Check if the next node passes the mid-split * @**l: Pointer to left encoded maple node. * @**m: Pointer to middle encoded maple node. * @**r: Pointer to right encoded maple node. * @slot: The offset * @*split: The split location. * @mid_split: The middle split. */ static inline void mte_mid_split_check(struct maple_enode **l, struct maple_enode **r, struct maple_enode *right, unsigned char slot, unsigned char *split, unsigned char mid_split) { if (*r == right) return; if (slot < mid_split) return; *l = *r; *r = right; *split = mid_split; } /* * mast_set_split_parents() - Helper function to set three nodes parents. Slot * is taken from @mast->l. * @mast - the maple subtree state * @left - the left node * @right - the right node * @split - the split location. */ static inline void mast_set_split_parents(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { unsigned char slot; struct maple_enode *l = left; struct maple_enode *r = right; if (mas_is_none(mast->l)) return; if (middle) r = middle; slot = mast->l->offset; mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->l, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->m, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->r, l, r, &slot, split); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @enode: The encoded maple node * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @old: The old maple encoded node that is being replaced. * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_enode *old_enode) { /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode); if (mte_is_leaf(mas->node)) return; mas_update_gap(mas); } /* * mast_cp_to_nodes() - Copy data out to nodes. * @mast: The maple subtree state * @left: The left encoded maple node * @middle: The middle encoded maple node * @right: The right encoded maple node * @split: The location to split between left and (middle ? middle : right) * @mid_split: The location to split between middle and right. */ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { bool new_lmax = true; mas_node_or_none(mast->l, left); mas_node_or_none(mast->m, middle); mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { mast->l->max = mast->orig_r->max; new_lmax = false; } mab_mas_cp(mast->bn, 0, split, mast->l, new_lmax); if (middle) { mab_mas_cp(mast->bn, 1 + split, mid_split, mast->m, true); mast->m->min = mast->bn->pivot[split] + 1; split = mid_split; } mast->r->max = mast->orig_r->max; if (right) { mab_mas_cp(mast->bn, 1 + split, mast->bn->b_end, mast->r, false); mast->r->min = mast->bn->pivot[split] + 1; } } /* * mast_combine_cp_left - Copy in the original left side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_left(struct maple_subtree_state *mast) { unsigned char l_slot = mast->orig_l->offset; if (!l_slot) return; mas_mab_cp(mast->orig_l, 0, l_slot - 1, mast->bn, 0); } /* * mast_combine_cp_right: Copy in the original right side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_right(struct maple_subtree_state *mast) { if (mast->bn->pivot[mast->bn->b_end - 1] >= mast->orig_r->max) return; mas_mab_cp(mast->orig_r, mast->orig_r->offset + 1, mt_slot_count(mast->orig_r->node), mast->bn, mast->bn->b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_sufficient: Check if the maple subtree state has enough data in the big * node to create at least one sufficient node * @mast: the maple subtree state */ static inline bool mast_sufficient(struct maple_subtree_state *mast) { if (mast->bn->b_end > mt_min_slot_count(mast->orig_l->node)) return true; return false; } /* * mast_overflow: Check if there is too much data in the subtree state for a * single node. * @mast: The maple subtree state */ static inline bool mast_overflow(struct maple_subtree_state *mast) { if (mast->bn->b_end >= mt_slot_count(mast->orig_l->node)) return true; return false; } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_spanning_rebalance() - Rebalance across two nodes which may not be peers. * @mas: The starting maple state * @mast: The maple_subtree_state, keeps track of 4 maple states. * @count: The estimated count of iterations needed. * * Follow the tree upwards from @l_mas and @r_mas for @count, or until the root * is hit. First @b_node is split into two entries which are inserted into the * next iteration of the loop. @b_node is returned populated with the final * iteration. @mas is used to obtain allocations. orig_l_mas keeps track of the * nodes that will remain active by using orig_l_mas->index and orig_l_mas->last * to account of what has been copied into the new sub-tree. The update of * orig_l_mas->last is used in mas_consume to find the slots that will need to * be either freed or destroyed. orig_l_mas->depth keeps track of the height of * the new sub-tree in case the sub-tree becomes the full tree. * * Return: the number of elements in b_node during the last loop. */ static int mas_spanning_rebalance(struct ma_state *mas, struct maple_subtree_state *mast, unsigned char count) { unsigned char split, mid_split; unsigned char slot = 0; struct maple_enode *left = NULL, *middle = NULL, *right = NULL; struct maple_enode *old_enode; MA_STATE(l_mas, mas->tree, mas->index, mas->index); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(m_mas, mas->tree, mas->index, mas->index); /* * The tree needs to be rebalanced and leaves need to be kept at the same level. * Rebalancing is done by use of the ``struct maple_topiary``. */ mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && unlikely(mast->bn->b_end <= mt_min_slots[mast->bn->type])) mast_spanning_rebalance(mast); l_mas.depth = 0; /* * Each level of the tree is examined and balanced, pushing data to the left or * right, or rebalancing against left or right nodes is employed to avoid * rippling up the tree to limit the amount of churn. Once a new sub-section of * the tree is created, there may be a mix of new and old nodes. The old nodes * will have the incorrect parent pointers and currently be in two trees: the * original tree and the partially new tree. To remedy the parent pointers in * the old tree, the new data is swapped into the active tree and a walk down * the tree is performed and the parent pointers are updated. * See mas_topiary_replace() for more information. */ while (count--) { mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, &mid_split, mast->orig_l->min); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); /* * Copy data from next level in the tree to mast->bn from next * iteration */ memset(mast->bn, 0, sizeof(struct maple_big_node)); mast->bn->type = mte_node_type(left); l_mas.depth++; /* Root already stored in l->node. */ if (mas_is_root_limits(mast->l)) goto new_root; mast_ascend(mast); mast_combine_cp_left(mast); l_mas.offset = mast->bn->b_end; mab_set_b_end(mast->bn, &l_mas, left); mab_set_b_end(mast->bn, &m_mas, middle); mab_set_b_end(mast->bn, &r_mas, right); /* Copy anything necessary out of the right node. */ mast_combine_cp_right(mast); mast->orig_l->last = mast->orig_l->max; if (mast_sufficient(mast)) continue; if (mast_overflow(mast)) continue; /* May be a new root stored in mast->bn */ if (mas_is_root_limits(mast->orig_l)) break; mast_spanning_rebalance(mast); /* rebalancing from other nodes may require another loop. */ if (!count) count++; } l_mas.node = mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), mte_node_type(mast->orig_l->node)); l_mas.depth++; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, &l_mas, true); mas_set_parent(mas, left, l_mas.node, slot); if (middle) mas_set_parent(mas, middle, l_mas.node, ++slot); if (right) mas_set_parent(mas, right, l_mas.node, ++slot); if (mas_is_root_limits(mast->l)) { new_root: mas_mn(mast->l)->parent = ma_parent_ptr(mas_tree_parent(mas)); while (!mte_is_root(mast->orig_l->node)) mast_ascend(mast); } else { mas_mn(&l_mas)->parent = mas_mn(mast->orig_l)->parent; } old_enode = mast->orig_l->node; mas->depth = l_mas.depth; mas->node = l_mas.node; mas->min = l_mas.min; mas->max = l_mas.max; mas->offset = l_mas.offset; mas_wmb_replace(mas, old_enode); mtree_range_walk(mas); return mast->bn->b_end; } /* * mas_rebalance() - Rebalance a given node. * @mas: The maple state * @b_node: The big maple node. * * Rebalance two nodes into a single node or two new nodes that are sufficient. * Continue upwards until tree is sufficient. * * Return: the number of elements in b_node during the last loop. */ static inline int mas_rebalance(struct ma_state *mas, struct maple_big_node *b_node) { char empty_count = mas_mt_height(mas); struct maple_subtree_state mast; unsigned char shift, b_end = ++b_node->b_end; MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mas_node_count(mas, empty_count * 2 - 1); if (mas_is_err(mas)) return 0; mast.orig_l = &l_mas; mast.orig_r = &r_mas; mast.bn = b_node; mast.bn->type = mte_node_type(mas->node); l_mas = r_mas = *mas; if (mas_next_sibling(&r_mas)) { mas_mab_cp(&r_mas, 0, mt_slot_count(r_mas.node), b_node, b_end); r_mas.last = r_mas.index = r_mas.max; } else { mas_prev_sibling(&l_mas); shift = mas_data_end(&l_mas) + 1; mab_shift_right(b_node, shift); mas->offset += shift; mas_mab_cp(&l_mas, 0, shift - 1, b_node, 0); b_node->b_end = shift + b_end; l_mas.index = l_mas.last = l_mas.min; } return mas_spanning_rebalance(mas, &mast, empty_count); } /* * mas_destroy_rebalance() - Rebalance left-most node while destroying the maple * state. * @mas: The maple state * @end: The end of the left-most node. * * During a mass-insert event (such as forking), it may be necessary to * rebalance the left-most node when it is not sufficient. */ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end) { enum maple_type mt = mte_node_type(mas->node); struct maple_node reuse, *newnode, *parent, *new_left, *left, *node; struct maple_enode *eparent, *old_eparent; unsigned char offset, tmp, split = mt_slots[mt] / 2; void __rcu **l_slots, **slots; unsigned long *l_pivs, *pivs, gap; bool in_rcu = mt_in_rcu(mas->tree); MA_STATE(l_mas, mas->tree, mas->index, mas->last); l_mas = *mas; mas_prev_sibling(&l_mas); /* set up node. */ if (in_rcu) { /* Allocate for both left and right as well as parent. */ mas_node_count(mas, 3); if (mas_is_err(mas)) return; newnode = mas_pop_node(mas); } else { newnode = &reuse; } node = mas_mn(mas); newnode->parent = node->parent; slots = ma_slots(newnode, mt); pivs = ma_pivots(newnode, mt); left = mas_mn(&l_mas); l_slots = ma_slots(left, mt); l_pivs = ma_pivots(left, mt); if (!l_slots[split]) split++; tmp = mas_data_end(&l_mas) - split; memcpy(slots, l_slots + split + 1, sizeof(void *) * tmp); memcpy(pivs, l_pivs + split + 1, sizeof(unsigned long) * tmp); pivs[tmp] = l_mas.max; memcpy(slots + tmp, ma_slots(node, mt), sizeof(void *) * end); memcpy(pivs + tmp, ma_pivots(node, mt), sizeof(unsigned long) * end); l_mas.max = l_pivs[split]; mas->min = l_mas.max + 1; old_eparent = mt_mk_node(mte_parent(l_mas.node), mas_parent_type(&l_mas, l_mas.node)); tmp += end; if (!in_rcu) { unsigned char max_p = mt_pivots[mt]; unsigned char max_s = mt_slots[mt]; if (tmp < max_p) memset(pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp)); memcpy(node, newnode, sizeof(struct maple_node)); ma_set_meta(node, mt, 0, tmp - 1); mte_set_pivot(old_eparent, mte_parent_slot(l_mas.node), l_pivs[split]); /* Remove data from l_pivs. */ tmp = split + 1; memset(l_pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); memset(l_slots + tmp, 0, sizeof(void *) * (max_s - tmp)); ma_set_meta(left, mt, 0, split); eparent = old_eparent; goto done; } /* RCU requires replacing both l_mas, mas, and parent. */ mas->node = mt_mk_node(newnode, mt); ma_set_meta(newnode, mt, 0, tmp); new_left = mas_pop_node(mas); new_left->parent = left->parent; mt = mte_node_type(l_mas.node); slots = ma_slots(new_left, mt); pivs = ma_pivots(new_left, mt); memcpy(slots, l_slots, sizeof(void *) * split); memcpy(pivs, l_pivs, sizeof(unsigned long) * split); ma_set_meta(new_left, mt, 0, split); l_mas.node = mt_mk_node(new_left, mt); /* replace parent. */ offset = mte_parent_slot(mas->node); mt = mas_parent_type(&l_mas, l_mas.node); parent = mas_pop_node(mas); slots = ma_slots(parent, mt); pivs = ma_pivots(parent, mt); memcpy(parent, mte_to_node(old_eparent), sizeof(struct maple_node)); rcu_assign_pointer(slots[offset], mas->node); rcu_assign_pointer(slots[offset - 1], l_mas.node); pivs[offset - 1] = l_mas.max; eparent = mt_mk_node(parent, mt); done: gap = mas_leaf_max_gap(mas); mte_set_gap(eparent, mte_parent_slot(mas->node), gap); gap = mas_leaf_max_gap(&l_mas); mte_set_gap(eparent, mte_parent_slot(l_mas.node), gap); mas_ascend(mas); if (in_rcu) { mas_replace_node(mas, old_eparent); mas_adopt_children(mas, mas->node); } mas_update_gap(mas); } /* * mas_split_final_node() - Split the final node in a subtree operation. * @mast: the maple subtree state * @mas: The maple state * @height: The height of the tree in case it's a new root. */ static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; if (mte_is_root(mas->node)) { if (mt_is_alloc(mas->tree)) mast->bn->type = maple_arange_64; else mast->bn->type = maple_range_64; mas->depth = height; } /* * Only a single node is used here, could be root. * The Big_node data should just fit in a single node. */ ancestor = mas_new_ma_node(mas, mast->bn); mas_set_parent(mas, mast->l->node, ancestor, mast->l->offset); mas_set_parent(mas, mast->r->node, ancestor, mast->r->offset); mte_to_node(ancestor)->parent = mas_mn(mas)->parent; mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; } /* * mast_fill_bnode() - Copy data into the big node in the subtree state * @mast: The maple subtree state * @mas: the maple state * @skip: The number of entries to skip for new nodes insertion. */ static inline void mast_fill_bnode(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char skip) { bool cp = true; unsigned char split; memset(mast->bn->gap, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->gap)); memset(mast->bn->slot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->slot)); memset(mast->bn->pivot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->pivot)); mast->bn->b_end = 0; if (mte_is_root(mas->node)) { cp = false; } else { mas_ascend(mas); mas->offset = mte_parent_slot(mas->node); } if (cp && mast->l->offset) mas_mab_cp(mas, 0, mast->l->offset - 1, mast->bn, 0); split = mast->bn->b_end; mab_set_b_end(mast->bn, mast->l, mast->l->node); mast->r->offset = mast->bn->b_end; mab_set_b_end(mast->bn, mast->r, mast->r->node); if (mast->bn->pivot[mast->bn->b_end - 1] == mas->max) cp = false; if (cp) mas_mab_cp(mas, split + skip, mt_slot_count(mas->node) - 1, mast->bn, mast->bn->b_end); mast->bn->b_end--; mast->bn->type = mte_node_type(mas->node); } /* * mast_split_data() - Split the data in the subtree state big node into regular * nodes. * @mast: The maple subtree state * @mas: The maple state * @split: The location to split the big node */ static inline void mast_split_data(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char split) { unsigned char p_slot; mab_mas_cp(mast->bn, 0, split, mast->l, true); mte_set_pivot(mast->r->node, 0, mast->r->max); mab_mas_cp(mast->bn, split + 1, mast->bn->b_end, mast->r, false); mast->l->offset = mte_parent_slot(mas->node); mast->l->max = mast->bn->pivot[split]; mast->r->min = mast->l->max + 1; if (mte_is_leaf(mas->node)) return; p_slot = mast->orig_l->offset; mas_set_split_parent(mast->orig_l, mast->l->node, mast->r->node, &p_slot, split); mas_set_split_parent(mast->orig_r, mast->l->node, mast->r->node, &p_slot, split); } /* * mas_push_data() - Instead of splitting a node, it is beneficial to push the * data to the right or left node if there is room. * @mas: The maple state * @height: The current height of the maple state * @mast: The maple subtree state * @left: Push left or not. * * Keeping the height of the tree low means faster lookups. * * Return: True if pushed, false otherwise. */ static inline bool mas_push_data(struct ma_state *mas, int height, struct maple_subtree_state *mast, bool left) { unsigned char slot_total = mast->bn->b_end; unsigned char end, space, split; MA_STATE(tmp_mas, mas->tree, mas->index, mas->last); tmp_mas = *mas; tmp_mas.depth = mast->l->depth; if (left && !mas_prev_sibling(&tmp_mas)) return false; else if (!left && !mas_next_sibling(&tmp_mas)) return false; end = mas_data_end(&tmp_mas); slot_total += end; space = 2 * mt_slot_count(mas->node) - 2; /* -2 instead of -1 to ensure there isn't a triple split */ if (ma_is_leaf(mast->bn->type)) space--; if (mas->max == ULONG_MAX) space--; if (slot_total >= space) return false; /* Get the data; Fill mast->bn */ mast->bn->b_end++; if (left) { mab_shift_right(mast->bn, end + 1); mas_mab_cp(&tmp_mas, 0, end, mast->bn, 0); mast->bn->b_end = slot_total + 1; } else { mas_mab_cp(&tmp_mas, 0, end, mast->bn, mast->bn->b_end); } /* Configure mast for splitting of mast->bn */ split = mt_slots[mast->bn->type] - 2; if (left) { /* Switch mas to prev node */ *mas = tmp_mas; /* Start using mast->l for the left side. */ tmp_mas.node = mast->l->node; *mast->l = tmp_mas; } else { tmp_mas.node = mast->r->node; *mast->r = tmp_mas; split = slot_total - split; } split = mab_no_null_split(mast->bn, split, mt_slots[mast->bn->type]); /* Update parent slot for split calculation. */ if (left) mast->orig_l->offset += end + 1; mast_split_data(mast, mas, split); mast_fill_bnode(mast, mas, 2); mas_split_final_node(mast, mas, height + 1); return true; } /* * mas_split() - Split data that is too big for one node into two. * @mas: The maple state * @b_node: The maple big node * Return: 1 on success, 0 on failure. */ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) { struct maple_subtree_state mast; int height = 0; unsigned char mid_split, split = 0; struct maple_enode *old; /* * Splitting is handled differently from any other B-tree; the Maple * Tree splits upwards. Splitting up means that the split operation * occurs when the walk of the tree hits the leaves and not on the way * down. The reason for splitting up is that it is impossible to know * how much space will be needed until the leaf is (or leaves are) * reached. Since overwriting data is allowed and a range could * overwrite more than one range or result in changing one entry into 3 * entries, it is impossible to know if a split is required until the * data is examined. * * Splitting is a balancing act between keeping allocations to a minimum * and avoiding a 'jitter' event where a tree is expanded to make room * for an entry followed by a contraction when the entry is removed. To * accomplish the balance, there are empty slots remaining in both left * and right nodes after a split. */ MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); mas->depth = mas_mt_height(mas); /* Allocation failures will happen early. */ mas_node_count(mas, 1 + mas->depth * 2); if (mas_is_err(mas)) return 0; mast.l = &l_mas; mast.r = &r_mas; mast.orig_l = &prev_l_mas; mast.orig_r = &prev_r_mas; mast.bn = b_node; while (height++ <= mas->depth) { if (mt_slots[b_node->type] > b_node->b_end) { mas_split_final_node(&mast, mas, height); break; } l_mas = r_mas = *mas; l_mas.node = mas_new_ma_node(mas, b_node); r_mas.node = mas_new_ma_node(mas, b_node); /* * Another way that 'jitter' is avoided is to terminate a split up early if the * left or right node has space to spare. This is referred to as "pushing left" * or "pushing right" and is similar to the B* tree, except the nodes left or * right can rarely be reused due to RCU, but the ripple upwards is halted which * is a significant savings. */ /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites * r->max. */ mast.r->max = mas->max; mast_fill_bnode(&mast, mas, 1); prev_l_mas = *mast.l; prev_r_mas = *mast.r; } /* Set the original node as dead */ old = mas->node; mas->node = l_mas.node; mas_wmb_replace(mas, old); mtree_range_walk(mas); return 1; } /* * mas_reuse_node() - Reuse the node to store the data. * @wr_mas: The maple write state * @bn: The maple big node * @end: The end of the data. * * Will always return false in RCU mode. * * Return: True if node was reused, false otherwise. */ static inline bool mas_reuse_node(struct ma_wr_state *wr_mas, struct maple_big_node *bn, unsigned char end) { /* Need to be rcu safe. */ if (mt_in_rcu(wr_mas->mas->tree)) return false; if (end > bn->b_end) { int clear = mt_slots[wr_mas->type] - bn->b_end; memset(wr_mas->slots + bn->b_end, 0, sizeof(void *) * clear--); memset(wr_mas->pivots + bn->b_end, 0, sizeof(void *) * clear); } mab_mas_cp(bn, 0, bn->b_end, wr_mas->mas, false); return true; } /* * mas_commit_b_node() - Commit the big node into the tree. * @wr_mas: The maple write state * @b_node: The maple big node * @end: The end of the data. */ static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node, unsigned char end) { struct maple_node *node; struct maple_enode *old_enode; unsigned char b_end = b_node->b_end; enum maple_type b_type = b_node->type; old_enode = wr_mas->mas->node; if ((b_end < mt_min_slots[b_type]) && (!mte_is_root(old_enode)) && (mas_mt_height(wr_mas->mas) > 1)) return mas_rebalance(wr_mas->mas, b_node); if (b_end >= mt_slots[b_type]) return mas_split(wr_mas->mas, b_node); if (mas_reuse_node(wr_mas, b_node, end)) goto reuse_node; mas_node_count(wr_mas->mas, 1); if (mas_is_err(wr_mas->mas)) return 0; node = mas_pop_node(wr_mas->mas); node->parent = mas_mn(wr_mas->mas)->parent; wr_mas->mas->node = mt_mk_node(node, b_type); mab_mas_cp(b_node, 0, b_end, wr_mas->mas, false); mas_replace_node(wr_mas->mas, old_enode); reuse_node: mas_update_gap(wr_mas->mas); wr_mas->mas->end = b_end; return 1; } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline int mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; mas_node_count(mas, 1); if (unlikely(mas_is_err(mas))) return 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mas->depth = 1; mas_set_height(mas); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); return slot; } static inline void mas_store_root(struct ma_state *mas, void *entry) { if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @mas: The maple state * @piv: The pivot value being written * @type: The maple node type * @entry: The data to write * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; mas_wr_walk_traverse(wr_mas); } return true; } static bool mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; mas_wr_walk_traverse(wr_mas); } return true; } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX * * Return 0 on error, 1 on success. */ static inline int mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; if (!entry && !mas->index && mas->last == ULONG_MAX) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } mas_node_count(mas, 1); if (mas_is_err(mas)) return 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); return 1; } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state * * Return: 0 on error, positive on success. */ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_subtree_state mast; struct maple_big_node b_node; struct ma_state *mas; unsigned char height; /* Left and Right side of spanning store */ MA_STATE(l_mas, NULL, 0, 0); MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); MA_WR_STATE(l_wr_mas, &l_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(__func__, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ height = mas_mt_height(mas); mas_node_count(mas, 1 + height * 3); if (mas_is_err(mas)) return 0; /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; /* Set up left side. */ l_mas = *mas; mas_wr_walk_index(&l_wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(&l_wr_mas, &r_wr_mas); mas->offset = l_mas.offset; mas->index = l_mas.index; mas->last = l_mas.last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!l_mas.index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node. */ if (r_mas.offset <= r_mas.end) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; /* Stop spanning searches by searching for just index. */ l_mas.index = l_mas.last = mas->index; mast.bn = &b_node; mast.orig_l = &l_mas; mast.orig_r = &r_mas; /* Combine l_mas and r_mas and split them up evenly again. */ return mas_spanning_rebalance(mas, &mast, height + 1); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. * * Return: True if stored, false otherwise */ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **dst_slots; unsigned long *dst_pivots; unsigned char dst_offset, offset_end = wr_mas->offset_end; struct maple_node reuse, *newnode; unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type]; bool in_rcu = mt_in_rcu(mas->tree); /* Check if there is enough data. The room is enough. */ if (!mte_is_root(mas->node) && (new_end <= mt_min_slots[wr_mas->type]) && !(mas->mas_flags & MA_STATE_BULK)) return false; if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { mas_node_count(mas, 1); if (mas_is_err(mas)) return false; newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void *) * mas->offset); /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return true; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state * * Return: True if stored, false otherwise */ static inline bool mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else if (!mt_in_rcu(mas->tree)) { /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } else { return false; } trace_ma_write(__func__, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); return true; } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; if (!wr_mas->entry) mas_wr_extend_null(wr_mas); } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * @new_end: The end of the node after the modification * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. * * Return: True if appended, false otherwise */ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas; void __rcu **slots; unsigned char end; mas = wr_mas->mas; if (mt_in_rcu(mas->tree)) return false; end = mas->end; if (mas->offset != end) return false; if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return true; } /* * mas_wr_bnode() - Slow path for a modification. * @wr_mas: The write maple state * * This is where split, rebalance end up. */ static void mas_wr_bnode(struct ma_wr_state *wr_mas) { struct maple_big_node b_node; trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end); } static inline void mas_wr_modify(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; /* Direct replacement */ if (wr_mas->r_min == mas->index && wr_mas->r_max == mas->last) { rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); return; } /* * new_end exceeds the size of the maple node and cannot enter the fast * path. */ new_end = mas_wr_new_end(wr_mas); if (new_end >= mt_slots[wr_mas->type]) goto slow_path; /* Attempt to append */ if (mas_wr_append(wr_mas, new_end)) return; if (new_end == mas->end && mas_wr_slot_store(wr_mas)) return; if (mas_wr_node_store(wr_mas, new_end)) return; if (mas_is_err(mas)) return; slow_path: mas_wr_bnode(wr_mas); } /* * mas_wr_store_entry() - Internal call to store a value * @mas: The maple state * @entry: The entry to store. * * Return: The contents that was stored at the index. */ static inline void *mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; wr_mas->content = mas_start(mas); if (mas_is_none(mas) || mas_is_ptr(mas)) { mas_store_root(mas, wr_mas->entry); return wr_mas->content; } if (unlikely(!mas_wr_walk(wr_mas))) { mas_wr_spanning_store(wr_mas); return wr_mas->content; } /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); /* New root for a single pointer */ if (unlikely(!mas->index && mas->last == ULONG_MAX)) { mas_new_root(mas, wr_mas->entry); return wr_mas->content; } mas_wr_modify(wr_mas); return wr_mas->content; } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; if (mas_is_none(mas) || mas_is_ptr(mas)) { mas_store_root(mas, entry); return NULL; } /* spanning writes always overwrite something */ if (!mas_wr_walk(&wr_mas)) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; if (!entry) return NULL; mas_wr_modify(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @max: The minimum starting range * @empty: Can be empty * @set_underflow: Set the @mas->node to underflow state on limit. * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) { mas->status = ma_underflow; return NULL; } goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * @set_overflow: Should @mas->node be set to overflow when the limit is * reached. * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_next_entry() - Internal function to get the next entry. * @mas: The maple state * @limit: The maximum range start. * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. * Sets @mas->index and @mas->last to the range, Does not update @mas->index and * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { mas->status = ma_overflow; return NULL; } return mas_next_slot(mas, limit, false); } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; goto done; } if (mas->index <= pivot) { mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } if (mte_is_root(mas->node)) found = true; done: mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, slot == MAPLE_NODE_SLOTS) * found the gap. (return, slot != MAPLE_NODE_SLOTS) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) { mas_start(mas); mas->offset = mas_data_end(mas); } else if (mas->offset >= 2) { mas->offset -= 2; } else if (!mas_rewind_node(mas)) { return -EBUSY; } /* Empty set. */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, false); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @mas: The maple state * @slots: Pointer to the slot array * @type: The maple node type * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: mt_free_rcu(&node->rcu); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) mt_free_rcu(&node->rcu); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } static void mas_wr_store_setup(struct ma_wr_state *wr_mas) { if (!mas_is_active(wr_mas->mas)) { if (mas_is_start(wr_mas->mas)) return; if (unlikely(mas_is_paused(wr_mas->mas))) goto reset; if (unlikely(mas_is_none(wr_mas->mas))) goto reset; if (unlikely(mas_is_overflow(wr_mas->mas))) goto reset; if (unlikely(mas_is_underflow(wr_mas->mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (wr_mas->mas->last > wr_mas->mas->max) goto reset; if (wr_mas->entry) return; if (mte_is_leaf(wr_mas->mas->node) && wr_mas->mas->last == wr_mas->mas->max) goto reset; return; reset: mas_reset(wr_mas->mas); } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * Note: The @mas should have pre-allocated entries to ensure there is memory to * store the entry. Please see mas_expected_entries()/mas_destroy() for more details. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX %p\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_store_setup(&wr_mas); mas_wr_store_entry(&wr_mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); mas_wr_store_setup(&wr_mas); trace_ma_write(__func__, mas, 0, entry); retry: mas_wr_store_entry(&wr_mas); if (unlikely(mas_nomem(mas, gfp))) goto retry; if (unlikely(mas_is_err(mas))) return xa_err(mas->node); return 0; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); mas_wr_store_setup(&wr_mas); trace_ma_write(__func__, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); unsigned char node_size; int request = 1; int ret; if (unlikely(!mas->index && mas->last == ULONG_MAX)) goto ask_now; mas_wr_store_setup(&wr_mas); wr_mas.content = mas_start(mas); /* Root expand */ if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) goto ask_now; if (unlikely(!mas_wr_walk(&wr_mas))) { /* Spanning store, use worst case for now */ request = 1 + mas_mt_height(mas) * 3; goto ask_now; } /* At this point, we are at the leaf node that needs to be altered. */ /* Exact fit, no nodes needed. */ if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last) return 0; mas_wr_end_piv(&wr_mas); node_size = mas_wr_new_end(&wr_mas); /* Slot store, does not require additional nodes */ if (node_size == mas->end) { /* reuse node */ if (!mt_in_rcu(mas->tree)) return 0; /* shifting boundary */ if (wr_mas.offset_end - mas->offset == 1) return 0; } if (node_size >= mt_slots[wr_mas.type]) { /* Split, worst case for now. */ request = 1 + mas_mt_height(mas) * 2; goto ask_now; } /* New root needs a single node */ if (unlikely(mte_is_root(mas->node))) goto ask_now; /* Potential spanning rebalance collapsing a node, use worst-case */ if (node_size - 1 <= mt_min_slots[wr_mas.type]) request = mas_mt_height(mas) * 2 - 1; /* node store, slot store needs one node */ ask_now: mas_node_count_gfp(mas, request, gfp); mas->mas_flags |= MA_STATE_PREALLOC; if (likely(!mas_is_err(mas))) return 0; mas_set_alloc_req(mas, 0); ret = xa_err(mas->node); mas_reset(mas); mas_destroy(mas); mas_reset(mas); return ret; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { struct maple_alloc *node; unsigned long total; /* * When using mas_for_each() to insert an expected number of elements, * it is possible that the number inserted is less than the expected * number. To fix an invalid final node, a check is performed here to * rebalance the previous node with the final node. */ if (mas->mas_flags & MA_STATE_REBALANCE) { unsigned char end; mas_start(mas); mtree_range_walk(mas); end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); mas->mas_flags &= ~MA_STATE_REBALANCE; } mas->mas_flags &= ~(MA_STATE_BULK|MA_STATE_PREALLOC); total = mas_allocated(mas); while (total) { node = mas->alloc; mas->alloc = node->slot[0]; if (node->node_count > 1) { size_t count = node->node_count - 1; mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } mt_free_one(ma_mnode_ptr(node)); total--; } mas->alloc = NULL; } EXPORT_SYMBOL_GPL(mas_destroy); /* * mas_expected_entries() - Set the expected number of entries that will be inserted. * @mas: The maple state * @nr_entries: The number of expected entries. * * This will attempt to pre-allocate enough nodes to store the expected number * of entries. The allocations will occur using the bulk allocator interface * for speed. Please call mas_destroy() on the @mas after inserting the entries * to ensure any unused nodes are freed. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) { int nonleaf_cap = MAPLE_ARANGE64_SLOTS - 2; struct maple_enode *enode = mas->node; int nr_nodes; int ret; /* * Sometimes it is necessary to duplicate a tree to a new tree, such as * forking a process and duplicating the VMAs from one tree to a new * tree. When such a situation arises, it is known that the new tree is * not going to be used until the entire tree is populated. For * performance reasons, it is best to use a bulk load with RCU disabled. * This allows for optimistic splitting that favours the left and reuse * of nodes during the operation. */ /* Optimize splitting for bulk insert in-order */ mas->mas_flags |= MA_STATE_BULK; /* * Avoid overflow, assume a gap between each entry and a trailing null. * If this is wrong, it just means allocation can happen during * insertion of entries. */ nr_nodes = max(nr_entries, nr_entries * 2 + 1); if (!mt_is_alloc(mas->tree)) nonleaf_cap = MAPLE_RANGE64_SLOTS - 2; /* Leaves; reduce slots to keep space for expansion */ nr_nodes = DIV_ROUND_UP(nr_nodes, MAPLE_RANGE64_SLOTS - 2); /* Internal nodes */ nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap); /* Add working room for split (2 nodes) + new parents */ mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL); /* Detect if allocations run out */ mas->mas_flags |= MA_STATE_PREALLOC; if (!mas_is_err(mas)) return 0; ret = xa_err(mas->node); mas->node = enode; mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_expected_entries); static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas->status = ma_active; break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas->status = ma_active; break; case ma_overflow: /* User expects mas to be one after where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; /* Retry unnecessary when holding the write lock. */ entry = mas_state_walk(mas); if (!entry) return NULL; write_retry: /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_store_setup(&wr_mas); mas_wr_store_entry(&wr_mas); if (mas_nomem(mas, GFP_KERNEL)) goto write_retry; return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) { mas_destroy(mas); return false; } if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas_allocated(mas)) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), sizeof(struct maple_node), SLAB_PANIC, NULL); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(__func__, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); MA_WR_STATE(wr_mas, &mas, entry); trace_ma_write(__func__, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); retry: mas_wr_store_entry(&wr_mas); if (mas_nomem(&mas, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&mas)) return xa_err(mas.node); return 0; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) return xa_err(ms.node); return 0; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_range); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(__func__, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); mt_free_one(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char request, count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); request = mas_data_end(mas) + 1; count = mt_alloc_bulk(gfp, request, (void **)new_slots); if (unlikely(count < request)) { memset(new_slots, 0, request * sizeof(void *)); mas_set_err(mas, -ENOMEM); return; } /* Restore node type information in slots. */ slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; ((unsigned long *)new_slots)[i] |= val; } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) return; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(__func__, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%p]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (%p)\n", entry); else pr_cont("%p\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } } pr_cont("%p\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } } pr_cont("%p\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); break; } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node %p depth %d type %d parent %p", node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(%p) flags %X, height %u root %p\n", mt, mt->ma_flags, mt_height(mt), entry); if (!xa_is_node(entry)) mt_dump_entry(entry, 0, 0, 0, format); else if (entry) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err("%p[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset %p[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap %p[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap %p[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap %p[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent %p[%u] does not have %p\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child %p at parent %p[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at %p[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at %p[%u]: child %p has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child %p has parent %p not %p\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at %p[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err("%p[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err("%p[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err("%p[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node%p: data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err("%p[%u] should not have entry %p\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err("%p[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at %p[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) { unsigned char end; MA_STATE(mas, mt, 0, 0); rcu_read_lock(); mas_start(&mas); if (!mas_is_active(&mas)) goto done; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (mas.max != ULONG_MAX))) { pr_err("Invalid size %u of %p\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); done: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 21506 1978 21530 15344 15350 17492 789 17448 16991 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */ |
| 7 7 7 7 1 137 137 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2006 - 2007 Ivo van Doorn * Copyright (C) 2007 Dmitry Torokhov * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/rfkill.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/device.h> #include <linux/miscdevice.h> #include <linux/wait.h> #include <linux/poll.h> #include <linux/fs.h> #include <linux/slab.h> #include "rfkill.h" #define POLL_INTERVAL (5 * HZ) #define RFKILL_BLOCK_HW BIT(0) #define RFKILL_BLOCK_SW BIT(1) #define RFKILL_BLOCK_SW_PREV BIT(2) #define RFKILL_BLOCK_ANY (RFKILL_BLOCK_HW |\ RFKILL_BLOCK_SW |\ RFKILL_BLOCK_SW_PREV) #define RFKILL_BLOCK_SW_SETCALL BIT(31) struct rfkill { spinlock_t lock; enum rfkill_type type; unsigned long state; unsigned long hard_block_reasons; u32 idx; bool registered; bool persistent; bool polling_paused; bool suspended; bool need_sync; const struct rfkill_ops *ops; void *data; #ifdef CONFIG_RFKILL_LEDS struct led_trigger led_trigger; const char *ledtrigname; #endif struct device dev; struct list_head node; struct delayed_work poll_work; struct work_struct uevent_work; struct work_struct sync_work; char name[]; }; #define to_rfkill(d) container_of(d, struct rfkill, dev) struct rfkill_int_event { struct list_head list; struct rfkill_event_ext ev; }; struct rfkill_data { struct list_head list; struct list_head events; struct mutex mtx; wait_queue_head_t read_wait; bool input_handler; u8 max_size; }; MODULE_AUTHOR("Ivo van Doorn <IvDoorn@gmail.com>"); MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>"); MODULE_DESCRIPTION("RF switch support"); MODULE_LICENSE("GPL"); /* * The locking here should be made much smarter, we currently have * a bit of a stupid situation because drivers might want to register * the rfkill struct under their own lock, and take this lock during * rfkill method calls -- which will cause an AB-BA deadlock situation. * * To fix that, we need to rework this code here to be mostly lock-free * and only use the mutex for list manipulations, not to protect the * various other global variables. Then we can avoid holding the mutex * around driver operations, and all is happy. */ static LIST_HEAD(rfkill_list); /* list of registered rf switches */ static DEFINE_MUTEX(rfkill_global_mutex); static LIST_HEAD(rfkill_fds); /* list of open fds of /dev/rfkill */ static unsigned int rfkill_default_state = 1; module_param_named(default_state, rfkill_default_state, uint, 0444); MODULE_PARM_DESC(default_state, "Default initial state for all radio types, 0 = radio off"); static struct { bool cur, sav; } rfkill_global_states[NUM_RFKILL_TYPES]; static bool rfkill_epo_lock_active; #ifdef CONFIG_RFKILL_LEDS static void rfkill_led_trigger_event(struct rfkill *rfkill) { struct led_trigger *trigger; if (!rfkill->registered) return; trigger = &rfkill->led_trigger; if (rfkill->state & RFKILL_BLOCK_ANY) led_trigger_event(trigger, LED_OFF); else led_trigger_event(trigger, LED_FULL); } static int rfkill_led_trigger_activate(struct led_classdev *led) { struct rfkill *rfkill; rfkill = container_of(led->trigger, struct rfkill, led_trigger); rfkill_led_trigger_event(rfkill); return 0; } const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) { return rfkill->led_trigger.name; } EXPORT_SYMBOL(rfkill_get_led_trigger_name); void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) { BUG_ON(!rfkill); rfkill->ledtrigname = name; } EXPORT_SYMBOL(rfkill_set_led_trigger_name); static int rfkill_led_trigger_register(struct rfkill *rfkill) { rfkill->led_trigger.name = rfkill->ledtrigname ? : dev_name(&rfkill->dev); rfkill->led_trigger.activate = rfkill_led_trigger_activate; return led_trigger_register(&rfkill->led_trigger); } static void rfkill_led_trigger_unregister(struct rfkill *rfkill) { led_trigger_unregister(&rfkill->led_trigger); } static struct led_trigger rfkill_any_led_trigger; static struct led_trigger rfkill_none_led_trigger; static struct work_struct rfkill_global_led_trigger_work; static void rfkill_global_led_trigger_worker(struct work_struct *work) { enum led_brightness brightness = LED_OFF; struct rfkill *rfkill; mutex_lock(&rfkill_global_mutex); list_for_each_entry(rfkill, &rfkill_list, node) { if (!(rfkill->state & RFKILL_BLOCK_ANY)) { brightness = LED_FULL; break; } } mutex_unlock(&rfkill_global_mutex); led_trigger_event(&rfkill_any_led_trigger, brightness); led_trigger_event(&rfkill_none_led_trigger, brightness == LED_OFF ? LED_FULL : LED_OFF); } static void rfkill_global_led_trigger_event(void) { schedule_work(&rfkill_global_led_trigger_work); } static int rfkill_global_led_trigger_register(void) { int ret; INIT_WORK(&rfkill_global_led_trigger_work, rfkill_global_led_trigger_worker); rfkill_any_led_trigger.name = "rfkill-any"; ret = led_trigger_register(&rfkill_any_led_trigger); if (ret) return ret; rfkill_none_led_trigger.name = "rfkill-none"; ret = led_trigger_register(&rfkill_none_led_trigger); if (ret) led_trigger_unregister(&rfkill_any_led_trigger); else /* Delay activation until all global triggers are registered */ rfkill_global_led_trigger_event(); return ret; } static void rfkill_global_led_trigger_unregister(void) { led_trigger_unregister(&rfkill_none_led_trigger); led_trigger_unregister(&rfkill_any_led_trigger); cancel_work_sync(&rfkill_global_led_trigger_work); } #else static void rfkill_led_trigger_event(struct rfkill *rfkill) { } static inline int rfkill_led_trigger_register(struct rfkill *rfkill) { return 0; } static inline void rfkill_led_trigger_unregister(struct rfkill *rfkill) { } static void rfkill_global_led_trigger_event(void) { } static int rfkill_global_led_trigger_register(void) { return 0; } static void rfkill_global_led_trigger_unregister(void) { } #endif /* CONFIG_RFKILL_LEDS */ static void rfkill_fill_event(struct rfkill_event_ext *ev, struct rfkill *rfkill, enum rfkill_operation op) { unsigned long flags; ev->idx = rfkill->idx; ev->type = rfkill->type; ev->op = op; spin_lock_irqsave(&rfkill->lock, flags); ev->hard = !!(rfkill->state & RFKILL_BLOCK_HW); ev->soft = !!(rfkill->state & (RFKILL_BLOCK_SW | RFKILL_BLOCK_SW_PREV)); ev->hard_block_reasons = rfkill->hard_block_reasons; spin_unlock_irqrestore(&rfkill->lock, flags); } static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op) { struct rfkill_data *data; struct rfkill_int_event *ev; list_for_each_entry(data, &rfkill_fds, list) { ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) continue; rfkill_fill_event(&ev->ev, rfkill, op); mutex_lock(&data->mtx); list_add_tail(&ev->list, &data->events); mutex_unlock(&data->mtx); wake_up_interruptible(&data->read_wait); } } static void rfkill_event(struct rfkill *rfkill) { if (!rfkill->registered) return; kobject_uevent(&rfkill->dev.kobj, KOBJ_CHANGE); /* also send event to /dev/rfkill */ rfkill_send_events(rfkill, RFKILL_OP_CHANGE); } /** * rfkill_set_block - wrapper for set_block method * * @rfkill: the rfkill struct to use * @blocked: the new software state * * Calls the set_block method (when applicable) and handles notifications * etc. as well. */ static void rfkill_set_block(struct rfkill *rfkill, bool blocked) { unsigned long flags; bool prev, curr; int err; if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP)) return; /* * Some platforms (...!) generate input events which affect the * _hard_ kill state -- whenever something tries to change the * current software state query the hardware state too. */ if (rfkill->ops->query) rfkill->ops->query(rfkill, rfkill->data); spin_lock_irqsave(&rfkill->lock, flags); prev = rfkill->state & RFKILL_BLOCK_SW; if (prev) rfkill->state |= RFKILL_BLOCK_SW_PREV; else rfkill->state &= ~RFKILL_BLOCK_SW_PREV; if (blocked) rfkill->state |= RFKILL_BLOCK_SW; else rfkill->state &= ~RFKILL_BLOCK_SW; rfkill->state |= RFKILL_BLOCK_SW_SETCALL; spin_unlock_irqrestore(&rfkill->lock, flags); err = rfkill->ops->set_block(rfkill->data, blocked); spin_lock_irqsave(&rfkill->lock, flags); if (err) { /* * Failed -- reset status to _PREV, which may be different * from what we have set _PREV to earlier in this function * if rfkill_set_sw_state was invoked. */ if (rfkill->state & RFKILL_BLOCK_SW_PREV) rfkill->state |= RFKILL_BLOCK_SW; else rfkill->state &= ~RFKILL_BLOCK_SW; } rfkill->state &= ~RFKILL_BLOCK_SW_SETCALL; rfkill->state &= ~RFKILL_BLOCK_SW_PREV; curr = rfkill->state & RFKILL_BLOCK_SW; spin_unlock_irqrestore(&rfkill->lock, flags); rfkill_led_trigger_event(rfkill); rfkill_global_led_trigger_event(); if (prev != curr) rfkill_event(rfkill); } static void rfkill_sync(struct rfkill *rfkill) { lockdep_assert_held(&rfkill_global_mutex); if (!rfkill->need_sync) return; rfkill_set_block(rfkill, rfkill_global_states[rfkill->type].cur); rfkill->need_sync = false; } static void rfkill_update_global_state(enum rfkill_type type, bool blocked) { int i; if (type != RFKILL_TYPE_ALL) { rfkill_global_states[type].cur = blocked; return; } for (i = 0; i < NUM_RFKILL_TYPES; i++) rfkill_global_states[i].cur = blocked; } #ifdef CONFIG_RFKILL_INPUT static atomic_t rfkill_input_disabled = ATOMIC_INIT(0); /** * __rfkill_switch_all - Toggle state of all switches of given type * @type: type of interfaces to be affected * @blocked: the new state * * This function sets the state of all switches of given type, * unless a specific switch is suspended. * * Caller must have acquired rfkill_global_mutex. */ static void __rfkill_switch_all(const enum rfkill_type type, bool blocked) { struct rfkill *rfkill; rfkill_update_global_state(type, blocked); list_for_each_entry(rfkill, &rfkill_list, node) { if (rfkill->type != type && type != RFKILL_TYPE_ALL) continue; rfkill_set_block(rfkill, blocked); } } /** * rfkill_switch_all - Toggle state of all switches of given type * @type: type of interfaces to be affected * @blocked: the new state * * Acquires rfkill_global_mutex and calls __rfkill_switch_all(@type, @state). * Please refer to __rfkill_switch_all() for details. * * Does nothing if the EPO lock is active. */ void rfkill_switch_all(enum rfkill_type type, bool blocked) { if (atomic_read(&rfkill_input_disabled)) return; mutex_lock(&rfkill_global_mutex); if (!rfkill_epo_lock_active) __rfkill_switch_all(type, blocked); mutex_unlock(&rfkill_global_mutex); } /** * rfkill_epo - emergency power off all transmitters * * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED, * ignoring everything in its path but rfkill_global_mutex and rfkill->mutex. * * The global state before the EPO is saved and can be restored later * using rfkill_restore_states(). */ void rfkill_epo(void) { struct rfkill *rfkill; int i; if (atomic_read(&rfkill_input_disabled)) return; mutex_lock(&rfkill_global_mutex); rfkill_epo_lock_active = true; list_for_each_entry(rfkill, &rfkill_list, node) rfkill_set_block(rfkill, true); for (i = 0; i < NUM_RFKILL_TYPES; i++) { rfkill_global_states[i].sav = rfkill_global_states[i].cur; rfkill_global_states[i].cur = true; } mutex_unlock(&rfkill_global_mutex); } /** * rfkill_restore_states - restore global states * * Restore (and sync switches to) the global state from the * states in rfkill_default_states. This can undo the effects of * a call to rfkill_epo(). */ void rfkill_restore_states(void) { int i; if (atomic_read(&rfkill_input_disabled)) return; mutex_lock(&rfkill_global_mutex); rfkill_epo_lock_active = false; for (i = 0; i < NUM_RFKILL_TYPES; i++) __rfkill_switch_all(i, rfkill_global_states[i].sav); mutex_unlock(&rfkill_global_mutex); } /** * rfkill_remove_epo_lock - unlock state changes * * Used by rfkill-input manually unlock state changes, when * the EPO switch is deactivated. */ void rfkill_remove_epo_lock(void) { if (atomic_read(&rfkill_input_disabled)) return; mutex_lock(&rfkill_global_mutex); rfkill_epo_lock_active = false; mutex_unlock(&rfkill_global_mutex); } /** * rfkill_is_epo_lock_active - returns true EPO is active * * Returns 0 (false) if there is NOT an active EPO condition, * and 1 (true) if there is an active EPO condition, which * locks all radios in one of the BLOCKED states. * * Can be called in atomic context. */ bool rfkill_is_epo_lock_active(void) { return rfkill_epo_lock_active; } /** * rfkill_get_global_sw_state - returns global state for a type * @type: the type to get the global state of * * Returns the current global state for a given wireless * device type. */ bool rfkill_get_global_sw_state(const enum rfkill_type type) { return rfkill_global_states[type].cur; } #endif bool rfkill_set_hw_state_reason(struct rfkill *rfkill, bool blocked, unsigned long reason) { unsigned long flags; bool ret, prev; BUG_ON(!rfkill); if (WARN(reason & ~(RFKILL_HARD_BLOCK_SIGNAL | RFKILL_HARD_BLOCK_NOT_OWNER), "hw_state reason not supported: 0x%lx", reason)) return blocked; spin_lock_irqsave(&rfkill->lock, flags); prev = !!(rfkill->hard_block_reasons & reason); if (blocked) { rfkill->state |= RFKILL_BLOCK_HW; rfkill->hard_block_reasons |= reason; } else { rfkill->hard_block_reasons &= ~reason; if (!rfkill->hard_block_reasons) rfkill->state &= ~RFKILL_BLOCK_HW; } ret = !!(rfkill->state & RFKILL_BLOCK_ANY); spin_unlock_irqrestore(&rfkill->lock, flags); rfkill_led_trigger_event(rfkill); rfkill_global_led_trigger_event(); if (rfkill->registered && prev != blocked) schedule_work(&rfkill->uevent_work); return ret; } EXPORT_SYMBOL(rfkill_set_hw_state_reason); static void __rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) { u32 bit = RFKILL_BLOCK_SW; /* if in a ops->set_block right now, use other bit */ if (rfkill->state & RFKILL_BLOCK_SW_SETCALL) bit = RFKILL_BLOCK_SW_PREV; if (blocked) rfkill->state |= bit; else rfkill->state &= ~bit; } bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) { unsigned long flags; bool prev, hwblock; BUG_ON(!rfkill); spin_lock_irqsave(&rfkill->lock, flags); prev = !!(rfkill->state & RFKILL_BLOCK_SW); __rfkill_set_sw_state(rfkill, blocked); hwblock = !!(rfkill->state & RFKILL_BLOCK_HW); blocked = blocked || hwblock; spin_unlock_irqrestore(&rfkill->lock, flags); if (!rfkill->registered) return blocked; if (prev != blocked && !hwblock) schedule_work(&rfkill->uevent_work); rfkill_led_trigger_event(rfkill); rfkill_global_led_trigger_event(); return blocked; } EXPORT_SYMBOL(rfkill_set_sw_state); void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked) { unsigned long flags; BUG_ON(!rfkill); BUG_ON(rfkill->registered); spin_lock_irqsave(&rfkill->lock, flags); __rfkill_set_sw_state(rfkill, blocked); rfkill->persistent = true; spin_unlock_irqrestore(&rfkill->lock, flags); } EXPORT_SYMBOL(rfkill_init_sw_state); void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) { unsigned long flags; bool swprev, hwprev; BUG_ON(!rfkill); spin_lock_irqsave(&rfkill->lock, flags); /* * No need to care about prev/setblock ... this is for uevent only * and that will get triggered by rfkill_set_block anyway. */ swprev = !!(rfkill->state & RFKILL_BLOCK_SW); hwprev = !!(rfkill->state & RFKILL_BLOCK_HW); __rfkill_set_sw_state(rfkill, sw); if (hw) rfkill->state |= RFKILL_BLOCK_HW; else rfkill->state &= ~RFKILL_BLOCK_HW; spin_unlock_irqrestore(&rfkill->lock, flags); if (!rfkill->registered) { rfkill->persistent = true; } else { if (swprev != sw || hwprev != hw) schedule_work(&rfkill->uevent_work); rfkill_led_trigger_event(rfkill); rfkill_global_led_trigger_event(); } } EXPORT_SYMBOL(rfkill_set_states); static const char * const rfkill_types[] = { NULL, /* RFKILL_TYPE_ALL */ "wlan", "bluetooth", "ultrawideband", "wimax", "wwan", "gps", "fm", "nfc", }; enum rfkill_type rfkill_find_type(const char *name) { int i; BUILD_BUG_ON(ARRAY_SIZE(rfkill_types) != NUM_RFKILL_TYPES); if (!name) return RFKILL_TYPE_ALL; for (i = 1; i < NUM_RFKILL_TYPES; i++) if (!strcmp(name, rfkill_types[i])) return i; return RFKILL_TYPE_ALL; } EXPORT_SYMBOL(rfkill_find_type); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "%s\n", rfkill->name); } static DEVICE_ATTR_RO(name); static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "%s\n", rfkill_types[rfkill->type]); } static DEVICE_ATTR_RO(type); static ssize_t index_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "%d\n", rfkill->idx); } static DEVICE_ATTR_RO(index); static ssize_t persistent_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "%d\n", rfkill->persistent); } static DEVICE_ATTR_RO(persistent); static ssize_t hard_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "%d\n", (rfkill->state & RFKILL_BLOCK_HW) ? 1 : 0); } static DEVICE_ATTR_RO(hard); static ssize_t soft_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); mutex_lock(&rfkill_global_mutex); rfkill_sync(rfkill); mutex_unlock(&rfkill_global_mutex); return sysfs_emit(buf, "%d\n", (rfkill->state & RFKILL_BLOCK_SW) ? 1 : 0); } static ssize_t soft_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct rfkill *rfkill = to_rfkill(dev); unsigned long state; int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; err = kstrtoul(buf, 0, &state); if (err) return err; if (state > 1 ) return -EINVAL; mutex_lock(&rfkill_global_mutex); rfkill_sync(rfkill); rfkill_set_block(rfkill, state); mutex_unlock(&rfkill_global_mutex); return count; } static DEVICE_ATTR_RW(soft); static ssize_t hard_block_reasons_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); return sysfs_emit(buf, "0x%lx\n", rfkill->hard_block_reasons); } static DEVICE_ATTR_RO(hard_block_reasons); static u8 user_state_from_blocked(unsigned long state) { if (state & RFKILL_BLOCK_HW) return RFKILL_USER_STATE_HARD_BLOCKED; if (state & RFKILL_BLOCK_SW) return RFKILL_USER_STATE_SOFT_BLOCKED; return RFKILL_USER_STATE_UNBLOCKED; } static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); mutex_lock(&rfkill_global_mutex); rfkill_sync(rfkill); mutex_unlock(&rfkill_global_mutex); return sysfs_emit(buf, "%d\n", user_state_from_blocked(rfkill->state)); } static ssize_t state_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct rfkill *rfkill = to_rfkill(dev); unsigned long state; int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; err = kstrtoul(buf, 0, &state); if (err) return err; if (state != RFKILL_USER_STATE_SOFT_BLOCKED && state != RFKILL_USER_STATE_UNBLOCKED) return -EINVAL; mutex_lock(&rfkill_global_mutex); rfkill_sync(rfkill); rfkill_set_block(rfkill, state == RFKILL_USER_STATE_SOFT_BLOCKED); mutex_unlock(&rfkill_global_mutex); return count; } static DEVICE_ATTR_RW(state); static struct attribute *rfkill_dev_attrs[] = { &dev_attr_name.attr, &dev_attr_type.attr, &dev_attr_index.attr, &dev_attr_persistent.attr, &dev_attr_state.attr, &dev_attr_soft.attr, &dev_attr_hard.attr, &dev_attr_hard_block_reasons.attr, NULL, }; ATTRIBUTE_GROUPS(rfkill_dev); static void rfkill_release(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); kfree(rfkill); } static int rfkill_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) { struct rfkill *rfkill = to_rfkill(dev); unsigned long flags; unsigned long reasons; u32 state; int error; error = add_uevent_var(env, "RFKILL_NAME=%s", rfkill->name); if (error) return error; error = add_uevent_var(env, "RFKILL_TYPE=%s", rfkill_types[rfkill->type]); if (error) return error; spin_lock_irqsave(&rfkill->lock, flags); state = rfkill->state; reasons = rfkill->hard_block_reasons; spin_unlock_irqrestore(&rfkill->lock, flags); error = add_uevent_var(env, "RFKILL_STATE=%d", user_state_from_blocked(state)); if (error) return error; return add_uevent_var(env, "RFKILL_HW_BLOCK_REASON=0x%lx", reasons); } void rfkill_pause_polling(struct rfkill *rfkill) { BUG_ON(!rfkill); if (!rfkill->ops->poll) return; rfkill->polling_paused = true; cancel_delayed_work_sync(&rfkill->poll_work); } EXPORT_SYMBOL(rfkill_pause_polling); void rfkill_resume_polling(struct rfkill *rfkill) { BUG_ON(!rfkill); if (!rfkill->ops->poll) return; rfkill->polling_paused = false; if (rfkill->suspended) return; queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, 0); } EXPORT_SYMBOL(rfkill_resume_polling); #ifdef CONFIG_PM_SLEEP static int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); rfkill->suspended = true; cancel_delayed_work_sync(&rfkill->poll_work); return 0; } static int rfkill_resume(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); bool cur; rfkill->suspended = false; if (!rfkill->registered) return 0; if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); } if (rfkill->ops->poll && !rfkill->polling_paused) queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, 0); return 0; } static SIMPLE_DEV_PM_OPS(rfkill_pm_ops, rfkill_suspend, rfkill_resume); #define RFKILL_PM_OPS (&rfkill_pm_ops) #else #define RFKILL_PM_OPS NULL #endif static struct class rfkill_class = { .name = "rfkill", .dev_release = rfkill_release, .dev_groups = rfkill_dev_groups, .dev_uevent = rfkill_dev_uevent, .pm = RFKILL_PM_OPS, }; bool rfkill_blocked(struct rfkill *rfkill) { unsigned long flags; u32 state; spin_lock_irqsave(&rfkill->lock, flags); state = rfkill->state; spin_unlock_irqrestore(&rfkill->lock, flags); return !!(state & RFKILL_BLOCK_ANY); } EXPORT_SYMBOL(rfkill_blocked); bool rfkill_soft_blocked(struct rfkill *rfkill) { unsigned long flags; u32 state; spin_lock_irqsave(&rfkill->lock, flags); state = rfkill->state; spin_unlock_irqrestore(&rfkill->lock, flags); return !!(state & RFKILL_BLOCK_SW); } EXPORT_SYMBOL(rfkill_soft_blocked); struct rfkill * __must_check rfkill_alloc(const char *name, struct device *parent, const enum rfkill_type type, const struct rfkill_ops *ops, void *ops_data) { struct rfkill *rfkill; struct device *dev; if (WARN_ON(!ops)) return NULL; if (WARN_ON(!ops->set_block)) return NULL; if (WARN_ON(!name)) return NULL; if (WARN_ON(type == RFKILL_TYPE_ALL || type >= NUM_RFKILL_TYPES)) return NULL; rfkill = kzalloc(sizeof(*rfkill) + strlen(name) + 1, GFP_KERNEL); if (!rfkill) return NULL; spin_lock_init(&rfkill->lock); INIT_LIST_HEAD(&rfkill->node); rfkill->type = type; strcpy(rfkill->name, name); rfkill->ops = ops; rfkill->data = ops_data; dev = &rfkill->dev; dev->class = &rfkill_class; dev->parent = parent; device_initialize(dev); return rfkill; } EXPORT_SYMBOL(rfkill_alloc); static void rfkill_poll(struct work_struct *work) { struct rfkill *rfkill; rfkill = container_of(work, struct rfkill, poll_work.work); /* * Poll hardware state -- driver will use one of the * rfkill_set{,_hw,_sw}_state functions and use its * return value to update the current status. */ rfkill->ops->poll(rfkill, rfkill->data); queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, round_jiffies_relative(POLL_INTERVAL)); } static void rfkill_uevent_work(struct work_struct *work) { struct rfkill *rfkill; rfkill = container_of(work, struct rfkill, uevent_work); mutex_lock(&rfkill_global_mutex); rfkill_event(rfkill); mutex_unlock(&rfkill_global_mutex); } static void rfkill_sync_work(struct work_struct *work) { struct rfkill *rfkill = container_of(work, struct rfkill, sync_work); mutex_lock(&rfkill_global_mutex); rfkill_sync(rfkill); mutex_unlock(&rfkill_global_mutex); } int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; struct device *dev; int error; if (!rfkill) return -EINVAL; dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); if (rfkill->registered) { error = -EALREADY; goto unlock; } rfkill->idx = rfkill_no; dev_set_name(dev, "rfkill%lu", rfkill_no); rfkill_no++; list_add_tail(&rfkill->node, &rfkill_list); error = device_add(dev); if (error) goto remove; error = rfkill_led_trigger_register(rfkill); if (error) goto devdel; rfkill->registered = true; INIT_DELAYED_WORK(&rfkill->poll_work, rfkill_poll); INIT_WORK(&rfkill->uevent_work, rfkill_uevent_work); INIT_WORK(&rfkill->sync_work, rfkill_sync_work); if (rfkill->ops->poll) queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, round_jiffies_relative(POLL_INTERVAL)); if (!rfkill->persistent || rfkill_epo_lock_active) { rfkill->need_sync = true; schedule_work(&rfkill->sync_work); } else { #ifdef CONFIG_RFKILL_INPUT bool soft_blocked = !!(rfkill->state & RFKILL_BLOCK_SW); if (!atomic_read(&rfkill_input_disabled)) __rfkill_switch_all(rfkill->type, soft_blocked); #endif } rfkill_global_led_trigger_event(); rfkill_send_events(rfkill, RFKILL_OP_ADD); mutex_unlock(&rfkill_global_mutex); return 0; devdel: device_del(&rfkill->dev); remove: list_del_init(&rfkill->node); unlock: mutex_unlock(&rfkill_global_mutex); return error; } EXPORT_SYMBOL(rfkill_register); void rfkill_unregister(struct rfkill *rfkill) { BUG_ON(!rfkill); if (rfkill->ops->poll) cancel_delayed_work_sync(&rfkill->poll_work); cancel_work_sync(&rfkill->uevent_work); cancel_work_sync(&rfkill->sync_work); rfkill->registered = false; device_del(&rfkill->dev); mutex_lock(&rfkill_global_mutex); rfkill_send_events(rfkill, RFKILL_OP_DEL); list_del_init(&rfkill->node); rfkill_global_led_trigger_event(); mutex_unlock(&rfkill_global_mutex); rfkill_led_trigger_unregister(rfkill); } EXPORT_SYMBOL(rfkill_unregister); void rfkill_destroy(struct rfkill *rfkill) { if (rfkill) put_device(&rfkill->dev); } EXPORT_SYMBOL(rfkill_destroy); static int rfkill_fop_open(struct inode *inode, struct file *file) { struct rfkill_data *data; struct rfkill *rfkill; struct rfkill_int_event *ev, *tmp; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->max_size = RFKILL_EVENT_SIZE_V1; INIT_LIST_HEAD(&data->events); mutex_init(&data->mtx); init_waitqueue_head(&data->read_wait); mutex_lock(&rfkill_global_mutex); /* * start getting events from elsewhere but hold mtx to get * startup events added first */ list_for_each_entry(rfkill, &rfkill_list, node) { ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) goto free; rfkill_sync(rfkill); rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); mutex_lock(&data->mtx); list_add_tail(&ev->list, &data->events); mutex_unlock(&data->mtx); } list_add(&data->list, &rfkill_fds); mutex_unlock(&rfkill_global_mutex); file->private_data = data; return stream_open(inode, file); free: mutex_unlock(&rfkill_global_mutex); mutex_destroy(&data->mtx); list_for_each_entry_safe(ev, tmp, &data->events, list) kfree(ev); kfree(data); return -ENOMEM; } static __poll_t rfkill_fop_poll(struct file *file, poll_table *wait) { struct rfkill_data *data = file->private_data; __poll_t res = EPOLLOUT | EPOLLWRNORM; poll_wait(file, &data->read_wait, wait); mutex_lock(&data->mtx); if (!list_empty(&data->events)) res = EPOLLIN | EPOLLRDNORM; mutex_unlock(&data->mtx); return res; } static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct rfkill_data *data = file->private_data; struct rfkill_int_event *ev; unsigned long sz; int ret; mutex_lock(&data->mtx); while (list_empty(&data->events)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } mutex_unlock(&data->mtx); /* since we re-check and it just compares pointers, * using !list_empty() without locking isn't a problem */ ret = wait_event_interruptible(data->read_wait, !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) goto out; } ev = list_first_entry(&data->events, struct rfkill_int_event, list); sz = min_t(unsigned long, sizeof(ev->ev), count); sz = min_t(unsigned long, sz, data->max_size); ret = sz; if (copy_to_user(buf, &ev->ev, sz)) ret = -EFAULT; list_del(&ev->list); kfree(ev); out: mutex_unlock(&data->mtx); return ret; } static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { struct rfkill_data *data = file->private_data; struct rfkill *rfkill; struct rfkill_event_ext ev; int ret; /* we don't need the 'hard' variable but accept it */ if (count < RFKILL_EVENT_SIZE_V1 - 1) return -EINVAL; /* * Copy as much data as we can accept into our 'ev' buffer, * but tell userspace how much we've copied so it can determine * our API version even in a write() call, if it cares. */ count = min(count, sizeof(ev)); count = min_t(size_t, count, data->max_size); if (copy_from_user(&ev, buf, count)) return -EFAULT; if (ev.type >= NUM_RFKILL_TYPES) return -EINVAL; mutex_lock(&rfkill_global_mutex); switch (ev.op) { case RFKILL_OP_CHANGE_ALL: rfkill_update_global_state(ev.type, ev.soft); list_for_each_entry(rfkill, &rfkill_list, node) if (rfkill->type == ev.type || ev.type == RFKILL_TYPE_ALL) rfkill_set_block(rfkill, ev.soft); ret = 0; break; case RFKILL_OP_CHANGE: list_for_each_entry(rfkill, &rfkill_list, node) if (rfkill->idx == ev.idx && (rfkill->type == ev.type || ev.type == RFKILL_TYPE_ALL)) rfkill_set_block(rfkill, ev.soft); ret = 0; break; default: ret = -EINVAL; break; } mutex_unlock(&rfkill_global_mutex); return ret ?: count; } static int rfkill_fop_release(struct inode *inode, struct file *file) { struct rfkill_data *data = file->private_data; struct rfkill_int_event *ev, *tmp; mutex_lock(&rfkill_global_mutex); list_del(&data->list); mutex_unlock(&rfkill_global_mutex); mutex_destroy(&data->mtx); list_for_each_entry_safe(ev, tmp, &data->events, list) kfree(ev); #ifdef CONFIG_RFKILL_INPUT if (data->input_handler) if (atomic_dec_return(&rfkill_input_disabled) == 0) printk(KERN_DEBUG "rfkill: input handler enabled\n"); #endif kfree(data); return 0; } static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct rfkill_data *data = file->private_data; int ret = -ENOTTY; u32 size; if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC) return -ENOTTY; mutex_lock(&data->mtx); switch (_IOC_NR(cmd)) { #ifdef CONFIG_RFKILL_INPUT case RFKILL_IOC_NOINPUT: if (!data->input_handler) { if (atomic_inc_return(&rfkill_input_disabled) == 1) printk(KERN_DEBUG "rfkill: input handler disabled\n"); data->input_handler = true; } ret = 0; break; #endif case RFKILL_IOC_MAX_SIZE: if (get_user(size, (__u32 __user *)arg)) { ret = -EFAULT; break; } if (size < RFKILL_EVENT_SIZE_V1 || size > U8_MAX) { ret = -EINVAL; break; } data->max_size = size; ret = 0; break; default: break; } mutex_unlock(&data->mtx); return ret; } static const struct file_operations rfkill_fops = { .owner = THIS_MODULE, .open = rfkill_fop_open, .read = rfkill_fop_read, .write = rfkill_fop_write, .poll = rfkill_fop_poll, .release = rfkill_fop_release, .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; #define RFKILL_NAME "rfkill" static struct miscdevice rfkill_miscdev = { .fops = &rfkill_fops, .name = RFKILL_NAME, .minor = RFKILL_MINOR, }; static int __init rfkill_init(void) { int error; rfkill_update_global_state(RFKILL_TYPE_ALL, !rfkill_default_state); error = class_register(&rfkill_class); if (error) goto error_class; error = misc_register(&rfkill_miscdev); if (error) goto error_misc; error = rfkill_global_led_trigger_register(); if (error) goto error_led_trigger; #ifdef CONFIG_RFKILL_INPUT error = rfkill_handler_init(); if (error) goto error_input; #endif return 0; #ifdef CONFIG_RFKILL_INPUT error_input: rfkill_global_led_trigger_unregister(); #endif error_led_trigger: misc_deregister(&rfkill_miscdev); error_misc: class_unregister(&rfkill_class); error_class: return error; } subsys_initcall(rfkill_init); static void __exit rfkill_exit(void) { #ifdef CONFIG_RFKILL_INPUT rfkill_handler_exit(); #endif rfkill_global_led_trigger_unregister(); misc_deregister(&rfkill_miscdev); class_unregister(&rfkill_class); } module_exit(rfkill_exit); MODULE_ALIAS_MISCDEV(RFKILL_MINOR); MODULE_ALIAS("devname:" RFKILL_NAME); |
| 71 71 71 71 71 44 44 44 34 34 34 34 34 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2022, SUSE. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/spinlock.h> #include "protocol.h" static DEFINE_SPINLOCK(mptcp_sched_list_lock); static LIST_HEAD(mptcp_sched_list); static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk, struct mptcp_sched_data *data) { struct sock *ssk; ssk = data->reinject ? mptcp_subflow_get_retrans(msk) : mptcp_subflow_get_send(msk); if (!ssk) return -EINVAL; mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true); return 0; } static struct mptcp_sched_ops mptcp_sched_default = { .get_subflow = mptcp_sched_default_get_subflow, .name = "default", .owner = THIS_MODULE, }; /* Must be called with rcu read lock held */ struct mptcp_sched_ops *mptcp_sched_find(const char *name) { struct mptcp_sched_ops *sched, *ret = NULL; list_for_each_entry_rcu(sched, &mptcp_sched_list, list) { if (!strcmp(sched->name, name)) { ret = sched; break; } } return ret; } int mptcp_register_scheduler(struct mptcp_sched_ops *sched) { if (!sched->get_subflow) return -EINVAL; spin_lock(&mptcp_sched_list_lock); if (mptcp_sched_find(sched->name)) { spin_unlock(&mptcp_sched_list_lock); return -EEXIST; } list_add_tail_rcu(&sched->list, &mptcp_sched_list); spin_unlock(&mptcp_sched_list_lock); pr_debug("%s registered", sched->name); return 0; } void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched) { if (sched == &mptcp_sched_default) return; spin_lock(&mptcp_sched_list_lock); list_del_rcu(&sched->list); spin_unlock(&mptcp_sched_list_lock); } void mptcp_sched_init(void) { mptcp_register_scheduler(&mptcp_sched_default); } int mptcp_init_sched(struct mptcp_sock *msk, struct mptcp_sched_ops *sched) { if (!sched) sched = &mptcp_sched_default; if (!bpf_try_module_get(sched, sched->owner)) return -EBUSY; msk->sched = sched; if (msk->sched->init) msk->sched->init(msk); pr_debug("sched=%s", msk->sched->name); return 0; } void mptcp_release_sched(struct mptcp_sock *msk) { struct mptcp_sched_ops *sched = msk->sched; if (!sched) return; msk->sched = NULL; if (sched->release) sched->release(msk); bpf_module_put(sched, sched->owner); } void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow, bool scheduled) { WRITE_ONCE(subflow->scheduled, scheduled); } int mptcp_sched_get_send(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct mptcp_sched_data data; msk_owned_by_me(msk); /* the following check is moved out of mptcp_subflow_get_send */ if (__mptcp_check_fallback(msk)) { if (msk->first && __tcp_can_send(msk->first) && sk_stream_memory_free(msk->first)) { mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true); return 0; } return -EINVAL; } mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) return 0; } data.reinject = false; if (msk->sched == &mptcp_sched_default || !msk->sched) return mptcp_sched_default_get_subflow(msk, &data); return msk->sched->get_subflow(msk, &data); } int mptcp_sched_get_retrans(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct mptcp_sched_data data; msk_owned_by_me(msk); /* the following check is moved out of mptcp_subflow_get_retrans */ if (__mptcp_check_fallback(msk)) return -EINVAL; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) return 0; } data.reinject = true; if (msk->sched == &mptcp_sched_default || !msk->sched) return mptcp_sched_default_get_subflow(msk, &data); return msk->sched->get_subflow(msk, &data); } |
| 6 2 21 21 21 8 8 8 6 2 8 3 1 1 1 1 1 1 1 1 2 2 11 1 4 2 1 7 2 5 1 28 3 2 2 7 8 1 1 1 3 50 15 36 12 12 4 11 11 11 5 5 5 5 8 8 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/dccp/proto.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/random.h> #include <linux/slab.h> #include <net/checksum.h> #include <net/inet_sock.h> #include <net/inet_common.h> #include <net/sock.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/delay.h> #include <linux/poll.h> #include "ccid.h" #include "dccp.h" #include "feat.h" #define CREATE_TRACE_POINTS #include "trace.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); DEFINE_PER_CPU(unsigned int, dccp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); /* the maximum queue length for tx in packets. 0 is no limit */ int sysctl_dccp_tx_qlen __read_mostly = 5; #ifdef CONFIG_IP_DCCP_DEBUG static const char *dccp_state_name(const int state) { static const char *const dccp_state_names[] = { [DCCP_OPEN] = "OPEN", [DCCP_REQUESTING] = "REQUESTING", [DCCP_PARTOPEN] = "PARTOPEN", [DCCP_LISTEN] = "LISTEN", [DCCP_RESPOND] = "RESPOND", [DCCP_CLOSING] = "CLOSING", [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", [DCCP_TIME_WAIT] = "TIME_WAIT", [DCCP_CLOSED] = "CLOSED", }; if (state >= DCCP_MAX_STATES) return "INVALID STATE!"; else return dccp_state_names[state]; } #endif void dccp_set_state(struct sock *sk, const int state) { const int oldstate = sk->sk_state; dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk, dccp_state_name(oldstate), dccp_state_name(state)); WARN_ON(state == oldstate); switch (state) { case DCCP_OPEN: if (oldstate != DCCP_OPEN) DCCP_INC_STATS(DCCP_MIB_CURRESTAB); /* Client retransmits all Confirm options until entering OPEN */ if (oldstate == DCCP_PARTOPEN) dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg); break; case DCCP_CLOSED: if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ || oldstate == DCCP_CLOSING) DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_set_state(sk, state); } EXPORT_SYMBOL_GPL(dccp_set_state); static void dccp_finish_passive_close(struct sock *sk) { switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: /* Node (client or server) has received Close packet. */ dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); dccp_set_state(sk, DCCP_CLOSED); break; case DCCP_PASSIVE_CLOSEREQ: /* * Client received CloseReq. We set the `active' flag so that * dccp_send_close() retransmits the Close as per RFC 4340, 8.3. */ dccp_send_close(sk, 1); dccp_set_state(sk, DCCP_CLOSING); } } void dccp_done(struct sock *sk) { dccp_set_state(sk, DCCP_CLOSED); dccp_clear_xmit_timers(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(dccp_done); const char *dccp_packet_name(const int type) { static const char *const dccp_packet_names[] = { [DCCP_PKT_REQUEST] = "REQUEST", [DCCP_PKT_RESPONSE] = "RESPONSE", [DCCP_PKT_DATA] = "DATA", [DCCP_PKT_ACK] = "ACK", [DCCP_PKT_DATAACK] = "DATAACK", [DCCP_PKT_CLOSEREQ] = "CLOSEREQ", [DCCP_PKT_CLOSE] = "CLOSE", [DCCP_PKT_RESET] = "RESET", [DCCP_PKT_SYNC] = "SYNC", [DCCP_PKT_SYNCACK] = "SYNCACK", }; if (type >= DCCP_NR_PKT_TYPES) return "INVALID"; else return dccp_packet_names[type]; } EXPORT_SYMBOL_GPL(dccp_packet_name); void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; } EXPORT_SYMBOL_GPL(dccp_destruct_common); static void dccp_sk_destruct(struct sock *sk) { dccp_destruct_common(sk); inet_sock_destruct(sk); } int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); pr_warn_once("DCCP is deprecated and scheduled to be removed in 2025, " "please contact the netdev mailing list\n"); icsk->icsk_rto = DCCP_TIMEOUT_INIT; icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; sk->sk_write_space = dccp_write_space; sk->sk_destruct = dccp_sk_destruct; icsk->icsk_sync_mss = dccp_sync_mss; dp->dccps_mss_cache = 536; dp->dccps_rate_last = jiffies; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); INIT_LIST_HEAD(&dp->dccps_featneg); /* control socket doesn't need feat nego */ if (likely(ctl_sock_initialized)) return dccp_feat_init(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_init_sock); void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } /* Clean up a referenced DCCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash != NULL) inet_put_port(sk); kfree(dp->dccps_service_list); dp->dccps_service_list = NULL; if (dp->dccps_hc_rx_ackvec != NULL) { dccp_ackvec_free(dp->dccps_hc_rx_ackvec); dp->dccps_hc_rx_ackvec = NULL; } ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; /* clean up feature negotiation state */ dccp_feat_list_purge(&dp->dccps_featneg); } EXPORT_SYMBOL_GPL(dccp_destroy_sock); static inline int dccp_need_reset(int state) { return state != DCCP_CLOSED && state != DCCP_LISTEN && state != DCCP_REQUESTING; } int dccp_disconnect(struct sock *sk, int flags) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); const int old_state = sk->sk_state; if (old_state != DCCP_CLOSED) dccp_set_state(sk, DCCP_CLOSED); /* * This corresponds to the ABORT function of RFC793, sec. 3.8 * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted". */ if (old_state == DCCP_LISTEN) { inet_csk_listen_stop(sk); } else if (dccp_need_reset(old_state)) { dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); sk->sk_err = ECONNRESET; } else if (old_state == DCCP_REQUESTING) sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { __kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); icsk->icsk_backoff = 0; inet_csk_delack_init(sk); __sk_dst_reset(sk); WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk_error_report(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_disconnect); /* * Wait for a DCCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask; u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events by poll logic and correct handling of state changes made by another threads is impossible in any case. */ mask = 0; if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. */ if (sk_stream_is_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; } } } return mask; } EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) goto out; switch (cmd) { case SIOCOUTQ: { *karg = sk_wmem_alloc_get(sk); /* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and * always 0, comparably to UDP. */ rc = 0; } break; case SIOCINQ: { struct sk_buff *skb; *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { /* * We will only return the amount of this packet since * that is all that will be read. */ *karg = skb->len; } rc = 0; } break; default: rc = -ENOIOCTLCMD; break; } out: release_sock(sk); return rc; } EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; if (service == DCCP_SERVICE_INVALID_VALUE || optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32)) return -EINVAL; if (optlen > sizeof(service)) { sl = kmalloc(optlen, GFP_KERNEL); if (sl == NULL) return -ENOMEM; sl->dccpsl_nr = optlen / sizeof(u32) - 1; if (copy_from_sockptr_offset(sl->dccpsl_list, optval, sizeof(service), optlen - sizeof(service)) || dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) { kfree(sl); return -EFAULT; } } lock_sock(sk); dp->dccps_service = service; kfree(dp->dccps_service_list); dp->dccps_service_list = sl; release_sock(sk); return 0; } static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) { u8 *list, len; int i, rc; if (cscov < 0 || cscov > 15) return -EINVAL; /* * Populate a list of permissible values, in the range cscov...15. This * is necessary since feature negotiation of single values only works if * both sides incidentally choose the same value. Since the list starts * lowest-value first, negotiation will pick the smallest shared value. */ if (cscov == 0) return 0; len = 16 - cscov; list = kmalloc(len, GFP_KERNEL); if (list == NULL) return -ENOBUFS; for (i = 0; i < len; i++) list[i] = cscov++; rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len); if (rc == 0) { if (rx) dccp_sk(sk)->dccps_pcrlen = cscov; else dccp_sk(sk)->dccps_pcslen = cscov; } kfree(list); return rc; } static int dccp_setsockopt_ccid(struct sock *sk, int type, sockptr_t optval, unsigned int optlen) { u8 *val; int rc = 0; if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) return -EINVAL; val = memdup_sockptr(optval, optlen); if (IS_ERR(val)) return PTR_ERR(val); lock_sock(sk); if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen); if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID)) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen); release_sock(sk); kfree(val); return rc; } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CHANGE_L: case DCCP_SOCKOPT_CHANGE_R: DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CCID: case DCCP_SOCKOPT_RX_CCID: case DCCP_SOCKOPT_TX_CCID: return dccp_setsockopt_ccid(sk, optname, optval, optlen); } if (optlen < (int)sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; if (optname == DCCP_SOCKOPT_SERVICE) return dccp_setsockopt_service(sk, val, optval, optlen); lock_sock(sk); switch (optname) { case DCCP_SOCKOPT_SERVER_TIMEWAIT: if (dp->dccps_role != DCCP_ROLE_SERVER) err = -EOPNOTSUPP; else dp->dccps_server_timewait = (val != 0); break; case DCCP_SOCKOPT_SEND_CSCOV: err = dccp_setsockopt_cscov(sk, val, false); break; case DCCP_SOCKOPT_RECV_CSCOV: err = dccp_setsockopt_cscov(sk, val, true); break; case DCCP_SOCKOPT_QPOLICY_ID: if (sk->sk_state != DCCP_CLOSED) err = -EISCONN; else if (val < 0 || val >= DCCPQ_POLICY_MAX) err = -EINVAL; else dp->dccps_qpolicy = val; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: if (val < 0) err = -EINVAL; else dp->dccps_tx_qlen = val; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, optname, optval, optlen); return do_dccp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_setsockopt); static int dccp_getsockopt_service(struct sock *sk, int len, __be32 __user *optval, int __user *optlen) { const struct dccp_sock *dp = dccp_sk(sk); const struct dccp_service_list *sl; int err = -ENOENT, slen = 0, total_len = sizeof(u32); lock_sock(sk); if ((sl = dp->dccps_service_list) != NULL) { slen = sl->dccpsl_nr * sizeof(u32); total_len += slen; } err = -EINVAL; if (total_len > len) goto out; err = 0; if (put_user(total_len, optlen) || put_user(dp->dccps_service, optval) || (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen))) err = -EFAULT; out: release_sock(sk); return err; } static int do_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct dccp_sock *dp; int val, len; if (get_user(len, optlen)) return -EFAULT; if (len < (int)sizeof(int)) return -EINVAL; dp = dccp_sk(sk); switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_SERVICE: return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); case DCCP_SOCKOPT_TX_CCID: val = ccid_get_current_tx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_RX_CCID: val = ccid_get_current_rx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_SERVER_TIMEWAIT: val = dp->dccps_server_timewait; break; case DCCP_SOCKOPT_SEND_CSCOV: val = dp->dccps_pcslen; break; case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; case DCCP_SOCKOPT_QPOLICY_ID: val = dp->dccps_qpolicy; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: val = dp->dccps_tx_qlen; break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); case 192 ... 255: return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname, len, (u32 __user *)optval, optlen); default: return -ENOPROTOOPT; } len = sizeof(val); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, optname, optval, optlen); return do_dccp_getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_getsockopt); static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) { struct cmsghdr *cmsg; /* * Assign an (opaque) qpolicy priority value to skb->priority. * * We are overloading this skb field for use with the qpolicy subystem. * The skb->priority is normally used for the SO_PRIORITY option, which * is initialised from sk_priority. Since the assignment of sk_priority * to skb->priority happens later (on layer 3), we overload this field * for use with queueing priorities as long as the skb is on layer 4. * The default priority value (if nothing is set) is 0. */ skb->priority = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_DCCP) continue; if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX && !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type)) return -EINVAL; switch (cmsg->cmsg_type) { case DCCP_SCM_PRIORITY: if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) return -EINVAL; skb->priority = *(__u32 *)CMSG_DATA(cmsg); break; default: return -EINVAL; } } return 0; } int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { const struct dccp_sock *dp = dccp_sk(sk); const int flags = msg->msg_flags; const int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; int rc, size; long timeo; trace_dccp_probe(sk, len); if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); timeo = sock_sndtimeo(sk, noblock); /* * We have to use sk_stream_wait_connect here to set sk_write_pending, * so that the trick in dccp_rcv_request_sent_state_process. */ /* Wait for a connection to finish. */ if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_release; size = sk->sk_prot->max_header + len; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (skb == NULL) goto out_release; if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_discard; } if (sk->sk_state == DCCP_CLOSED) { rc = -ENOTCONN; goto out_discard; } /* We need to check dccps_mss_cache after socket is locked. */ if (len > dp->dccps_mss_cache) { rc = -EMSGSIZE; goto out_discard; } skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) goto out_discard; rc = dccp_msghdr_parse(msg, skb); if (rc != 0) goto out_discard; dccp_qpolicy_push(sk, skb); /* * The xmit_timer is set if the TX CCID is rate-based and will expire * when congestion control permits to release further packets into the * network. Window-based CCIDs do not use this timer. */ if (!timer_pending(&dp->dccps_xmit_timer)) dccp_write_xmit(sk); out_release: release_sock(sk); return rc ? : len; out_discard: kfree_skb(skb); goto out_release; } EXPORT_SYMBOL_GPL(dccp_sendmsg); int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { const struct dccp_hdr *dh; long timeo; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) { len = -ENOTCONN; goto out; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); if (skb == NULL) goto verify_sock_status; dh = dccp_hdr(skb); switch (dh->dccph_type) { case DCCP_PKT_DATA: case DCCP_PKT_DATAACK: goto found_ok_skb; case DCCP_PKT_CLOSE: case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); len = 0; goto found_fin_ok; default: dccp_pr_debug("packet_type=%s\n", dccp_packet_name(dh->dccph_type)); sk_eat_skb(sk, skb); } verify_sock_status: if (sock_flag(sk, SOCK_DONE)) { len = 0; break; } if (sk->sk_err) { len = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) { len = 0; break; } if (sk->sk_state == DCCP_CLOSED) { if (!sock_flag(sk, SOCK_DONE)) { /* This occurs when user tries to read * from never connected socket. */ len = -ENOTCONN; break; } len = 0; break; } if (!timeo) { len = -EAGAIN; break; } if (signal_pending(current)) { len = sock_intr_errno(timeo); break; } sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) len = skb->len; else if (len < skb->len) msg->msg_flags |= MSG_TRUNC; if (skb_copy_datagram_msg(skb, 0, msg, len)) { /* Exception. Bailout! */ len = -EFAULT; break; } if (flags & MSG_TRUNC) len = skb->len; found_fin_ok: if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; } while (1); out: release_sock(sk); return len; } EXPORT_SYMBOL_GPL(dccp_recvmsg); int inet_dccp_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err; lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP) goto out; old_state = sk->sk_state; if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) goto out; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != DCCP_LISTEN) { struct dccp_sock *dp = dccp_sk(sk); dp->dccps_role = DCCP_ROLE_LISTEN; /* do not start to listen if feature negotiation setup fails */ if (dccp_feat_finalise_settings(dp)) { err = -EPROTO; goto out; } err = inet_csk_listen_start(sk); if (err) goto out; } err = 0; out: release_sock(sk); return err; } EXPORT_SYMBOL_GPL(inet_dccp_listen); static void dccp_terminate_connection(struct sock *sk) { u8 next_state = DCCP_CLOSED; switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: case DCCP_PASSIVE_CLOSEREQ: dccp_finish_passive_close(sk); break; case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER && !dccp_sk(sk)->dccps_server_timewait) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; fallthrough; default: dccp_set_state(sk, next_state); } } void dccp_close(struct sock *sk, long timeout) { struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; u32 data_was_unread = 0; int state; lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == DCCP_LISTEN) { dccp_set_state(sk, DCCP_CLOSED); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } sk_stop_timer(sk, &dp->dccps_xmit_timer); /* * We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the *reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { data_was_unread += skb->len; __kfree_skb(skb); } /* If socket has been already reset kill it. */ if (sk->sk_state == DCCP_CLOSED) goto adjudge_to_death; if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_set_state(sk, DCCP_CLOSED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); } else if (sk->sk_state != DCCP_CLOSED) { /* * Normal connection termination. May need to wait if there are * still packets in the TX queue that are delayed by the CCID. */ dccp_flush_write_queue(sk, &timeout); dccp_terminate_connection(sk); } /* * Flush write queue. This may be necessary in several cases: * - we have been closed by the peer but still have application data; * - abortive termination (unread data or zero linger time), * - normal termination but queue could not be flushed within time limit */ __skb_queue_purge(&sk->sk_write_queue); sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); /* * It is the last release_sock in its life. It will remove backlog. */ release_sock(sk); /* * Now socket is owned by kernel and we acquire BH lock * to finish close. No need to check for user refs. */ local_bh_disable(); bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) goto out; if (sk->sk_state == DCCP_CLOSED) inet_csk_destroy_sock(sk); /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); sock_put(sk); } EXPORT_SYMBOL_GPL(dccp_close); void dccp_shutdown(struct sock *sk, int how) { dccp_pr_debug("called shutdown(%x)\n", how); } EXPORT_SYMBOL_GPL(dccp_shutdown); static inline int __init dccp_mib_init(void) { dccp_statistics = alloc_percpu(struct dccp_mib); if (!dccp_statistics) return -ENOMEM; return 0; } static inline void dccp_mib_exit(void) { free_percpu(dccp_statistics); } static int thash_entries; module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); #ifdef CONFIG_IP_DCCP_DEBUG bool dccp_debug; module_param(dccp_debug, bool, 0644); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); EXPORT_SYMBOL_GPL(dccp_debug); #endif static int __init dccp_init(void) { unsigned long goal; unsigned long nr_pages = totalram_pages(); int ehash_order, bhash_order, i; int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) goto out_fail; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; dccp_hashinfo.bind2_bucket_cachep = kmem_cache_create("dccp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind2_bucket_cachep) goto out_free_bind_bucket_cachep; /* * Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ if (nr_pages >= (128 * 1024)) goal = nr_pages >> (21 - PAGE_SHIFT); else goal = nr_pages >> (23 - PAGE_SHIFT); if (thash_entries) goal = (thash_entries * sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT; for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++) ; do { unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE / sizeof(struct inet_ehash_bucket); while (hash_size & (hash_size - 1)) hash_size--; dccp_hashinfo.ehash_mask = hash_size - 1; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); goto out_free_bind2_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&dccp_hashinfo)) goto out_free_dccp_ehash; bhash_order = ehash_order; do { dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE / sizeof(struct inet_bind_hashbucket); if ((dccp_hashinfo.bhash_size > (64 * 1024)) && bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { DCCP_CRIT("Failed to allocate DCCP bind hash table"); goto out_free_dccp_locks; } dccp_hashinfo.bhash2 = (struct inet_bind_hashbucket *) __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order); if (!dccp_hashinfo.bhash2) { DCCP_CRIT("Failed to allocate DCCP bind2 hash table"); goto out_free_dccp_bhash; } for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); spin_lock_init(&dccp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain); } dccp_hashinfo.pernet = false; rc = dccp_mib_init(); if (rc) goto out_free_dccp_bhash2; rc = dccp_ackvec_init(); if (rc) goto out_free_dccp_mib; rc = dccp_sysctl_init(); if (rc) goto out_ackvec_exit; rc = ccid_initialize_builtins(); if (rc) goto out_sysctl_exit; dccp_timestamping_init(); return 0; out_sysctl_exit: dccp_sysctl_exit(); out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); out_free_dccp_bhash2: free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); out_free_bind2_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; dccp_hashinfo.bhash2 = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; dccp_hashinfo.bind2_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { int bhash_order = get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)); ccid_cleanup_builtins(); dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); inet_hashinfo2_free_mod(&dccp_hashinfo); } module_init(dccp_init); module_exit(dccp_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); |
| 1 1 1 1 1528 1528 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007, 2008, 2009 Siemens AG */ #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <net/cfg802154.h> #include <net/rtnetlink.h> #include "ieee802154.h" #include "nl802154.h" #include "sysfs.h" #include "core.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" /* RCU-protected (and RTNL for writers) */ LIST_HEAD(cfg802154_rdev_list); int cfg802154_rdev_list_generation; struct wpan_phy *wpan_phy_find(const char *str) { struct device *dev; if (WARN_ON(!str)) return NULL; dev = class_find_device_by_name(&wpan_phy_class, str); if (!dev) return NULL; return container_of(dev, struct wpan_phy, dev); } EXPORT_SYMBOL(wpan_phy_find); struct wpan_phy_iter_data { int (*fn)(struct wpan_phy *phy, void *data); void *data; }; static int wpan_phy_iter(struct device *dev, void *_data) { struct wpan_phy_iter_data *wpid = _data; struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); return wpid->fn(phy, wpid->data); } int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data) { struct wpan_phy_iter_data wpid = { .fn = fn, .data = data, }; return class_for_each_device(&wpan_phy_class, NULL, &wpid, wpan_phy_iter); } EXPORT_SYMBOL(wpan_phy_for_each); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx) { struct cfg802154_registered_device *result = NULL, *rdev; ASSERT_RTNL(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (rdev->wpan_phy_idx == wpan_phy_idx) { result = rdev; break; } } return result; } struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx) { struct cfg802154_registered_device *rdev; ASSERT_RTNL(); rdev = cfg802154_rdev_by_wpan_phy_idx(wpan_phy_idx); if (!rdev) return NULL; return &rdev->wpan_phy; } struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) { static atomic_t wpan_phy_counter = ATOMIC_INIT(0); struct cfg802154_registered_device *rdev; size_t alloc_size; alloc_size = sizeof(*rdev) + priv_size; rdev = kzalloc(alloc_size, GFP_KERNEL); if (!rdev) return NULL; rdev->ops = ops; rdev->wpan_phy_idx = atomic_inc_return(&wpan_phy_counter); if (unlikely(rdev->wpan_phy_idx < 0)) { /* ugh, wrapped! */ atomic_dec(&wpan_phy_counter); kfree(rdev); return NULL; } /* atomic_inc_return makes it start at 1, make it start at 0 */ rdev->wpan_phy_idx--; INIT_LIST_HEAD(&rdev->wpan_dev_list); device_initialize(&rdev->wpan_phy.dev); dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx); rdev->wpan_phy.dev.class = &wpan_phy_class; rdev->wpan_phy.dev.platform_data = rdev; wpan_phy_net_set(&rdev->wpan_phy, &init_net); init_waitqueue_head(&rdev->dev_wait); init_waitqueue_head(&rdev->wpan_phy.sync_txq); spin_lock_init(&rdev->wpan_phy.queue_lock); return &rdev->wpan_phy; } EXPORT_SYMBOL(wpan_phy_new); int wpan_phy_register(struct wpan_phy *phy) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy); int ret; rtnl_lock(); ret = device_add(&phy->dev); if (ret) { rtnl_unlock(); return ret; } list_add_rcu(&rdev->list, &cfg802154_rdev_list); cfg802154_rdev_list_generation++; /* TODO phy registered lock */ rtnl_unlock(); /* TODO nl802154 phy notify */ return 0; } EXPORT_SYMBOL(wpan_phy_register); void wpan_phy_unregister(struct wpan_phy *phy) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy); wait_event(rdev->dev_wait, ({ int __count; rtnl_lock(); __count = rdev->opencount; rtnl_unlock(); __count == 0; })); rtnl_lock(); /* TODO nl802154 phy notify */ /* TODO phy registered lock */ WARN_ON(!list_empty(&rdev->wpan_dev_list)); /* First remove the hardware from everywhere, this makes * it impossible to find from userspace. */ list_del_rcu(&rdev->list); synchronize_rcu(); cfg802154_rdev_list_generation++; device_del(&phy->dev); rtnl_unlock(); } EXPORT_SYMBOL(wpan_phy_unregister); void wpan_phy_free(struct wpan_phy *phy) { put_device(&phy->dev); } EXPORT_SYMBOL(wpan_phy_free); static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev) { struct ieee802154_pan_device *child, *tmp; mutex_lock(&wpan_dev->association_lock); kfree(wpan_dev->parent); wpan_dev->parent = NULL; list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) { list_del(&child->node); kfree(child); } wpan_dev->nchildren = 0; mutex_unlock(&wpan_dev->association_lock); } int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, struct net *net) { struct wpan_dev *wpan_dev; int err = 0; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); if (err) break; wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; } if (err) { /* failed -- clean up to old netns */ net = wpan_phy_net(&rdev->wpan_phy); list_for_each_entry_continue_reverse(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); WARN_ON(err); wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; } return err; } wpan_phy_net_set(&rdev->wpan_phy, net); err = device_rename(&rdev->wpan_phy.dev, dev_name(&rdev->wpan_phy.dev)); WARN_ON(err); return 0; } void cfg802154_dev_free(struct cfg802154_registered_device *rdev) { kfree(rdev); } static void cfg802154_update_iface_num(struct cfg802154_registered_device *rdev, int iftype, int num) { ASSERT_RTNL(); rdev->num_running_ifaces += num; } static int cfg802154_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct cfg802154_registered_device *rdev; if (!wpan_dev) return NOTIFY_DONE; rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); /* TODO WARN_ON unspec type */ switch (state) { /* TODO NETDEV_DEVTYPE */ case NETDEV_REGISTER: dev->features |= NETIF_F_NETNS_LOCAL; wpan_dev->identifier = ++rdev->wpan_dev_id; list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list); rdev->devlist_generation++; mutex_init(&wpan_dev->association_lock); INIT_LIST_HEAD(&wpan_dev->children); wpan_dev->max_associations = SZ_16K; wpan_dev->netdev = dev; break; case NETDEV_DOWN: cfg802154_update_iface_num(rdev, wpan_dev->iftype, -1); rdev->opencount--; wake_up(&rdev->dev_wait); break; case NETDEV_UP: cfg802154_update_iface_num(rdev, wpan_dev->iftype, 1); rdev->opencount++; break; case NETDEV_UNREGISTER: cfg802154_free_peer_structures(wpan_dev); /* It is possible to get NETDEV_UNREGISTER * multiple times. To detect that, check * that the interface is still on the list * of registered interfaces, and only then * remove and clean it up. */ if (!list_empty(&wpan_dev->list)) { list_del_rcu(&wpan_dev->list); rdev->devlist_generation++; } /* synchronize (so that we won't find this netdev * from other code any more) and then clear the list * head so that the above code can safely check for * !list_empty() to avoid double-cleanup. */ synchronize_rcu(); INIT_LIST_HEAD(&wpan_dev->list); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block cfg802154_netdev_notifier = { .notifier_call = cfg802154_netdev_notifier_call, }; static void __net_exit cfg802154_pernet_exit(struct net *net) { struct cfg802154_registered_device *rdev; rtnl_lock(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (net_eq(wpan_phy_net(&rdev->wpan_phy), net)) WARN_ON(cfg802154_switch_netns(rdev, &init_net)); } rtnl_unlock(); } static struct pernet_operations cfg802154_pernet_ops = { .exit = cfg802154_pernet_exit, }; static int __init wpan_phy_class_init(void) { int rc; rc = register_pernet_device(&cfg802154_pernet_ops); if (rc) goto err; rc = wpan_phy_sysfs_init(); if (rc) goto err_sysfs; rc = register_netdevice_notifier(&cfg802154_netdev_notifier); if (rc) goto err_nl; rc = ieee802154_nl_init(); if (rc) goto err_notifier; rc = nl802154_init(); if (rc) goto err_ieee802154_nl; return 0; err_ieee802154_nl: ieee802154_nl_exit(); err_notifier: unregister_netdevice_notifier(&cfg802154_netdev_notifier); err_nl: wpan_phy_sysfs_exit(); err_sysfs: unregister_pernet_device(&cfg802154_pernet_ops); err: return rc; } subsys_initcall(wpan_phy_class_init); static void __exit wpan_phy_class_exit(void) { nl802154_exit(); ieee802154_nl_exit(); unregister_netdevice_notifier(&cfg802154_netdev_notifier); wpan_phy_sysfs_exit(); unregister_pernet_device(&cfg802154_pernet_ops); } module_exit(wpan_phy_class_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface"); MODULE_AUTHOR("Dmitry Eremin-Solenikov"); |
| 11 11 11 5229 5226 | 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 /* * x86 specific code for irq_work * * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> #include <linux/irq_work.h> #include <linux/hardirq.h> #include <asm/apic.h> #include <asm/idtentry.h> #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> #ifdef CONFIG_X86_LOCAL_APIC DEFINE_IDTENTRY_SYSVEC(sysvec_irq_work) { apic_eoi(); trace_irq_work_entry(IRQ_WORK_VECTOR); inc_irq_stat(apic_irq_work_irqs); irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); } void arch_irq_work_raise(void) { if (!arch_irq_work_has_interrupt()) return; __apic_send_IPI_self(IRQ_WORK_VECTOR); apic_wait_icr_idle(); } #endif |
| 72 72 72 72 52 51 45 4 3 3 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_queue.h> #include <net/ip6_checksum.h> #ifdef CONFIG_INET __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u8 protocol) { const struct iphdr *iph = ip_hdr(skb); __sum16 csum = 0; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) break; if ((protocol != IPPROTO_TCP && protocol != IPPROTO_UDP && !csum_fold(skb->csum)) || !csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len - dataoff, protocol, skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } fallthrough; case CHECKSUM_NONE: if (protocol != IPPROTO_TCP && protocol != IPPROTO_UDP) skb->csum = 0; else skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, skb->len - dataoff, protocol, 0); csum = __skb_checksum_complete(skb); } return csum; } EXPORT_SYMBOL(nf_ip_checksum); #endif static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u8 protocol) { const struct iphdr *iph = ip_hdr(skb); __sum16 csum = 0; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: if (len == skb->len - dataoff) return nf_ip_checksum(skb, hook, dataoff, protocol); fallthrough; case CHECKSUM_NONE: skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol, skb->len - dataoff, 0); skb->ip_summed = CHECKSUM_NONE; return __skb_checksum_complete_head(skb, dataoff + len); } return csum; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u8 protocol) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); __sum16 csum = 0; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) break; if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb->len - dataoff, protocol, csum_sub(skb->csum, skb_checksum(skb, 0, dataoff, 0)))) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } fallthrough; case CHECKSUM_NONE: skb->csum = ~csum_unfold( csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb->len - dataoff, protocol, csum_sub(0, skb_checksum(skb, 0, dataoff, 0)))); csum = __skb_checksum_complete(skb); } return csum; } EXPORT_SYMBOL(nf_ip6_checksum); static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u8 protocol) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); __wsum hsum; __sum16 csum = 0; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: if (len == skb->len - dataoff) return nf_ip6_checksum(skb, hook, dataoff, protocol); fallthrough; case CHECKSUM_NONE: hsum = skb_checksum(skb, 0, dataoff, 0); skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb->len - dataoff, protocol, csum_sub(0, hsum))); skb->ip_summed = CHECKSUM_NONE; return __skb_checksum_complete_head(skb, dataoff + len); } return csum; }; __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u8 protocol, unsigned short family) { __sum16 csum = 0; switch (family) { case AF_INET: csum = nf_ip_checksum(skb, hook, dataoff, protocol); break; case AF_INET6: csum = nf_ip6_checksum(skb, hook, dataoff, protocol); break; } return csum; } EXPORT_SYMBOL_GPL(nf_checksum); __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u8 protocol, unsigned short family) { __sum16 csum = 0; switch (family) { case AF_INET: csum = nf_ip_checksum_partial(skb, hook, dataoff, len, protocol); break; case AF_INET6: csum = nf_ip6_checksum_partial(skb, hook, dataoff, len, protocol); break; } return csum; } EXPORT_SYMBOL_GPL(nf_checksum_partial); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family) { const struct nf_ipv6_ops *v6ops __maybe_unused; int ret = 0; switch (family) { case AF_INET: ret = nf_ip_route(net, dst, fl, strict); break; case AF_INET6: ret = nf_ip6_route(net, dst, fl, strict); break; } return ret; } EXPORT_SYMBOL_GPL(nf_route); static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) { #ifdef CONFIG_INET const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos && skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) return ip_route_me_harder(entry->state.net, entry->state.sk, skb, RTN_UNSPEC); } #endif return 0; } int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; int ret = 0; switch (entry->state.pf) { case AF_INET: ret = nf_ip_reroute(skb, entry); break; case AF_INET6: v6ops = rcu_dereference(nf_ipv6_ops); if (v6ops) ret = v6ops->reroute(skb, entry); break; } return ret; } /* Only get and check the lengths, not do any hop-by-hop stuff. */ int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen) { int len, off = sizeof(struct ipv6hdr); unsigned char *nh; if (!pskb_may_pull(skb, off + 8)) return -ENOMEM; nh = (unsigned char *)(ipv6_hdr(skb) + 1); len = (nh[1] + 1) << 3; if (!pskb_may_pull(skb, off + len)) return -ENOMEM; nh = skb_network_header(skb); off += 2; len -= 2; while (len > 0) { int optlen; if (nh[off] == IPV6_TLV_PAD1) { off++; len--; continue; } if (len < 2) return -EBADMSG; optlen = nh[off + 1] + 2; if (optlen > len) return -EBADMSG; if (nh[off] == IPV6_TLV_JUMBO) { u32 pkt_len; if (nh[off + 1] != 4 || (off & 3) != 2) return -EBADMSG; pkt_len = ntohl(*(__be32 *)(nh + off + 2)); if (pkt_len <= IPV6_MAXPLEN || ipv6_hdr(skb)->payload_len) return -EBADMSG; if (pkt_len > skb->len - sizeof(struct ipv6hdr)) return -EBADMSG; *plen = pkt_len; } off += optlen; len -= optlen; } return len ? -EBADMSG : 0; } EXPORT_SYMBOL_GPL(nf_ip6_check_hbh_len); |
| 95 685 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NSPROXY_H #define _LINUX_NSPROXY_H #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/sched.h> struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; struct cgroup_namespace; struct fs_struct; /* * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. * * The pid namespace is an exception -- it's accessed using * task_active_pid_ns. The pid namespace here is the * namespace that children will use. * * 'count' is the number of tasks holding a reference. * The count for each namespace, then, will be the number * of nsproxies pointing to it, not the number of tasks. * * The nsproxy is shared by tasks which share all namespaces. * As soon as a single namespace is cloned or unshared, the * nsproxy is copied. */ struct nsproxy { refcount_t count; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; struct time_namespace *time_ns; struct time_namespace *time_ns_for_children; struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. * * If a new user namespace is requested cred will * point to a modifiable set of credentials. If a pointer * to a modifiable set is needed nsset_cred() must be * used and tested. */ struct nsset { unsigned flags; struct nsproxy *nsproxy; struct fs_struct *fs; const struct cred *cred; }; static inline struct cred *nsset_cred(struct nsset *set) { if (set->flags & CLONE_NEWUSER) return (struct cred *)set->cred; return NULL; } /* * the namespaces access rules are: * * 1. only current task is allowed to change tsk->nsproxy pointer or * any pointer on the nsproxy itself. Current must hold the task_lock * when changing tsk->nsproxy. * * 2. when accessing (i.e. reading) current task's namespaces - no * precautions should be taken - just dereference the pointers * * 3. the access to other task namespaces is performed like this * task_lock(task); * nsproxy = task->nsproxy; * if (nsproxy != NULL) { * / * * * work with the namespaces here * * e.g. get the reference on one of them * * / * } / * * * NULL task->nsproxy means that this task is * * almost dead (zombie) * * / * task_unlock(task); * */ int copy_namespaces(unsigned long flags, struct task_struct *tsk); void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { if (refcount_dec_and_test(&ns->count)) free_nsproxy(ns); } static inline void get_nsproxy(struct nsproxy *ns) { refcount_inc(&ns->count); } #endif |
| 13 13 1 1 1 1 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for the UDP-Lite (RFC 3828) code. */ #ifndef _UDPLITE_H #define _UDPLITE_H #include <net/ip6_checksum.h> #include <net/udp.h> /* UDP-Lite socket options */ #define UDPLITE_SEND_CSCOV 10 /* sender partial coverage (as sent) */ #define UDPLITE_RECV_CSCOV 11 /* receiver partial coverage (threshold ) */ extern struct proto udplite_prot; extern struct udp_table udplite_table; /* * Checksum computation is all in software, hence simpler getfrag. */ static __inline__ int udplite_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } /* * Checksumming routines */ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) { u16 cscov; /* In UDPv4 a zero checksum means that the transmitter generated no * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets * with a zero checksum field are illegal. */ if (uh->check == 0) { net_dbg_ratelimited("UDPLite: zeroed checksum field\n"); return 1; } cscov = ntohs(uh->len); if (cscov == 0) /* Indicates that full coverage is required. */ ; else if (cscov < 8 || cscov > skb->len) { /* * Coverage length violates RFC 3828: log and discard silently. */ net_dbg_ratelimited("UDPLite: bad csum coverage %d/%d\n", cscov, skb->len); return 1; } else if (cscov < skb->len) { UDP_SKB_CB(skb)->partial_cov = 1; UDP_SKB_CB(skb)->cscov = cscov; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; skb->csum_valid = 0; } return 0; } /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { const int off = skb_transport_offset(skb); const struct sock *sk = skb->sk; int len = skb->len - off; if (udp_test_bit(UDPLITE_SEND_CC, sk)) { u16 pcslen = READ_ONCE(udp_sk(sk)->pcslen); if (pcslen < len) { if (pcslen > 0) len = pcslen; udp_hdr(skb)->len = htons(pcslen); } } skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ return skb_checksum(skb, off, len, 0); } void udplite4_register(void); #endif /* _UDPLITE_H */ |
| 156 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #ifndef __IPVLAN_H #define __IPVLAN_H #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <net/ip.h> #include <net/ip6_route.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #define IPVLAN_DRV "ipvlan" #define IPV_DRV_VER "0.1" #define IPVLAN_HASH_SIZE (1 << BITS_PER_BYTE) #define IPVLAN_HASH_MASK (IPVLAN_HASH_SIZE - 1) #define IPVLAN_MAC_FILTER_BITS 8 #define IPVLAN_MAC_FILTER_SIZE (1 << IPVLAN_MAC_FILTER_BITS) #define IPVLAN_MAC_FILTER_MASK (IPVLAN_MAC_FILTER_SIZE - 1) #define IPVLAN_QBACKLOG_LIMIT 1000 typedef enum { IPVL_IPV6 = 0, IPVL_ICMPV6, IPVL_IPV4, IPVL_ARP, } ipvl_hdr_type; struct ipvl_pcpu_stats { u64_stats_t rx_pkts; u64_stats_t rx_bytes; u64_stats_t rx_mcast; u64_stats_t tx_pkts; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errs; u32 tx_drps; }; struct ipvl_port; struct ipvl_dev { struct net_device *dev; struct list_head pnode; struct ipvl_port *port; struct net_device *phy_dev; struct list_head addrs; struct ipvl_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; spinlock_t addrs_lock; }; struct ipvl_addr { struct ipvl_dev *master; /* Back pointer to master */ union { struct in6_addr ip6; /* IPv6 address on logical interface */ struct in_addr ip4; /* IPv4 address on logical interface */ } ipu; #define ip6addr ipu.ip6 #define ip4addr ipu.ip4 struct hlist_node hlnode; /* Hash-table linkage */ struct list_head anode; /* logical-interface linkage */ ipvl_hdr_type atype; struct rcu_head rcu; }; struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; int count; struct ida ida; netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { bool tx_pkt; }; #define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0])) static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d) { return rcu_dereference(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d) { return rcu_dereference_bh(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) { return rtnl_dereference(d->rx_handler_data); } static inline bool ipvlan_is_private(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_PRIVATE); } static inline void ipvlan_mark_private(struct ipvl_port *port) { port->flags |= IPVLAN_F_PRIVATE; } static inline void ipvlan_clear_private(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_PRIVATE; } static inline bool ipvlan_is_vepa(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_VEPA); } static inline void ipvlan_mark_vepa(struct ipvl_port *port) { port->flags |= IPVLAN_F_VEPA; } static inline void ipvlan_clear_vepa(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_VEPA; } void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); void ipvlan_process_multicast(struct work_struct *work); int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev); void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr); struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, int addr_type, bool use_dest); void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); #ifdef CONFIG_IPVLAN_L3S int ipvlan_l3s_register(struct ipvl_port *port); void ipvlan_l3s_unregister(struct ipvl_port *port); void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); int ipvlan_l3s_init(void); void ipvlan_l3s_cleanup(void); #else static inline int ipvlan_l3s_register(struct ipvl_port *port) { return -ENOTSUPP; } static inline void ipvlan_l3s_unregister(struct ipvl_port *port) { } static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) { } static inline int ipvlan_l3s_init(void) { return 0; } static inline void ipvlan_l3s_cleanup(void) { } #endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame; } #endif /* __IPVLAN_H */ |
| 34 34 13 10 3 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 | // 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; /* Send out corked data remaining in sndbuf */ smc_tx_pending(&smc->conn); 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) { write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); 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(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(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); } |
| 172 172 1 171 1 177 177 177 34 34 36 35 1 34 3 1 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/kernel.h> #include <net/dst_metadata.h> #include <net/udp.h> #include <net/udp_tunnel.h> int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { int err; struct socket *sock = NULL; struct sockaddr_in udp_addr; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->peer_ip; udp_addr.sin_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr), 0); if (err < 0) goto error; } sock->sk->sk_no_check_tx = !cfg->use_udp_checksums; *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL(udp_sock_create4); void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *cfg) { struct sock *sk = sock->sk; /* Disable multicast loopback */ inet_clear_bit(MC_LOOP, sk); /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ inet_inc_convert_csum(sk); rcu_assign_sk_user_data(sk, cfg->sk_user_data); udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv; udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup; udp_sk(sk)->encap_destroy = cfg->encap_destroy; udp_sk(sk)->gro_receive = cfg->gro_receive; udp_sk(sk)->gro_complete = cfg->gro_complete; udp_tunnel_encap_enable(sk); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct udp_tunnel_info ti; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; udp_tunnel_nic_add_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct udp_tunnel_info ti; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; udp_tunnel_nic_del_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port); /* Notify netdevs that UDP port started listening */ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { udp_tunnel_nic_add_port(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port); /* Notify netdevs that UDP port is no more listening */ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { udp_tunnel_nic_del_port(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port); 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) { struct udphdr *uh; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); synchronize_rcu(); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; if (family == AF_INET) tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size); else tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) info->key.tun_flags |= TUNNEL_CSUM; return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, int oif, __be32 *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache) { struct rtable *rt = NULL; struct flowi4 fl4; #ifdef CONFIG_DST_CACHE if (dst_cache) { rt = dst_cache_get_ip4(dst_cache, saddr); if (rt) return rt; } #endif memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_mark = skb->mark; fl4.flowi4_proto = IPPROTO_UDP; fl4.flowi4_oif = oif; fl4.daddr = key->u.ipv4.dst; fl4.saddr = key->u.ipv4.src; fl4.fl4_dport = dport; fl4.fl4_sport = sport; fl4.flowi4_tos = RT_TOS(tos); fl4.flowi4_flags = key->flow_flags; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); return ERR_PTR(-ENETUNREACH); } if (rt->dst.dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); ip_rt_put(rt); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (dst_cache) dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); #endif *saddr = fl4.saddr; return rt; } EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup); MODULE_LICENSE("GPL"); |
| 6 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 | // SPDX-License-Identifier: GPL-2.0-or-later /* * DCCP over IPv6 * Linux INET6 implementation * * Based on net/dccp6/ipv6.c * * Arnaldo Carvalho de Melo <acme@ghostprotocols.net> */ #include <linux/module.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/xfrm.h> #include <linux/string.h> #include <net/addrconf.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> #include <net/inet6_connection_sock.h> #include <net/inet6_hashtables.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/netns/generic.h> #include <net/sock.h> #include "dccp.h" #include "ipv6.h" #include "feat.h" struct dccp_v6_pernet { struct sock *v6_ctl_sk; }; static unsigned int dccp_v6_pernet_id __read_mostly; /* The per-net v6_ctl_sk is used for sending RSTs and ACKs */ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr) { return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr); } static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, dccp_hdr(skb)->dccph_dport, dccp_hdr(skb)->dccph_sport ); } static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr; const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, offset + sizeof(*dh))) return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; hdr = (const struct ipv6hdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, ntohs(dh->dccph_sport), inet6_iif(skb), 0); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = dccp_hdr_seq(dh); if (sk->sk_state == DCCP_NEW_SYN_RECV) { dccp_req_err(sk, seq); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (!ip6_sk_accept_pmtu(sk)) goto out; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; dst = inet6_csk_update_pmtu(sk, ntohl(info)); if (!dst) goto out; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk_error_report(sk); dccp_done(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } goto out; } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { sk->sk_err = err; sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct in6_addr *final_p, final; struct flowi6 fl6; int err = -1; struct dst_entry *dst; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; fl6.daddr = ireq->ir_v6_rmt_addr; fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = ireq->ir_iif; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = htons(ireq->ir_num); security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); rcu_read_lock(); final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto done; } skb = dccp_make_response(sk, dst, req); if (skb != NULL) { struct dccp_hdr *dh = dccp_hdr(skb); struct ipv6_txoptions *opt; dh->dccph_checksum = dccp_v6_csum_finish(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6.daddr = ireq->ir_v6_rmt_addr; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, np->tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); err = net_xmit_eval(err); } done: dst_release(dst); return err; } static void dccp_v6_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); kfree(inet_rsk(req)->ipv6_opt); kfree_skb(inet_rsk(req)->pktopts); } static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) { const struct ipv6hdr *rxip6h; struct sk_buff *skb; struct flowi6 fl6; struct net *net = dev_net(skb_dst(rxskb)->dev); struct dccp_v6_pernet *pn; struct sock *ctl_sk; struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; if (!ipv6_unicast_destination(rxskb)) return; pn = net_generic(net, dccp_v6_pernet_id); ctl_sk = pn->v6_ctl_sk; skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) return; rxip6h = ipv6_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr, &rxip6h->daddr); memset(&fl6, 0, sizeof(fl6)); fl6.daddr = rxip6h->saddr; fl6.saddr = rxip6h->daddr; fl6.flowi6_proto = IPPROTO_DCCP; fl6.flowi6_oif = inet6_iif(rxskb); fl6.fl6_dport = dccp_hdr(skb)->dccph_dport; fl6.fl6_sport = dccp_hdr(skb)->dccph_sport; security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; } kfree_skb(skb); } static struct request_sock_ops dccp6_request_sock_ops = { .family = AF_INET6, .obj_size = sizeof(struct dccp6_request_sock), .rtx_syn_ack = dccp_v6_send_response, .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v6_reqsk_destructor, .send_reset = dccp_v6_ctl_send_reset, .syn_ack_timeout = dccp_syn_ack_timeout, }; static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct request_sock *req; struct dccp_request_sock *dreq; struct inet_request_sock *ireq; struct ipv6_pinfo *np = inet6_sk(sk); const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) return 0; /* discard, don't send a reset here */ if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; } /* * There are no SYN attacks on IPv6, yet... */ dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; if (inet_csk_reqsk_queue_is_full(sk)) goto drop; if (sk_acceptq_is_full(sk)) goto drop; req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk, true); if (req == NULL) goto drop; if (dccp_reqsk_init(req, dccp_sk(sk), skb)) goto drop_and_free; dreq = dccp_rsk(req); if (dccp_parse_options(sk, dreq, skb)) goto drop_and_free; ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ireq_family = AF_INET6; ireq->ir_mark = inet_request_mark(sk, skb); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { refcount_inc(&skb->users); ireq->pktopts = skb; } ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if); /* So that link locals have meaning */ if (!ireq->ir_iif && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = inet6_iif(skb); /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v6_init_sequence(skb); dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; if (dccp_v6_send_response(sk, req)) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); reqsk_put(req); return 0; drop_and_free: reqsk_free(req); drop: __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); return -1; } static struct sock *dccp_v6_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 inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; if (skb->protocol == htons(ETH_P_IP)) { /* * v6 mapped */ newsk = dccp_v4_request_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (newsk == NULL) return NULL; newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->mcast_oif = inet_iif(skb); newnp->mcast_hops = ip_hdr(skb)->ttl; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count * here, dccp_create_openreq_child now does this for us, see the comment in * that function for the gory details. -acme */ /* It is tricky place. Until this moment IPv4 tcp worked with IPv6 icsk.icsk_af_ops. Sync it now. */ dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { struct flowi6 fl6; dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP); if (!dst) goto out; } newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, dccp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; /* * Clone native IPv6 options from listening socket (if any) * * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; dccp_sync_mss(newsk, dst_mtu(dst)); newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); dccp_done(newsk); goto out; } *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; } return newsk; out_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: dst_release(dst); out: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } /* The socket must have it's spinlock held when we get * here. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *opt_skb = NULL; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, dccp_rcv_established and rcv_established handle them correctly, but it is not case with dccp_v6_hnd_req and dccp_v6_ctl_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_do_rcv(sk, skb); if (sk_filter(sk, skb)) goto discard; /* * socket locking is here for SMP purposes as backlog rcv is currently * called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; } /* * Step 3: Process LISTEN state * If S.state == LISTEN, * If P.type == Request or P contains a valid Init Cookie option, * (* Must scan the packet's options to check for Init * Cookies. Only Init Cookies are processed here, * however; other options are processed in Step 8. This * scan need only be performed if the endpoint uses Init * Cookies *) * (* Generate a new socket and switch to that socket *) * Set S := new socket for this port pair * S.state = RESPOND * Choose S.ISS (initial seqno) or set from Init Cookies * Initialize S.GAR := S.ISS * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies * Continue with S.state == RESPOND * (* A Response packet will be generated in Step 11 *) * Otherwise, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return * * NOTE: the check for the packet types is done in * dccp_rcv_state_process */ if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len)) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: dccp_v6_ctl_send_reset(sk, skb); discard: if (opt_skb != NULL) __kfree_skb(opt_skb); kfree_skb(skb); return 0; /* Handling IPV6_PKTOPTIONS skb the similar * way it's done for net/ipv6/tcp_ipv6.c */ ipv6_pktoptions: if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) WRITE_ONCE(np->mcast_oif, inet6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (inet6_test_bit(REPFLOW, sk)) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } kfree_skb(opt_skb); return 0; } static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; bool refcounted; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; /* Step 1: If header checksum is incorrect, drop packet and return. */ if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; if (dccp_packet_without_ack(skb)) DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; else DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, inet6_iif(skb), 0, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; } /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (sk->sk_state == DCCP_TIME_WAIT) { dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n"); inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); struct sock *nsk; sk = req->rsk_listener; if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sock_hold(sk); refcounted = true; nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n", dh->dccph_cscov, min_cov); /* FIXME: send Data Dropped option (see also dccp_v4_rcv) */ goto discard_and_relse; } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; nf_reset_ct(skb); return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; dccp_v6_ctl_send_reset(sk, skb); } discard_it: kfree_skb(skb); return 0; discard_and_relse: if (refcounted) sock_put(sk); goto discard_it; } static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; dp->dccps_role = DCCP_ROLE_CLIENT; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl6, 0, sizeof(fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6.flowlabel); if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) usin->sin6_addr.s6_addr[15] = 1; addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != usin->sin6_scope_id) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* * DCCP over IPv4 */ if (addr_type == IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; net_dbg_ratelimited("connect: ipv4 mapped\n"); if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; icsk->icsk_af_ops = &dccp_ipv6_mapped; sk->sk_backlog_rcv = dccp_v4_do_rcv; err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; icsk->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_DCCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } if (saddr == NULL) { saddr = &fl6.saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; inet->inet_dport = usin->sin6_port; dccp_set_state(sk, DCCP_REQUESTING); err = inet6_hash_connect(&dccp_death_row, sk); if (err) goto late_failure; dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); err = dccp_connect(sk); if (err) goto late_failure; return 0; late_failure: dccp_set_state(sk, DCCP_CLOSED); inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .queue_xmit = inet6_csk_xmit, .send_check = dccp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .conn_request = dccp_v6_conn_request, .syn_recv_sock = dccp_v6_request_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), }; /* * DCCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .conn_request = dccp_v6_conn_request, .syn_recv_sock = dccp_v6_request_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), }; static void dccp_v6_sk_destruct(struct sock *sk) { dccp_destruct_common(sk); inet6_sock_destruct(sk); } /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int dccp_v6_init_sock(struct sock *sk) { static __u8 dccp_v6_ctl_sock_initialized; int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized); if (err == 0) { if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_destruct = dccp_v6_sk_destruct; } return err; } static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; static struct proto dccp_v6_prot = { .name = "DCCPv6", .owner = THIS_MODULE, .close = dccp_close, .connect = dccp_v6_connect, .disconnect = dccp_disconnect, .ioctl = dccp_ioctl, .init = dccp_v6_init_sock, .setsockopt = dccp_setsockopt, .getsockopt = dccp_getsockopt, .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, .hash = inet6_hash, .unhash = inet_unhash, .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), .ipv6_pinfo_offset = offsetof(struct dccp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, }; static const struct inet6_protocol dccp_v6_protocol = { .handler = dccp_v6_rcv, .err_handler = dccp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; static const struct proto_ops inet6_dccp_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet6_getname, .poll = dccp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = inet_dccp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw dccp_v6_protosw = { .type = SOCK_DCCP, .protocol = IPPROTO_DCCP, .prot = &dccp_v6_prot, .ops = &inet6_dccp_ops, .flags = INET_PROTOSW_ICSK, }; static int __net_init dccp_v6_init_net(struct net *net) { struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); if (dccp_hashinfo.bhash == NULL) return -ESOCKTNOSUPPORT; return inet_ctl_sock_create(&pn->v6_ctl_sk, PF_INET6, SOCK_DCCP, IPPROTO_DCCP, net); } static void __net_exit dccp_v6_exit_net(struct net *net) { struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); inet_ctl_sock_destroy(pn->v6_ctl_sk); } static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) { inet_twsk_purge(&dccp_hashinfo, AF_INET6); } static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; static int __init dccp_v6_init(void) { int err = proto_register(&dccp_v6_prot, 1); if (err) goto out; inet6_register_protosw(&dccp_v6_protosw); err = register_pernet_subsys(&dccp_v6_ops); if (err) goto out_destroy_ctl_sock; err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP); if (err) goto out_unregister_proto; out: return err; out_unregister_proto: unregister_pernet_subsys(&dccp_v6_ops); out_destroy_ctl_sock: inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); goto out; } static void __exit dccp_v6_exit(void) { inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); unregister_pernet_subsys(&dccp_v6_ops); inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); } module_init(dccp_v6_init); module_exit(dccp_v6_exit); /* * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) * values directly, Also cover the case where the protocol is not specified, * i.e. net-pf-PF_INET6-proto-0-type-SOCK_DCCP */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol"); |
| 97 32 30 13 25 25 25 25 2 61 11 6 4 9 9 9 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #ifndef _LINUX_SKMSG_H #define _LINUX_SKMSG_H #include <linux/bpf.h> #include <linux/filter.h> #include <linux/scatterlist.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/tcp.h> #include <net/strparser.h> #define MAX_MSG_FRAGS MAX_SKB_FRAGS #define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1) enum __sk_action { __SK_DROP = 0, __SK_PASS, __SK_REDIRECT, __SK_NONE, }; struct sk_msg_sg { u32 start; u32 curr; u32 end; u32 size; u32 copybreak; DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the * chaining; * 2) to chain tailer SG entries after the message. */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { struct sk_msg_sg sg; void *data; void *data_end; u32 apply_bytes; u32 cork_bytes; u32 flags; struct sk_buff *skb; struct sock *sk_redir; struct sock *sk; struct list_head list; }; struct sk_psock_progs { struct bpf_prog *msg_parser; struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; }; enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { struct list_head list; struct bpf_map *map; void *link_raw; }; struct sk_psock_work_state { u32 len; u32 off; }; struct sk_psock { struct sock *sk; struct sock *sk_redir; u32 apply_bytes; u32 cork_bytes; u32 eval; bool redir_ingress; /* undefined if sk_redir is null */ struct sk_msg *cork; struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; #endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; spinlock_t ingress_lock; unsigned long state; struct list_head link; spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); /* psock_update_sk_prot may be called with restore=false many times * so the handler must be safe for this case. It will be called * exactly once with restore=true when the psock is being destroyed * and psock refcnt is zero, but before an RCU grace period. */ int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; struct sock *sk_pair; struct rcu_work rwork; }; int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { WARN_ON(i == msg->sg.end && bytes); } static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) { if (psock->apply_bytes) { if (psock->apply_bytes < bytes) psock->apply_bytes = 0; else psock->apply_bytes -= bytes; } } static inline u32 sk_msg_iter_dist(u32 start, u32 end) { return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start); } #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ var = NR_MSG_FRAG_IDS - 1; \ else \ var--; \ } while (0) #define sk_msg_iter_var_next(var) \ do { \ var++; \ if (var == NR_MSG_FRAG_IDS) \ var = 0; \ } while (0) #define sk_msg_iter_prev(msg, which) \ sk_msg_iter_var_prev(msg->sg.which) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); memset(msg, 0, sizeof(*msg)); sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, int which, u32 size) { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) { memcpy(dst, src, sizeof(*src)); sk_msg_init(src); } static inline bool sk_msg_full(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS; } static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; } static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) { return msg->sg.data[which]; } static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); } static inline bool sk_msg_to_ingress(const struct sk_msg *msg) { return msg->flags & BPF_F_INGRESS; } static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { msg->data = sg_virt(sge); msg->data_end = msg->data + sge->length; } } static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, u32 len, u32 offset) { struct scatterlist *sge; get_page(page); sge = sk_msg_elem(msg, msg->sg.end); sg_set_page(sge, page, len, offset); sg_unmark_end(sge); __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) __set_bit(i, msg->sg.copy); else __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; } while (1); } static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, true); } static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, false); } static inline struct sk_psock *sk_psock(const struct sock *sk) { return __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_PSOCK); } static inline void sk_psock_set_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { set_bit(bit, &psock->state); } static inline void sk_psock_clear_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { clear_bit(bit, &psock->state); } static inline bool sk_psock_test_state(const struct sk_psock *psock, enum sk_psock_state_bits bit) { return test_bit(bit, &psock->state); } static inline void sock_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); kfree_skb(skb); } static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); else { sk_msg_free(psock->sk, msg); kfree(msg); } spin_unlock_bh(&psock->ingress_lock); } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); if (msg) list_del(&msg->list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock, struct sk_msg *msg) { struct sk_msg *ret; spin_lock_bh(&psock->ingress_lock); if (list_is_last(&msg->list, &psock->ingress_msg)) ret = NULL; else ret = list_next_entry(msg, list); spin_unlock_bh(&psock->ingress_lock); return ret; } static inline bool sk_psock_queue_empty(const struct sk_psock *psock) { return psock ? list_empty(&psock->ingress_msg) : true; } static inline void kfree_sk_msg(struct sk_msg *msg) { if (msg->skb) consume_skb(msg->skb); kfree(msg); } static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; sk->sk_err = err; sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); #else static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { return -EOPNOTSUPP; } static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { } static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { } #endif void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); static inline struct sk_psock_link *sk_psock_init_link(void) { return kzalloc(sizeof(struct sk_psock_link), GFP_ATOMIC | __GFP_NOWARN); } static inline void sk_psock_free_link(struct sk_psock_link *link) { kfree(link); } struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); static inline void sk_psock_cork_free(struct sk_psock *psock) { if (psock->cork) { sk_msg_free(psock->sk, psock->cork); kfree(psock->cork); psock->cork = NULL; } } static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, true); } static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock && !refcount_inc_not_zero(&psock->refcnt)) psock = NULL; rcu_read_unlock(); return psock; } void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) { if (refcount_dec_and_test(&psock->refcnt)) sk_psock_drop(sk, psock); } static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); } static inline void psock_set_prog(struct bpf_prog **pprog, struct bpf_prog *prog) { prog = xchg(pprog, prog); if (prog) bpf_prog_put(prog); } static inline int psock_replace_prog(struct bpf_prog **pprog, struct bpf_prog *prog, struct bpf_prog *old) { if (cmpxchg(pprog, old, prog) != old) return -ENOENT; if (old) bpf_prog_put(old); return 0; } static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); psock_set_prog(&progs->stream_parser, NULL); psock_set_prog(&progs->stream_verdict, NULL); psock_set_prog(&progs->skb_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); static inline bool sk_psock_strp_enabled(struct sk_psock *psock) { if (!psock) return false; return !!psock->saved_data_ready; } #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) /* We only have two bits so far. */ #define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) static inline bool skb_bpf_strparser(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_STRPARSER; } static inline void skb_bpf_set_strparser(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_STRPARSER; } static inline bool skb_bpf_ingress(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_INGRESS; } static inline void skb_bpf_set_ingress(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_INGRESS; } static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir, bool ingress) { skb->_sk_redir = (unsigned long)sk_redir; if (ingress) skb->_sk_redir |= BPF_F_INGRESS; } static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return (struct sock *)(sk_redir & BPF_F_PTR_MASK); } static inline void skb_bpf_redirect_clear(struct sk_buff *skb) { skb->_sk_redir = 0; } #endif /* CONFIG_NET_SOCK_MSG */ #endif /* _LINUX_SKMSG_H */ |
| 2336 2336 2336 4 4 21 21 21 2336 2336 2336 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Block rq-qos policy for assigning an I/O priority class to requests. * * Using an rq-qos policy for assigning I/O priority class has two advantages * over using the ioprio_set() system call: * * - This policy is cgroup based so it has all the advantages of cgroups. * - While ioprio_set() does not affect page cache writeback I/O, this rq-qos * controller affects page cache writeback I/O for filesystems that support * assiociating a cgroup with writeback I/O. See also * Documentation/admin-guide/cgroup-v2.rst. */ #include <linux/blk-mq.h> #include <linux/blk_types.h> #include <linux/kernel.h> #include <linux/module.h> #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-rq-qos.h" /** * enum prio_policy - I/O priority class policy. * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. * @POLICY_PROMOTE_TO_RT: modify no-IOPRIO_CLASS_RT to IOPRIO_CLASS_RT. * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into * IOPRIO_CLASS_BE. * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. * @POLICY_NONE_TO_RT: an alias for POLICY_PROMOTE_TO_RT. * * See also <linux/ioprio.h>. */ enum prio_policy { POLICY_NO_CHANGE = 0, POLICY_PROMOTE_TO_RT = 1, POLICY_RESTRICT_TO_BE = 2, POLICY_ALL_TO_IDLE = 3, POLICY_NONE_TO_RT = 4, }; static const char *policy_name[] = { [POLICY_NO_CHANGE] = "no-change", [POLICY_PROMOTE_TO_RT] = "promote-to-rt", [POLICY_RESTRICT_TO_BE] = "restrict-to-be", [POLICY_ALL_TO_IDLE] = "idle", [POLICY_NONE_TO_RT] = "none-to-rt", }; static struct blkcg_policy ioprio_policy; /** * struct ioprio_blkg - Per (cgroup, request queue) data. * @pd: blkg_policy_data structure. */ struct ioprio_blkg { struct blkg_policy_data pd; }; /** * struct ioprio_blkcg - Per cgroup data. * @cpd: blkcg_policy_data structure. * @prio_policy: One of the IOPRIO_CLASS_* values. See also <linux/ioprio.h>. */ struct ioprio_blkcg { struct blkcg_policy_data cpd; enum prio_policy prio_policy; }; static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct ioprio_blkg, pd) : NULL; } static struct ioprio_blkcg *blkcg_to_ioprio_blkcg(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &ioprio_policy), struct ioprio_blkcg, cpd); } static struct ioprio_blkcg * ioprio_blkcg_from_css(struct cgroup_subsys_state *css) { return blkcg_to_ioprio_blkcg(css_to_blkcg(css)); } static struct ioprio_blkcg *ioprio_blkcg_from_bio(struct bio *bio) { struct blkg_policy_data *pd = blkg_to_pd(bio->bi_blkg, &ioprio_policy); if (!pd) return NULL; return blkcg_to_ioprio_blkcg(pd->blkg->blkcg); } static int ioprio_show_prio_policy(struct seq_file *sf, void *v) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(seq_css(sf)); seq_printf(sf, "%s\n", policy_name[blkcg->prio_policy]); return 0; } static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(of_css(of)); int ret; if (off != 0) return -EIO; /* kernfs_fop_write_iter() terminates 'buf' with '\0'. */ ret = sysfs_match_string(policy_name, buf); if (ret < 0) return ret; blkcg->prio_policy = ret; return nbytes; } static struct blkg_policy_data * ioprio_alloc_pd(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { struct ioprio_blkg *ioprio_blkg; ioprio_blkg = kzalloc(sizeof(*ioprio_blkg), gfp); if (!ioprio_blkg) return NULL; return &ioprio_blkg->pd; } static void ioprio_free_pd(struct blkg_policy_data *pd) { struct ioprio_blkg *ioprio_blkg = pd_to_ioprio(pd); kfree(ioprio_blkg); } static struct blkcg_policy_data *ioprio_alloc_cpd(gfp_t gfp) { struct ioprio_blkcg *blkcg; blkcg = kzalloc(sizeof(*blkcg), gfp); if (!blkcg) return NULL; blkcg->prio_policy = POLICY_NO_CHANGE; return &blkcg->cpd; } static void ioprio_free_cpd(struct blkcg_policy_data *cpd) { struct ioprio_blkcg *blkcg = container_of(cpd, typeof(*blkcg), cpd); kfree(blkcg); } #define IOPRIO_ATTRS \ { \ .name = "prio.class", \ .seq_show = ioprio_show_prio_policy, \ .write = ioprio_set_prio_policy, \ }, \ { } /* sentinel */ /* cgroup v2 attributes */ static struct cftype ioprio_files[] = { IOPRIO_ATTRS }; /* cgroup v1 attributes */ static struct cftype ioprio_legacy_files[] = { IOPRIO_ATTRS }; static struct blkcg_policy ioprio_policy = { .dfl_cftypes = ioprio_files, .legacy_cftypes = ioprio_legacy_files, .cpd_alloc_fn = ioprio_alloc_cpd, .cpd_free_fn = ioprio_free_cpd, .pd_alloc_fn = ioprio_alloc_pd, .pd_free_fn = ioprio_free_pd, }; void blkcg_set_ioprio(struct bio *bio) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio); u16 prio; if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE) return; if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT || blkcg->prio_policy == POLICY_NONE_TO_RT) { /* * For RT threads, the default priority level is 4 because * task_nice is 0. By promoting non-RT io-priority to RT-class * and default level 4, those requests that are already * RT-class but need a higher io-priority can use ioprio_set() * to achieve this. */ if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) != IOPRIO_CLASS_RT) bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 4); return; } /* * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers * correspond to a lower priority. Hence, the max_t() below selects * the lower priority of bi_ioprio and the cgroup I/O priority class. * If the bio I/O priority equals IOPRIO_CLASS_NONE, the cgroup I/O * priority is assigned to the bio. */ prio = max_t(u16, bio->bi_ioprio, IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0)); if (prio > bio->bi_ioprio) bio->bi_ioprio = prio; } void blk_ioprio_exit(struct gendisk *disk) { blkcg_deactivate_policy(disk, &ioprio_policy); } int blk_ioprio_init(struct gendisk *disk) { return blkcg_activate_policy(disk, &ioprio_policy); } static int __init ioprio_init(void) { return blkcg_policy_register(&ioprio_policy); } static void __exit ioprio_exit(void) { blkcg_policy_unregister(&ioprio_policy); } module_init(ioprio_init); module_exit(ioprio_exit); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * file.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * * debugfs is for people to use instead of /proc or /sys. * See Documentation/filesystems/ for more details. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> #include <linux/pm_runtime.h> #include <linux/poll.h> #include <linux/security.h> #include "internal.h" struct poll_table_struct; static ssize_t default_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return 0; } static ssize_t default_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return count; } const struct file_operations debugfs_noop_file_operations = { .read = default_read_file, .write = default_write_file, .open = simple_open, .llseek = noop_llseek, }; #define F_DENTRY(filp) ((filp)->f_path.dentry) const struct file_operations *debugfs_real_fops(const struct file *filp) { struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata; if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) { /* * Urgh, we've been called w/o a protecting * debugfs_file_get(). */ WARN_ON(1); return NULL; } return fsd->real_fops; } EXPORT_SYMBOL_GPL(debugfs_real_fops); /** * debugfs_file_get - mark the beginning of file data access * @dentry: the dentry object whose data is being accessed. * * Up to a matching call to debugfs_file_put(), any successive call * into the file removing functions debugfs_remove() and * debugfs_remove_recursive() will block. Since associated private * file data may only get freed after a successful return of any of * the removal functions, you may safely access it after a successful * call to debugfs_file_get() without worrying about lifetime issues. * * If -%EIO is returned, the file has already been removed and thus, * it is not safe to access any of its data. If, on the other hand, * it is allowed to access the file data, zero is returned. */ int debugfs_file_get(struct dentry *dentry) { struct debugfs_fsdata *fsd; void *d_fsd; /* * This could only happen if some debugfs user erroneously calls * debugfs_file_get() on a dentry that isn't even a file, let * them know about it. */ if (WARN_ON(!d_is_reg(dentry))) return -EINVAL; d_fsd = READ_ONCE(dentry->d_fsdata); if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); mutex_init(&fsd->cancellations_mtx); if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); fsd = READ_ONCE(dentry->d_fsdata); } } /* * In case of a successful cmpxchg() above, this check is * strictly necessary and must follow it, see the comment in * __debugfs_remove_file(). * OTOH, if the cmpxchg() hasn't been executed or wasn't * successful, this serves the purpose of not starving * removers. */ if (d_unlinked(dentry)) return -EIO; if (!refcount_inc_not_zero(&fsd->active_users)) return -EIO; return 0; } EXPORT_SYMBOL_GPL(debugfs_file_get); /** * debugfs_file_put - mark the end of file data access * @dentry: the dentry object formerly passed to * debugfs_file_get(). * * Allow any ongoing concurrent call into debugfs_remove() or * debugfs_remove_recursive() blocked by a former call to * debugfs_file_get() to proceed and return to its caller. */ void debugfs_file_put(struct dentry *dentry) { struct debugfs_fsdata *fsd = READ_ONCE(dentry->d_fsdata); if (refcount_dec_and_test(&fsd->active_users)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_file_put); /** * debugfs_enter_cancellation - enter a debugfs cancellation * @file: the file being accessed * @cancellation: the cancellation object, the cancel callback * inside of it must be initialized * * When a debugfs file is removed it needs to wait for all active * operations to complete. However, the operation itself may need * to wait for hardware or completion of some asynchronous process * or similar. As such, it may need to be cancelled to avoid long * waits or even deadlocks. * * This function can be used inside a debugfs handler that may * need to be cancelled. As soon as this function is called, the * cancellation's 'cancel' callback may be called, at which point * the caller should proceed to call debugfs_leave_cancellation() * and leave the debugfs handler function as soon as possible. * Note that the 'cancel' callback is only ever called in the * context of some kind of debugfs_remove(). * * This function must be paired with debugfs_leave_cancellation(). */ void debugfs_enter_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); INIT_LIST_HEAD(&cancellation->list); if (WARN_ON(!d_is_reg(dentry))) return; if (WARN_ON(!cancellation->cancel)) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); list_add(&cancellation->list, &fsd->cancellations); mutex_unlock(&fsd->cancellations_mtx); /* if we're already removing wake it up to cancel */ if (d_unlinked(dentry)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_enter_cancellation); /** * debugfs_leave_cancellation - leave cancellation section * @file: the file being accessed * @cancellation: the cancellation previously registered with * debugfs_enter_cancellation() * * See the documentation of debugfs_enter_cancellation(). */ void debugfs_leave_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); if (WARN_ON(!d_is_reg(dentry))) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); if (!list_empty(&cancellation->list)) list_del(&cancellation->list); mutex_unlock(&fsd->cancellations_mtx); } EXPORT_SYMBOL_GPL(debugfs_leave_cancellation); /* * Only permit access to world-readable files when the kernel is locked down. * We also need to exclude any file that has ways to write or alter it as root * can bypass the permissions check. */ static int debugfs_locked_down(struct inode *inode, struct file *filp, const struct file_operations *real_fops) { if ((inode->i_mode & 07777 & ~0444) == 0 && !(filp->f_mode & FMODE_WRITE) && !real_fops->unlocked_ioctl && !real_fops->compat_ioctl && !real_fops->mmap) return 0; if (security_locked_down(LOCKDOWN_DEBUGFS)) return -EPERM; return 0; } static int open_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not clean up after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } replace_fops(filp, real_fops); if (real_fops->open) r = real_fops->open(inode, filp); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_open_proxy_file_operations = { .open = open_proxy_open, }; #define PROTO(args...) args #define ARGS(args...) args #define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \ static ret_type full_proxy_ ## name(proto) \ { \ struct dentry *dentry = F_DENTRY(filp); \ const struct file_operations *real_fops; \ ret_type r; \ \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ real_fops = debugfs_real_fops(filp); \ r = real_fops->name(args); \ debugfs_file_put(dentry); \ return r; \ } FULL_PROXY_FUNC(llseek, loff_t, filp, PROTO(struct file *filp, loff_t offset, int whence), ARGS(filp, offset, whence)); FULL_PROXY_FUNC(read, ssize_t, filp, PROTO(struct file *filp, char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(write, ssize_t, filp, PROTO(struct file *filp, const char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(unlocked_ioctl, long, filp, PROTO(struct file *filp, unsigned int cmd, unsigned long arg), ARGS(filp, cmd, arg)); static __poll_t full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { struct dentry *dentry = F_DENTRY(filp); __poll_t r = 0; const struct file_operations *real_fops; if (debugfs_file_get(dentry)) return EPOLLHUP; real_fops = debugfs_real_fops(filp); r = real_fops->poll(filp, wait); debugfs_file_put(dentry); return r; } static int full_proxy_release(struct inode *inode, struct file *filp) { const struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = debugfs_real_fops(filp); const struct file_operations *proxy_fops = filp->f_op; int r = 0; /* * We must not protect this against removal races here: the * original releaser should be called unconditionally in order * not to leak any resources. Releasers must not assume that * ->i_private is still being meaningful here. */ if (real_fops->release) r = real_fops->release(inode, filp); replace_fops(filp, d_inode(dentry)->i_fop); kfree(proxy_fops); fops_put(real_fops); return r; } static void __full_proxy_fops_init(struct file_operations *proxy_fops, const struct file_operations *real_fops) { proxy_fops->release = full_proxy_release; if (real_fops->llseek) proxy_fops->llseek = full_proxy_llseek; if (real_fops->read) proxy_fops->read = full_proxy_read; if (real_fops->write) proxy_fops->write = full_proxy_write; if (real_fops->poll) proxy_fops->poll = full_proxy_poll; if (real_fops->unlocked_ioctl) proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } static int full_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; struct file_operations *proxy_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not cleanup after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL); if (!proxy_fops) { r = -ENOMEM; goto free_proxy; } __full_proxy_fops_init(proxy_fops, real_fops); replace_fops(filp, proxy_fops); if (real_fops->open) { r = real_fops->open(inode, filp); if (r) { replace_fops(filp, d_inode(dentry)->i_fop); goto free_proxy; } else if (filp->f_op != proxy_fops) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); goto free_proxy; } } goto out; free_proxy: kfree(proxy_fops); fops_put(real_fops); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_full_proxy_file_operations = { .open = full_proxy_open, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; ret = simple_attr_read(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } EXPORT_SYMBOL_GPL(debugfs_attr_read); static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; if (is_signed) ret = simple_attr_write_signed(file, buf, len, ppos); else ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } ssize_t debugfs_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(debugfs_attr_write); ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, const struct file_operations *fops_ro, const struct file_operations *fops_wo) { /* if there are no write bits set, make read only */ if (!(mode & S_IWUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_ro); /* if there are no read bits set, make write only */ if (!(mode & S_IRUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_wo); return debugfs_create_file_unsafe(name, mode, parent, value, fops); } static int debugfs_u8_set(void *data, u64 val) { *(u8 *)data = val; return 0; } static int debugfs_u8_get(void *data, u64 *val) { *val = *(u8 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_ro, debugfs_u8_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); /** * debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8, &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); static int debugfs_u16_set(void *data, u64 val) { *(u16 *)data = val; return 0; } static int debugfs_u16_get(void *data, u64 *val) { *val = *(u16 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_ro, debugfs_u16_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); /** * debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16, &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); static int debugfs_u32_set(void *data, u64 val) { *(u32 *)data = val; return 0; } static int debugfs_u32_get(void *data, u64 *val) { *val = *(u32 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_ro, debugfs_u32_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); /** * debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32, &fops_u32_ro, &fops_u32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u32); static int debugfs_u64_set(void *data, u64 val) { *(u64 *)data = val; return 0; } static int debugfs_u64_get(void *data, u64 *val) { *val = *(u64 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u64, debugfs_u64_get, debugfs_u64_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_ro, debugfs_u64_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); /** * debugfs_create_u64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64, &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); static int debugfs_ulong_set(void *data, u64 val) { *(unsigned long *)data = val; return 0; } static int debugfs_ulong_get(void *data, u64 *val) { *val = *(unsigned long *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); /** * debugfs_create_ulong - create a debugfs file that is used to read and write * an unsigned long value. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_ulong, &fops_ulong_ro, &fops_ulong_wo); } EXPORT_SYMBOL_GPL(debugfs_create_ulong); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_ro, debugfs_u16_get, NULL, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_wo, NULL, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); /* * debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value * * These functions are exactly the same as the above functions (but use a hex * output for the decimal challenged). For details look at the above unsigned * decimal functions. */ /** * debugfs_create_x8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8, &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); /** * debugfs_create_x16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16, &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); /** * debugfs_create_x32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32, &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); /** * debugfs_create_x64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64, &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); static int debugfs_size_t_set(void *data, u64 val) { *(size_t *)data = val; return 0; } static int debugfs_size_t_get(void *data, u64 *val) { *val = *(size_t *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, "%llu\n"); /* %llu and %zu are more or less the same */ DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); /** * debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_size_t, &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); static int debugfs_atomic_t_set(void *data, u64 val) { atomic_set((atomic_t *)data, val); return 0; } static int debugfs_atomic_t_get(void *data, u64 *val) { *val = atomic_read((atomic_t *)data); return 0; } DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** * debugfs_create_atomic_t - create a debugfs file that is used to read and * write an atomic_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_atomic_t, &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[2]; bool val; int r; struct dentry *dentry = F_DENTRY(file); r = debugfs_file_get(dentry); if (unlikely(r)) return r; val = *(bool *)file->private_data; debugfs_file_put(dentry); if (val) buf[0] = 'Y'; else buf[0] = 'N'; buf[1] = '\n'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } EXPORT_SYMBOL_GPL(debugfs_read_file_bool); ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { bool bv; int r; bool *val = file->private_data; struct dentry *dentry = F_DENTRY(file); r = kstrtobool_from_user(user_buf, count, &bv); if (!r) { r = debugfs_file_get(dentry); if (unlikely(r)) return r; *val = bv; debugfs_file_put(dentry); } return count; } EXPORT_SYMBOL_GPL(debugfs_write_file_bool); static const struct file_operations fops_bool = { .read = debugfs_read_file_bool, .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_ro = { .read = debugfs_read_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_wo = { .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_bool, &fops_bool_ro, &fops_bool_wo); } EXPORT_SYMBOL_GPL(debugfs_create_bool); ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *str, *copy = NULL; int copy_len, len; ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; str = *(char **)file->private_data; len = strlen(str) + 1; copy = kmalloc(len, GFP_KERNEL); if (!copy) { debugfs_file_put(dentry); return -ENOMEM; } copy_len = strscpy(copy, str, len); debugfs_file_put(dentry); if (copy_len < 0) { kfree(copy); return copy_len; } copy[copy_len] = '\n'; ret = simple_read_from_buffer(user_buf, count, ppos, copy, len); kfree(copy); return ret; } EXPORT_SYMBOL_GPL(debugfs_create_str); static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *old, *new = NULL; int pos = *ppos; int r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; old = *(char **)file->private_data; /* only allow strict concatenation */ r = -EINVAL; if (pos && pos != strlen(old)) goto error; r = -E2BIG; if (pos + count + 1 > PAGE_SIZE) goto error; r = -ENOMEM; new = kmalloc(pos + count + 1, GFP_KERNEL); if (!new) goto error; if (pos) memcpy(new, old, pos); r = -EFAULT; if (copy_from_user(new + pos, user_buf, count)) goto error; new[pos + count] = '\0'; strim(new); rcu_assign_pointer(*(char __rcu **)file->private_data, new); synchronize_rcu(); kfree(old); debugfs_file_put(dentry); return count; error: kfree(new); debugfs_file_put(dentry); return r; } static const struct file_operations fops_str = { .read = debugfs_read_file_str, .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_ro = { .read = debugfs_read_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_wo = { .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_str - create a debugfs file that is used to read and write a string value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str, &fops_str_ro, &fops_str_wo); } static ssize_t read_file_blob(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_read_from_buffer(user_buf, count, ppos, blob->data, blob->size); debugfs_file_put(dentry); return r; } static ssize_t write_file_blob(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_write_to_buffer(blob->data, blob->size, ppos, user_buf, count); debugfs_file_put(dentry); return r; } static const struct file_operations fops_blob = { .read = read_file_blob, .write = write_file_blob, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_blob - create a debugfs file that is used to read and write * a binary blob * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @blob: a pointer to a struct debugfs_blob_wrapper which contains a pointer * to the blob data and the size of the data. * * This function creates a file in debugfs with the given name that exports * @blob->data as a binary blob. If the @mode variable is so set it can be * read from and written to. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will * be returned. */ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob) { return debugfs_create_file_unsafe(name, mode & 0644, parent, blob, &fops_blob); } EXPORT_SYMBOL_GPL(debugfs_create_blob); static size_t u32_format_array(char *buf, size_t bufsize, u32 *array, int array_size) { size_t ret = 0; while (--array_size >= 0) { size_t len; char term = array_size ? ' ' : '\n'; len = snprintf(buf, bufsize, "%u%c", *array++, term); ret += len; buf += len; bufsize -= len; } return ret; } static int u32_array_open(struct inode *inode, struct file *file) { struct debugfs_u32_array *data = inode->i_private; int size, elements = data->n_elements; char *buf; /* * Max size: * - 10 digits + ' '/'\n' = 11 bytes per number * - terminating NUL character */ size = elements*11; buf = kmalloc(size+1, GFP_KERNEL); if (!buf) return -ENOMEM; buf[size] = 0; file->private_data = buf; u32_format_array(buf, size, data->array, data->n_elements); return nonseekable_open(inode, file); } static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { size_t size = strlen(file->private_data); return simple_read_from_buffer(buf, len, ppos, file->private_data, size); } static int u32_array_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release = u32_array_release, .read = u32_array_read, .llseek = no_llseek, }; /** * debugfs_create_u32_array - create a debugfs file that is used to read u32 * array. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @array: wrapper struct containing data pointer and size of the array. * * This function creates a file in debugfs with the given name that exports * @array as data. If the @mode variable is so set it can be read from. * Writing is not supported. Seek within the file is also not supported. * Once array is created its size can not be changed. */ void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, struct debugfs_u32_array *array) { debugfs_create_file_unsafe(name, mode, parent, array, &u32_array_fops); } EXPORT_SYMBOL_GPL(debugfs_create_u32_array); #ifdef CONFIG_HAS_IOMEM /* * The regset32 stuff is used to print 32-bit registers using the * seq_file utilities. We offer printing a register set in an already-opened * sequential file or create a debugfs file that only prints a regset32. */ /** * debugfs_print_regs32 - use seq_print to describe a set of registers * @s: the seq_file structure being used to generate output * @regs: an array if struct debugfs_reg32 structures * @nregs: the length of the above array * @base: the base address to be used in reading the registers * @prefix: a string to be prefixed to every output line * * This function outputs a text block describing the current values of * some 32-bit hardware registers. It is meant to be used within debugfs * files based on seq_file that need to show registers, intermixed with other * information. The prefix argument may be used to specify a leading string, * because some peripherals have several blocks of identical registers, * for example configuration of dma channels */ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix) { int i; for (i = 0; i < nregs; i++, regs++) { if (prefix) seq_printf(s, "%s", prefix); seq_printf(s, "%s = 0x%08x\n", regs->name, readl(base + regs->offset)); if (seq_has_overflowed(s)) break; } } EXPORT_SYMBOL_GPL(debugfs_print_regs32); static int debugfs_regset32_show(struct seq_file *s, void *data) { struct debugfs_regset32 *regset = s->private; if (regset->dev) pm_runtime_get_sync(regset->dev); debugfs_print_regs32(s, regset->regs, regset->nregs, regset->base, ""); if (regset->dev) pm_runtime_put(regset->dev); return 0; } DEFINE_SHOW_ATTRIBUTE(debugfs_regset32); /** * debugfs_create_regset32 - create a debugfs file that returns register values * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @regset: a pointer to a struct debugfs_regset32, which contains a pointer * to an array of register definitions, the array size and the base * address where the register bank is to be found. * * This function creates a file in debugfs with the given name that reports * the names and values of a set of 32-bit registers. If the @mode variable * is so set it can be read from. Writing is not supported. */ void debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, struct debugfs_regset32 *regset) { debugfs_create_file(name, mode, parent, regset, &debugfs_regset32_fops); } EXPORT_SYMBOL_GPL(debugfs_create_regset32); #endif /* CONFIG_HAS_IOMEM */ struct debugfs_devm_entry { int (*read)(struct seq_file *seq, void *data); struct device *dev; }; static int debugfs_devm_entry_open(struct inode *inode, struct file *f) { struct debugfs_devm_entry *entry = inode->i_private; return single_open(f, entry->read, entry->dev); } static const struct file_operations debugfs_devm_entry_ops = { .owner = THIS_MODULE, .open = debugfs_devm_entry_open, .release = single_release, .read = seq_read, .llseek = seq_lseek }; /** * debugfs_create_devm_seqfile - create a debugfs file that is bound to device. * * @dev: device related to this debugfs file. * @name: name of the debugfs file. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @read_fn: function pointer called to print the seq_file content. */ void debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, int (*read_fn)(struct seq_file *s, void *data)) { struct debugfs_devm_entry *entry; if (IS_ERR(parent)) return; entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL); if (!entry) return; entry->read = read_fn; entry->dev = dev; debugfs_create_file(name, S_IRUGO, parent, entry, &debugfs_devm_entry_ops); } EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile); |
| 137 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This file provides /sys/class/ieee80211/<wiphy name>/ * and some default attributes. * * Copyright 2005-2006 Jiri Benc <jbenc@suse.cz> * Copyright 2006 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2020-2021, 2023 Intel Corporation */ #include <linux/device.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <net/cfg80211.h> #include "sysfs.h" #include "core.h" #include "rdev-ops.h" static inline struct cfg80211_registered_device *dev_to_rdev( struct device *dev) { return container_of(dev, struct cfg80211_registered_device, wiphy.dev); } #define SHOW_FMT(name, fmt, member) \ static ssize_t name ## _show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sprintf(buf, fmt "\n", dev_to_rdev(dev)->member); \ } \ static DEVICE_ATTR_RO(name) SHOW_FMT(index, "%d", wiphy_idx); SHOW_FMT(macaddress, "%pM", wiphy.perm_addr); SHOW_FMT(address_mask, "%pM", wiphy.addr_mask); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wiphy *wiphy = &dev_to_rdev(dev)->wiphy; return sprintf(buf, "%s\n", wiphy_name(wiphy)); } static DEVICE_ATTR_RO(name); static ssize_t addresses_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wiphy *wiphy = &dev_to_rdev(dev)->wiphy; char *start = buf; int i; if (!wiphy->addresses) return sprintf(buf, "%pM\n", wiphy->perm_addr); for (i = 0; i < wiphy->n_addresses; i++) buf += sprintf(buf, "%pM\n", wiphy->addresses[i].addr); return buf - start; } static DEVICE_ATTR_RO(addresses); static struct attribute *ieee80211_attrs[] = { &dev_attr_index.attr, &dev_attr_macaddress.attr, &dev_attr_address_mask.attr, &dev_attr_addresses.attr, &dev_attr_name.attr, NULL, }; ATTRIBUTE_GROUPS(ieee80211); static void wiphy_dev_release(struct device *dev) { struct cfg80211_registered_device *rdev = dev_to_rdev(dev); cfg80211_dev_free(rdev); } #ifdef CONFIG_PM_SLEEP static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_leave(rdev, wdev); } static int wiphy_suspend(struct device *dev) { struct cfg80211_registered_device *rdev = dev_to_rdev(dev); int ret = 0; rdev->suspend_at = ktime_get_boottime_seconds(); rtnl_lock(); wiphy_lock(&rdev->wiphy); if (rdev->wiphy.registered) { if (!rdev->wiphy.wowlan_config) { cfg80211_leave_all(rdev); cfg80211_process_rdev_events(rdev); } cfg80211_process_wiphy_works(rdev, NULL); if (rdev->ops->suspend) ret = rdev_suspend(rdev, rdev->wiphy.wowlan_config); if (ret == 1) { /* Driver refuse to configure wowlan */ cfg80211_leave_all(rdev); cfg80211_process_rdev_events(rdev); cfg80211_process_wiphy_works(rdev, NULL); ret = rdev_suspend(rdev, NULL); } if (ret == 0) rdev->suspended = true; } wiphy_unlock(&rdev->wiphy); rtnl_unlock(); return ret; } static int wiphy_resume(struct device *dev) { struct cfg80211_registered_device *rdev = dev_to_rdev(dev); int ret = 0; /* Age scan results with time spent in suspend */ cfg80211_bss_age(rdev, ktime_get_boottime_seconds() - rdev->suspend_at); rtnl_lock(); wiphy_lock(&rdev->wiphy); if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); rdev->suspended = false; schedule_work(&rdev->wiphy_work); wiphy_unlock(&rdev->wiphy); if (ret) cfg80211_shutdown_all_interfaces(&rdev->wiphy); rtnl_unlock(); return ret; } static SIMPLE_DEV_PM_OPS(wiphy_pm_ops, wiphy_suspend, wiphy_resume); #define WIPHY_PM_OPS (&wiphy_pm_ops) #else #define WIPHY_PM_OPS NULL #endif static const void *wiphy_namespace(const struct device *d) { struct wiphy *wiphy = container_of(d, struct wiphy, dev); return wiphy_net(wiphy); } struct class ieee80211_class = { .name = "ieee80211", .dev_release = wiphy_dev_release, .dev_groups = ieee80211_groups, .pm = WIPHY_PM_OPS, .ns_type = &net_ns_type_operations, .namespace = wiphy_namespace, }; int wiphy_sysfs_init(void) { return class_register(&ieee80211_class); } void wiphy_sysfs_exit(void) { class_unregister(&ieee80211_class); } |
| 23 23 39 39 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * IEEE 802.11 defines * * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen * <jkmaline@cc.hut.fi> * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright (c) 2005, Devicescape Software, Inc. * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH * Copyright (c) 2018 - 2023 Intel Corporation */ #ifndef LINUX_IEEE80211_H #define LINUX_IEEE80211_H #include <linux/types.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/bitfield.h> #include <asm/byteorder.h> #include <asm/unaligned.h> /* * DS bit usage * * TA = transmitter address * RA = receiver address * DA = destination address * SA = source address * * ToDS FromDS A1(RA) A2(TA) A3 A4 Use * ----------------------------------------------------------------- * 0 0 DA SA BSSID - IBSS/DLS * 0 1 DA BSSID SA - AP -> STA * 1 0 BSSID SA DA - AP <- STA * 1 1 RA TA DA SA unspecified (WDS) */ #define FCS_LEN 4 #define IEEE80211_FCTL_VERS 0x0003 #define IEEE80211_FCTL_FTYPE 0x000c #define IEEE80211_FCTL_STYPE 0x00f0 #define IEEE80211_FCTL_TODS 0x0100 #define IEEE80211_FCTL_FROMDS 0x0200 #define IEEE80211_FCTL_MOREFRAGS 0x0400 #define IEEE80211_FCTL_RETRY 0x0800 #define IEEE80211_FCTL_PM 0x1000 #define IEEE80211_FCTL_MOREDATA 0x2000 #define IEEE80211_FCTL_PROTECTED 0x4000 #define IEEE80211_FCTL_ORDER 0x8000 #define IEEE80211_FCTL_CTL_EXT 0x0f00 #define IEEE80211_SCTL_FRAG 0x000F #define IEEE80211_SCTL_SEQ 0xFFF0 #define IEEE80211_FTYPE_MGMT 0x0000 #define IEEE80211_FTYPE_CTL 0x0004 #define IEEE80211_FTYPE_DATA 0x0008 #define IEEE80211_FTYPE_EXT 0x000c /* management */ #define IEEE80211_STYPE_ASSOC_REQ 0x0000 #define IEEE80211_STYPE_ASSOC_RESP 0x0010 #define IEEE80211_STYPE_REASSOC_REQ 0x0020 #define IEEE80211_STYPE_REASSOC_RESP 0x0030 #define IEEE80211_STYPE_PROBE_REQ 0x0040 #define IEEE80211_STYPE_PROBE_RESP 0x0050 #define IEEE80211_STYPE_BEACON 0x0080 #define IEEE80211_STYPE_ATIM 0x0090 #define IEEE80211_STYPE_DISASSOC 0x00A0 #define IEEE80211_STYPE_AUTH 0x00B0 #define IEEE80211_STYPE_DEAUTH 0x00C0 #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ #define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 #define IEEE80211_STYPE_PSPOLL 0x00A0 #define IEEE80211_STYPE_RTS 0x00B0 #define IEEE80211_STYPE_CTS 0x00C0 #define IEEE80211_STYPE_ACK 0x00D0 #define IEEE80211_STYPE_CFEND 0x00E0 #define IEEE80211_STYPE_CFENDACK 0x00F0 /* data */ #define IEEE80211_STYPE_DATA 0x0000 #define IEEE80211_STYPE_DATA_CFACK 0x0010 #define IEEE80211_STYPE_DATA_CFPOLL 0x0020 #define IEEE80211_STYPE_DATA_CFACKPOLL 0x0030 #define IEEE80211_STYPE_NULLFUNC 0x0040 #define IEEE80211_STYPE_CFACK 0x0050 #define IEEE80211_STYPE_CFPOLL 0x0060 #define IEEE80211_STYPE_CFACKPOLL 0x0070 #define IEEE80211_STYPE_QOS_DATA 0x0080 #define IEEE80211_STYPE_QOS_DATA_CFACK 0x0090 #define IEEE80211_STYPE_QOS_DATA_CFPOLL 0x00A0 #define IEEE80211_STYPE_QOS_DATA_CFACKPOLL 0x00B0 #define IEEE80211_STYPE_QOS_NULLFUNC 0x00C0 #define IEEE80211_STYPE_QOS_CFACK 0x00D0 #define IEEE80211_STYPE_QOS_CFPOLL 0x00E0 #define IEEE80211_STYPE_QOS_CFACKPOLL 0x00F0 /* extension, added by 802.11ad */ #define IEEE80211_STYPE_DMG_BEACON 0x0000 #define IEEE80211_STYPE_S1G_BEACON 0x0010 /* bits unique to S1G beacon */ #define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 /* see 802.11ah-2016 9.9 NDP CMAC frames */ #define IEEE80211_S1G_1MHZ_NDP_BITS 25 #define IEEE80211_S1G_1MHZ_NDP_BYTES 4 #define IEEE80211_S1G_2MHZ_NDP_BITS 37 #define IEEE80211_S1G_2MHZ_NDP_BYTES 5 #define IEEE80211_NDP_FTYPE_CTS 0 #define IEEE80211_NDP_FTYPE_CF_END 0 #define IEEE80211_NDP_FTYPE_PS_POLL 1 #define IEEE80211_NDP_FTYPE_ACK 2 #define IEEE80211_NDP_FTYPE_PS_POLL_ACK 3 #define IEEE80211_NDP_FTYPE_BA 4 #define IEEE80211_NDP_FTYPE_BF_REPORT_POLL 5 #define IEEE80211_NDP_FTYPE_PAGING 6 #define IEEE80211_NDP_FTYPE_PREQ 7 #define SM64(f, v) ((((u64)v) << f##_S) & f) /* NDP CMAC frame fields */ #define IEEE80211_NDP_FTYPE 0x0000000000000007 #define IEEE80211_NDP_FTYPE_S 0x0000000000000000 /* 1M Probe Request 11ah 9.9.3.1.1 */ #define IEEE80211_NDP_1M_PREQ_ANO 0x0000000000000008 #define IEEE80211_NDP_1M_PREQ_ANO_S 3 #define IEEE80211_NDP_1M_PREQ_CSSID 0x00000000000FFFF0 #define IEEE80211_NDP_1M_PREQ_CSSID_S 4 #define IEEE80211_NDP_1M_PREQ_RTYPE 0x0000000000100000 #define IEEE80211_NDP_1M_PREQ_RTYPE_S 20 #define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 #define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 /* 2M Probe Request 11ah 9.9.3.1.2 */ #define IEEE80211_NDP_2M_PREQ_ANO 0x0000000000000008 #define IEEE80211_NDP_2M_PREQ_ANO_S 3 #define IEEE80211_NDP_2M_PREQ_CSSID 0x0000000FFFFFFFF0 #define IEEE80211_NDP_2M_PREQ_CSSID_S 4 #define IEEE80211_NDP_2M_PREQ_RTYPE 0x0000001000000000 #define IEEE80211_NDP_2M_PREQ_RTYPE_S 36 #define IEEE80211_ANO_NETTYPE_WILD 15 /* bits unique to S1G beacon */ #define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ #define IEEE80211_CTL_EXT_POLL 0x2000 #define IEEE80211_CTL_EXT_SPR 0x3000 #define IEEE80211_CTL_EXT_GRANT 0x4000 #define IEEE80211_CTL_EXT_DMG_CTS 0x5000 #define IEEE80211_CTL_EXT_DMG_DTS 0x6000 #define IEEE80211_CTL_EXT_SSW 0x8000 #define IEEE80211_CTL_EXT_SSW_FBACK 0x9000 #define IEEE80211_CTL_EXT_SSW_ACK 0xa000 #define IEEE80211_SN_MASK ((IEEE80211_SCTL_SEQ) >> 4) #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) /* PV1 Layout IEEE 802.11-2020 9.8.3.1 */ #define IEEE80211_PV1_FCTL_VERS 0x0003 #define IEEE80211_PV1_FCTL_FTYPE 0x001c #define IEEE80211_PV1_FCTL_STYPE 0x00e0 #define IEEE80211_PV1_FCTL_FROMDS 0x0100 #define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 #define IEEE80211_PV1_FCTL_PM 0x0400 #define IEEE80211_PV1_FCTL_MOREDATA 0x0800 #define IEEE80211_PV1_FCTL_PROTECTED 0x1000 #define IEEE80211_PV1_FCTL_END_SP 0x2000 #define IEEE80211_PV1_FCTL_RELAYED 0x4000 #define IEEE80211_PV1_FCTL_ACK_POLICY 0x8000 #define IEEE80211_PV1_FCTL_CTL_EXT 0x0f00 static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2) { return (sn1 + sn2) & IEEE80211_SN_MASK; } static inline u16 ieee80211_sn_inc(u16 sn) { return ieee80211_sn_add(sn, 1); } static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) { return (sn1 - sn2) & IEEE80211_SN_MASK; } #define IEEE80211_SEQ_TO_SN(seq) (((seq) & IEEE80211_SCTL_SEQ) >> 4) #define IEEE80211_SN_TO_SEQ(ssn) (((ssn) << 4) & IEEE80211_SCTL_SEQ) /* miscellaneous IEEE 802.11 constants */ #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 #define IEEE80211_MAX_AID 2007 #define IEEE80211_MAX_AID_S1G 8191 #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section 6.2.1.1.2. 802.11e clarifies the figure in section 7.1.2. The frame body is up to 2304 octets long (maximum MSDU size) plus any crypt overhead. */ #define IEEE80211_MAX_DATA_LEN 2304 /* 802.11ad extends maximum MSDU size for DMG (freq > 40Ghz) networks * to 7920 bytes, see 8.2.3 General frame format */ #define IEEE80211_MAX_DATA_LEN_DMG 7920 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 /* Maximal size of an A-MSDU that can be transported in a HT BA session */ #define IEEE80211_MAX_MPDU_LEN_HT_BA 4095 /* Maximal size of an A-MSDU */ #define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 #define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 #define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 #define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 #define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_MAX_MESH_ID_LEN 32 #define IEEE80211_FIRST_TSPEC_TSID 8 #define IEEE80211_NUM_TIDS 16 /* number of user priorities 802.11 uses */ #define IEEE80211_NUM_UPS 8 /* number of ACs */ #define IEEE80211_NUM_ACS 4 #define IEEE80211_QOS_CTL_LEN 2 /* 1d tag mask */ #define IEEE80211_QOS_CTL_TAG1D_MASK 0x0007 /* TID mask */ #define IEEE80211_QOS_CTL_TID_MASK 0x000f /* EOSP */ #define IEEE80211_QOS_CTL_EOSP 0x0010 /* ACK policy */ #define IEEE80211_QOS_CTL_ACK_POLICY_NORMAL 0x0000 #define IEEE80211_QOS_CTL_ACK_POLICY_NOACK 0x0020 #define IEEE80211_QOS_CTL_ACK_POLICY_NO_EXPL 0x0040 #define IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK 0x0060 #define IEEE80211_QOS_CTL_ACK_POLICY_MASK 0x0060 /* A-MSDU 802.11n */ #define IEEE80211_QOS_CTL_A_MSDU_PRESENT 0x0080 /* Mesh Control 802.11s */ #define IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT 0x0100 /* Mesh Power Save Level */ #define IEEE80211_QOS_CTL_MESH_PS_LEVEL 0x0200 /* Mesh Receiver Service Period Initiated */ #define IEEE80211_QOS_CTL_RSPI 0x0400 /* U-APSD queue for WMM IEs sent by AP */ #define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) #define IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK 0x0f /* U-APSD queues for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VO (1<<0) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VI (1<<1) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_BK (1<<2) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_BE (1<<3) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK 0x0f /* U-APSD max SP length for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL 0x00 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_2 0x01 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_4 0x02 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_6 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 #define IEEE80211_HT_CTL_LEN 4 /* trigger type within common_info of trigger frame */ #define IEEE80211_TRIGGER_TYPE_MASK 0xf #define IEEE80211_TRIGGER_TYPE_BASIC 0x0 #define IEEE80211_TRIGGER_TYPE_BFRP 0x1 #define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 #define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 #define IEEE80211_TRIGGER_TYPE_BSRP 0x4 #define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 #define IEEE80211_TRIGGER_TYPE_BQRP 0x6 #define IEEE80211_TRIGGER_TYPE_NFRP 0x7 /* UL-bandwidth within common_info of trigger frame */ #define IEEE80211_TRIGGER_ULBW_MASK 0xc0000 #define IEEE80211_TRIGGER_ULBW_20MHZ 0x0 #define IEEE80211_TRIGGER_ULBW_40MHZ 0x1 #define IEEE80211_TRIGGER_ULBW_80MHZ 0x2 #define IEEE80211_TRIGGER_ULBW_160_80P80MHZ 0x3 struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; struct_group(addrs, u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; ); __le16 seq_ctrl; u8 addr4[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; __le16 qos_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr_4addr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; u8 addr4[ETH_ALEN]; __le16 qos_ctrl; } __packed __aligned(2); struct ieee80211_trigger { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; u8 ta[ETH_ALEN]; __le64 common_info; u8 variable[]; } __packed __aligned(2); /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_tods(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_TODS)) != 0; } /** * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_fromds(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FROMDS)) != 0; } /** * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_a4(__le16 fc) { __le16 tmp = cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS); return (fc & tmp) == tmp; } /** * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_morefrags(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREFRAGS)) != 0; } /** * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_retry(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_RETRY)) != 0; } /** * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_pm(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PM)) != 0; } /** * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_moredata(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) != 0; } /** * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_protected(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PROTECTED)) != 0; } /** * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_has_order(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_ORDER)) != 0; } /** * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_mgmt(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT); } /** * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_ctl(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL); } /** * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA); } /** * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_ext(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_EXT); } /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_data_qos(__le16 fc) { /* * mask with QOS_DATA rather than IEEE80211_FCTL_STYPE as we just need * to check the one bit */ return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_STYPE_QOS_DATA)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA); } /** * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_data_present(__le16 fc) { /* * mask with 0x40 and test that that bit is clear to only return true * for the data-containing substypes. */ return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | 0x40)) == cpu_to_le16(IEEE80211_FTYPE_DATA); } /** * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_assoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); } /** * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_assoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP); } /** * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_reassoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); } /** * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_reassoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP); } /** * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_probe_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); } /** * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_probe_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); } /** * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } /** * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && * IEEE80211_STYPE_S1G_BEACON * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_s1g_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); } /** * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT && * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_next_tbtt_present(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) && fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT); } /** * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only * true for S1G beacons when they're short. * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) { return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc); } /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_atim(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ATIM); } /** * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_disassoc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DISASSOC); } /** * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_auth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); } /** * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_deauth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH); } /** * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_action(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); } /** * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_back_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); } /** * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_back(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK); } /** * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_pspoll(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); } /** * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_rts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); } /** * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_cts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS); } /** * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_ack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); } /** * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_cfend(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFEND); } /** * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_cfendack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFENDACK); } /** * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC); } /** * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); } /** * ieee80211_is_trigger - check if frame is trigger frame * @fc: frame control field in little-endian byteorder */ static inline bool ieee80211_is_trigger(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); } /** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee80211_is_any_nullfunc(__le16 fc) { return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)); } /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder */ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0; } /** * ieee80211_is_frag - check if a frame is a fragment * @hdr: 802.11 header of the frame */ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr) { return ieee80211_has_morefrags(hdr->frame_control) || hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG); } struct ieee80211s_hdr { u8 flags; u8 ttl; __le32 seqnum; u8 eaddr1[ETH_ALEN]; u8 eaddr2[ETH_ALEN]; } __packed __aligned(2); /* Mesh flags */ #define MESH_FLAGS_AE_A4 0x1 #define MESH_FLAGS_AE_A5_A6 0x2 #define MESH_FLAGS_AE 0x3 #define MESH_FLAGS_PS_DEEP 0x4 /** * enum ieee80211_preq_flags - mesh PREQ element flags * * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield */ enum ieee80211_preq_flags { IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, }; /** * enum ieee80211_preq_target_flags - mesh PREQ element per target flags * * @IEEE80211_PREQ_TO_FLAG: target only subfield * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield */ enum ieee80211_preq_target_flags { IEEE80211_PREQ_TO_FLAG = 1<<0, IEEE80211_PREQ_USN_FLAG = 1<<2, }; /** * struct ieee80211_quiet_ie - Quiet element * @count: Quiet Count * @period: Quiet Period * @duration: Quiet Duration * @offset: Quiet Offset * * This structure represents the payload of the "Quiet element" as * described in IEEE Std 802.11-2020 section 9.4.2.22. */ struct ieee80211_quiet_ie { u8 count; u8 period; __le16 duration; __le16 offset; } __packed; /** * struct ieee80211_msrment_ie - Measurement element * @token: Measurement Token * @mode: Measurement Report Mode * @type: Measurement Type * @request: Measurement Request or Measurement Report * * This structure represents the payload of both the "Measurement * Request element" and the "Measurement Report element" as described * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21. */ struct ieee80211_msrment_ie { u8 token; u8 mode; u8 type; u8 request[]; } __packed; /** * struct ieee80211_channel_sw_ie - Channel Switch Announcement element * @mode: Channel Switch Mode * @new_ch_num: New Channel Number * @count: Channel Switch Count * * This structure represents the payload of the "Channel Switch * Announcement element" as described in IEEE Std 802.11-2020 section * 9.4.2.18. */ struct ieee80211_channel_sw_ie { u8 mode; u8 new_ch_num; u8 count; } __packed; /** * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element * @mode: Channel Switch Mode * @new_operating_class: New Operating Class * @new_ch_num: New Channel Number * @count: Channel Switch Count * * This structure represents the "Extended Channel Switch Announcement * element" as described in IEEE Std 802.11-2020 section 9.4.2.52. */ struct ieee80211_ext_chansw_ie { u8 mode; u8 new_operating_class; u8 new_ch_num; u8 count; } __packed; /** * struct ieee80211_sec_chan_offs_ie - secondary channel offset IE * @sec_chan_offs: secondary channel offset, uses IEEE80211_HT_PARAM_CHA_SEC_* * values here * This structure represents the "Secondary Channel Offset element" */ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; /** * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE * @mesh_ttl: Time To Live * @mesh_flags: Flags * @mesh_reason: Reason Code * @mesh_pre_value: Precedence Value * * This structure represents the payload of the "Mesh Channel Switch * Parameters element" as described in IEEE Std 802.11-2020 section * 9.4.2.102. */ struct ieee80211_mesh_chansw_params_ie { u8 mesh_ttl; u8 mesh_flags; __le16 mesh_reason; __le16 mesh_pre_value; } __packed; /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE * @new_channel_width: New Channel Width * @new_center_freq_seg0: New Channel Center Frequency Segment 0 * @new_center_freq_seg1: New Channel Center Frequency Segment 1 * * This structure represents the payload of the "Wide Bandwidth * Channel Switch element" as described in IEEE Std 802.11-2020 * section 9.4.2.160. */ struct ieee80211_wide_bw_chansw_ie { u8 new_channel_width; u8 new_center_freq_seg0, new_center_freq_seg1; } __packed; /** * struct ieee80211_tim_ie - Traffic Indication Map information element * @dtim_count: DTIM Count * @dtim_period: DTIM Period * @bitmap_ctrl: Bitmap Control * @required_octet: "Syntatic sugar" to force the struct size to the * minimum valid size when carried in a non-S1G PPDU * @virtual_map: Partial Virtual Bitmap * * This structure represents the payload of the "TIM element" as * described in IEEE Std 802.11-2020 section 9.4.2.5. Note that this * definition is only applicable when the element is carried in a * non-S1G PPDU. When the TIM is carried in an S1G PPDU, the Bitmap * Control and Partial Virtual Bitmap may not be present. */ struct ieee80211_tim_ie { u8 dtim_count; u8 dtim_period; u8 bitmap_ctrl; union { u8 required_octet; DECLARE_FLEX_ARRAY(u8, virtual_map); }; } __packed; /** * struct ieee80211_meshconf_ie - Mesh Configuration element * @meshconf_psel: Active Path Selection Protocol Identifier * @meshconf_pmetric: Active Path Selection Metric Identifier * @meshconf_congest: Congestion Control Mode Identifier * @meshconf_synch: Synchronization Method Identifier * @meshconf_auth: Authentication Protocol Identifier * @meshconf_form: Mesh Formation Info * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) * * This structure represents the payload of the "Mesh Configuration * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. */ struct ieee80211_meshconf_ie { u8 meshconf_psel; u8 meshconf_pmetric; u8 meshconf_congest; u8 meshconf_synch; u8 meshconf_auth; u8 meshconf_form; u8 meshconf_cap; } __packed; /** * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags * * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish * additional mesh peerings with other mesh STAs * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure * is ongoing * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has * neighbors in deep sleep mode * * Enumerates the "Mesh Capability" as described in IEEE Std * 802.11-2020 section 9.4.2.97.7. */ enum mesh_config_capab_flags { IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, IEEE80211_MESHCONF_CAPAB_FORWARDING = 0x08, IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING = 0x20, IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, }; #define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 /* * mesh channel switch parameters element's flag indicator * */ #define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0) #define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1) #define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) /** * struct ieee80211_rann_ie - RANN (root announcement) element * @rann_flags: Flags * @rann_hopcount: Hop Count * @rann_ttl: Element TTL * @rann_addr: Root Mesh STA Address * @rann_seq: HWMP Sequence Number * @rann_interval: Interval * @rann_metric: Metric * * This structure represents the payload of the "RANN element" as * described in IEEE Std 802.11-2020 section 9.4.2.111. */ struct ieee80211_rann_ie { u8 rann_flags; u8 rann_hopcount; u8 rann_ttl; u8 rann_addr[ETH_ALEN]; __le32 rann_seq; __le32 rann_interval; __le32 rann_metric; } __packed; enum ieee80211_rann_flags { RANN_FLAG_IS_GATE = 1 << 0, }; enum ieee80211_ht_chanwidth_values { IEEE80211_HT_CHANWIDTH_20MHZ = 0, IEEE80211_HT_CHANWIDTH_ANY = 1, }; /** * enum ieee80211_vht_opmode_bits - VHT operating mode field bits * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask * (the NSS value is the value of this field + 1) * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU * using a beamforming steering matrix */ enum ieee80211_vht_opmode_bits { IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, }; /** * enum ieee80211_s1g_chanwidth * These are defined in IEEE802.11-2016ah Table 10-20 * as BSS Channel Width * * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel */ enum ieee80211_s1g_chanwidth { IEEE80211_S1G_CHANWIDTH_1MHZ = 0, IEEE80211_S1G_CHANWIDTH_2MHZ = 1, IEEE80211_S1G_CHANWIDTH_4MHZ = 3, IEEE80211_S1G_CHANWIDTH_8MHZ = 7, IEEE80211_S1G_CHANWIDTH_16MHZ = 15, }; #define WLAN_SA_QUERY_TR_ID_LEN 2 #define WLAN_MEMBERSHIP_LEN 8 #define WLAN_USER_POSITION_LEN 16 /** * struct ieee80211_tpc_report_ie - TPC Report element * @tx_power: Transmit Power * @link_margin: Link Margin * * This structure represents the payload of the "TPC Report element" as * described in IEEE Std 802.11-2020 section 9.4.2.16. */ struct ieee80211_tpc_report_ie { u8 tx_power; u8 link_margin; } __packed; #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 #define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) #define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK GENMASK(7, 5) #define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT 10 struct ieee80211_addba_ext_ie { u8 data; } __packed; /** * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element * @compat_info: Compatibility Information * @beacon_int: Beacon Interval * @tsf_completion: TSF Completion * * This structure represents the payload of the "S1G Beacon * Compatibility element" as described in IEEE Std 802.11-2020 section * 9.4.2.196. */ struct ieee80211_s1g_bcn_compat_ie { __le16 compat_info; __le16 beacon_int; __le32 tsf_completion; } __packed; /** * struct ieee80211_s1g_oper_ie - S1G Operation element * @ch_width: S1G Operation Information Channel Width * @oper_class: S1G Operation Information Operating Class * @primary_ch: S1G Operation Information Primary Channel Number * @oper_ch: S1G Operation Information Channel Center Frequency * @basic_mcs_nss: Basic S1G-MCS and NSS Set * * This structure represents the payload of the "S1G Operation * element" as described in IEEE Std 802.11-2020 section 9.4.2.212. */ struct ieee80211_s1g_oper_ie { u8 ch_width; u8 oper_class; u8 primary_ch; u8 oper_ch; __le16 basic_mcs_nss; } __packed; /** * struct ieee80211_aid_response_ie - AID Response element * @aid: AID/Group AID * @switch_count: AID Switch Count * @response_int: AID Response Interval * * This structure represents the payload of the "AID Response element" * as described in IEEE Std 802.11-2020 section 9.4.2.194. */ struct ieee80211_aid_response_ie { __le16 aid; u8 switch_count; __le16 response_int; } __packed; struct ieee80211_s1g_cap { u8 capab_info[10]; u8 supp_mcs_nss[5]; } __packed; struct ieee80211_ext { __le16 frame_control; __le16 duration; union { struct { u8 sa[ETH_ALEN]; __le32 timestamp; u8 change_seq; u8 variable[0]; } __packed s1g_beacon; struct { u8 sa[ETH_ALEN]; __le32 timestamp; u8 change_seq; u8 next_tbtt[3]; u8 variable[0]; } __packed s1g_short_beacon; } u; } __packed __aligned(2); #define IEEE80211_TWT_CONTROL_NDP BIT(0) #define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) #define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) #define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) #define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) #define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) #define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) #define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) #define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) #define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) #define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) #define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) #define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) enum ieee80211_twt_setup_cmd { TWT_SETUP_CMD_REQUEST, TWT_SETUP_CMD_SUGGEST, TWT_SETUP_CMD_DEMAND, TWT_SETUP_CMD_GROUPING, TWT_SETUP_CMD_ACCEPT, TWT_SETUP_CMD_ALTERNATE, TWT_SETUP_CMD_DICTATE, TWT_SETUP_CMD_REJECT, }; struct ieee80211_twt_params { __le16 req_type; __le64 twt; u8 min_twt_dur; __le16 mantissa; u8 channel; } __packed; struct ieee80211_twt_setup { u8 dialog_token; u8 element_id; u8 length; u8 control; u8 params[]; } __packed; #define IEEE80211_TTLM_MAX_CNT 2 #define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 #define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 #define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 #define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 #define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 #define IEEE80211_TTLM_DIRECTION_DOWN 0 #define IEEE80211_TTLM_DIRECTION_UP 1 #define IEEE80211_TTLM_DIRECTION_BOTH 2 /** * struct ieee80211_ttlm_elem - TID-To-Link Mapping element * * Defined in section 9.4.2.314 in P802.11be_D4 * * @control: the first part of control field * @optional: the second part of control field */ struct ieee80211_ttlm_elem { u8 control; u8 optional[]; } __packed; struct ieee80211_mgmt { __le16 frame_control; __le16 duration; u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; u8 bssid[ETH_ALEN]; __le16 seq_ctrl; union { struct { __le16 auth_alg; __le16 auth_transaction; __le16 status_code; /* possibly followed by Challenge text */ u8 variable[]; } __packed auth; struct { __le16 reason_code; } __packed deauth; struct { __le16 capab_info; __le16 listen_interval; /* followed by SSID and Supported rates */ u8 variable[]; } __packed assoc_req; struct { __le16 capab_info; __le16 status_code; __le16 aid; /* followed by Supported rates */ u8 variable[]; } __packed assoc_resp, reassoc_resp; struct { __le16 capab_info; __le16 status_code; u8 variable[]; } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ u8 variable[]; } __packed reassoc_req; struct { __le16 reason_code; } __packed disassoc; struct { __le64 timestamp; __le16 beacon_int; __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params, TIM */ u8 variable[]; } __packed beacon; struct { /* only variable items: SSID, Supported rates */ DECLARE_FLEX_ARRAY(u8, variable); } __packed probe_req; struct { __le64 timestamp; __le16 beacon_int; __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params */ u8 variable[]; } __packed probe_resp; struct { u8 category; union { struct { u8 action_code; u8 dialog_token; u8 status_code; u8 variable[]; } __packed wme_action; struct{ u8 action_code; u8 variable[]; } __packed chan_switch; struct{ u8 action_code; struct ieee80211_ext_chansw_ie data; u8 variable[]; } __packed ext_chan_switch; struct{ u8 action_code; u8 dialog_token; u8 element_id; u8 length; struct ieee80211_msrment_ie msr_elem; } __packed measurement; struct{ u8 action_code; u8 dialog_token; __le16 capab; __le16 timeout; __le16 start_seq_num; /* followed by BA Extension */ u8 variable[]; } __packed addba_req; struct{ u8 action_code; u8 dialog_token; __le16 status; __le16 capab; __le16 timeout; } __packed addba_resp; struct{ u8 action_code; __le16 params; __le16 reason_code; } __packed delba; struct { u8 action_code; u8 variable[]; } __packed self_prot; struct{ u8 action_code; u8 variable[]; } __packed mesh_action; struct { u8 action; u8 trans_id[WLAN_SA_QUERY_TR_ID_LEN]; } __packed sa_query; struct { u8 action; u8 smps_control; } __packed ht_smps; struct { u8 action_code; u8 chanwidth; } __packed ht_notify_cw; struct { u8 action_code; u8 dialog_token; __le16 capability; u8 variable[0]; } __packed tdls_discover_resp; struct { u8 action_code; u8 operating_mode; } __packed vht_opmode_notif; struct { u8 action_code; u8 membership[WLAN_MEMBERSHIP_LEN]; u8 position[WLAN_USER_POSITION_LEN]; } __packed vht_group_notif; struct { u8 action_code; u8 dialog_token; u8 tpc_elem_id; u8 tpc_elem_length; struct ieee80211_tpc_report_ie tpc; } __packed tpc_report; struct { u8 action_code; u8 dialog_token; u8 follow_up; u8 tod[6]; u8 toa[6]; __le16 tod_error; __le16 toa_error; u8 variable[]; } __packed ftm; struct { u8 action_code; u8 variable[]; } __packed s1g; struct { u8 action_code; u8 dialog_token; u8 follow_up; u32 tod; u32 toa; u8 max_tod_error; u8 max_toa_error; } __packed wnm_timing_msr; } u; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ } u; } __packed __aligned(2); /* Supported rates membership selectors */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 #define BSS_MEMBERSHIP_SELECTOR_GLK 125 #define BSS_MEMBERSHIP_SELECTOR_EPS 124 #define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123 #define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 #define BSS_MEMBERSHIP_SELECTOR_EHT_PHY 121 /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) /* Management MIC information element (IEEE 802.11w) */ struct ieee80211_mmie { u8 element_id; u8 length; __le16 key_id; u8 sequence_number[6]; u8 mic[8]; } __packed; /* Management MIC information element (IEEE 802.11w) for GMAC and CMAC-256 */ struct ieee80211_mmie_16 { u8 element_id; u8 length; __le16 key_id; u8 sequence_number[6]; u8 mic[16]; } __packed; struct ieee80211_vendor_ie { u8 element_id; u8 len; u8 oui[3]; u8 oui_type; } __packed; struct ieee80211_wmm_ac_param { u8 aci_aifsn; /* AIFSN, ACM, ACI */ u8 cw; /* ECWmin, ECWmax (CW = 2^ECW - 1) */ __le16 txop_limit; } __packed; struct ieee80211_wmm_param_ie { u8 element_id; /* Element ID: 221 (0xdd); */ u8 len; /* Length: 24 */ /* required fields for WMM version 1 */ u8 oui[3]; /* 00:50:f2 */ u8 oui_type; /* 2 */ u8 oui_subtype; /* 1 */ u8 version; /* 1 for WMM version 1.0 */ u8 qos_info; /* AP/STA specific QoS info */ u8 reserved; /* 0 */ /* AC_BE, AC_BK, AC_VI, AC_VO */ struct ieee80211_wmm_ac_param ac[4]; } __packed; /* Control frames */ struct ieee80211_rts { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; u8 ta[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; u8 bssid[ETH_ALEN]; u8 ta[ETH_ALEN]; } __packed __aligned(2); /* TDLS */ /* Channel switch timing */ struct ieee80211_ch_switch_timing { __le16 switch_time; __le16 switch_timeout; } __packed; /* Link-id information element */ struct ieee80211_tdls_lnkie { u8 ie_type; /* Link Identifier IE */ u8 ie_len; u8 bssid[ETH_ALEN]; u8 init_sta[ETH_ALEN]; u8 resp_sta[ETH_ALEN]; } __packed; struct ieee80211_tdls_data { u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; __be16 ether_type; u8 payload_type; u8 category; u8 action_code; union { struct { u8 dialog_token; __le16 capability; u8 variable[0]; } __packed setup_req; struct { __le16 status_code; u8 dialog_token; __le16 capability; u8 variable[0]; } __packed setup_resp; struct { __le16 status_code; u8 dialog_token; u8 variable[0]; } __packed setup_cfm; struct { __le16 reason_code; u8 variable[0]; } __packed teardown; struct { u8 dialog_token; u8 variable[0]; } __packed discover_req; struct { u8 target_channel; u8 oper_class; u8 variable[0]; } __packed chan_switch_req; struct { __le16 status_code; u8 variable[0]; } __packed chan_switch_resp; } u; } __packed; /* * Peer-to-Peer IE attribute related definitions. */ /* * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute. */ enum ieee80211_p2p_attr_id { IEEE80211_P2P_ATTR_STATUS = 0, IEEE80211_P2P_ATTR_MINOR_REASON, IEEE80211_P2P_ATTR_CAPABILITY, IEEE80211_P2P_ATTR_DEVICE_ID, IEEE80211_P2P_ATTR_GO_INTENT, IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT, IEEE80211_P2P_ATTR_LISTEN_CHANNEL, IEEE80211_P2P_ATTR_GROUP_BSSID, IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING, IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR, IEEE80211_P2P_ATTR_MANAGABILITY, IEEE80211_P2P_ATTR_CHANNEL_LIST, IEEE80211_P2P_ATTR_ABSENCE_NOTICE, IEEE80211_P2P_ATTR_DEVICE_INFO, IEEE80211_P2P_ATTR_GROUP_INFO, IEEE80211_P2P_ATTR_GROUP_ID, IEEE80211_P2P_ATTR_INTERFACE, IEEE80211_P2P_ATTR_OPER_CHANNEL, IEEE80211_P2P_ATTR_INVITE_FLAGS, /* 19 - 220: Reserved */ IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221, IEEE80211_P2P_ATTR_MAX }; /* Notice of Absence attribute - described in P2P spec 4.1.14 */ /* Typical max value used here */ #define IEEE80211_P2P_NOA_DESC_MAX 4 struct ieee80211_p2p_noa_desc { u8 count; __le32 duration; __le32 interval; __le32 start_time; } __packed; struct ieee80211_p2p_noa_attr { u8 index; u8 oppps_ctwindow; struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX]; } __packed; #define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F /** * struct ieee80211_bar - Block Ack Request frame format * @frame_control: Frame Control * @duration: Duration * @ra: RA * @ta: TA * @control: BAR Control * @start_seq_num: Starting Sequence Number (see Figure 9-37) * * This structure represents the "BlockAckReq frame format" * as described in IEEE Std 802.11-2020 section 9.3.1.7. */ struct ieee80211_bar { __le16 frame_control; __le16 duration; __u8 ra[ETH_ALEN]; __u8 ta[ETH_ALEN]; __le16 control; __le16 start_seq_num; } __packed; /* 802.11 BAR control masks */ #define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL 0x0000 #define IEEE80211_BAR_CTRL_MULTI_TID 0x0002 #define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA 0x0004 #define IEEE80211_BAR_CTRL_TID_INFO_MASK 0xf000 #define IEEE80211_BAR_CTRL_TID_INFO_SHIFT 12 #define IEEE80211_HT_MCS_MASK_LEN 10 /** * struct ieee80211_mcs_info - Supported MCS Set field * @rx_mask: RX mask * @rx_highest: highest supported RX rate. If set represents * the highest supported RX data rate in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. * @tx_params: TX parameters * @reserved: Reserved bits * * This structure represents the "Supported MCS Set field" as * described in IEEE Std 802.11-2020 section 9.4.2.55.4. */ struct ieee80211_mcs_info { u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; __le16 rx_highest; u8 tx_params; u8 reserved[3]; } __packed; /* 802.11n HT capability MSC set */ #define IEEE80211_HT_MCS_RX_HIGHEST_MASK 0x3ff #define IEEE80211_HT_MCS_TX_DEFINED 0x01 #define IEEE80211_HT_MCS_TX_RX_DIFF 0x02 /* value 0 == 1 stream etc */ #define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK 0x0C #define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT 2 #define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 #define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 #define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) /* * 802.11n D5.0 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 */ #define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33 #define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \ (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) /** * struct ieee80211_ht_cap - HT capabilities element * @cap_info: HT Capability Information * @ampdu_params_info: A-MPDU Parameters * @mcs: Supported MCS Set * @extended_ht_cap_info: HT Extended Capabilities * @tx_BF_cap_info: Transmit Beamforming Capabilities * @antenna_selection_info: ASEL Capability * * This structure represents the payload of the "HT Capabilities * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. */ struct ieee80211_ht_cap { __le16 cap_info; u8 ampdu_params_info; /* 16 bytes MCS information */ struct ieee80211_mcs_info mcs; __le16 extended_ht_cap_info; __le32 tx_BF_cap_info; u8 antenna_selection_info; } __packed; /* 802.11n HT capabilities masks (for cap_info) */ #define IEEE80211_HT_CAP_LDPC_CODING 0x0001 #define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 #define IEEE80211_HT_CAP_SM_PS 0x000C #define IEEE80211_HT_CAP_SM_PS_SHIFT 2 #define IEEE80211_HT_CAP_GRN_FLD 0x0010 #define IEEE80211_HT_CAP_SGI_20 0x0020 #define IEEE80211_HT_CAP_SGI_40 0x0040 #define IEEE80211_HT_CAP_TX_STBC 0x0080 #define IEEE80211_HT_CAP_RX_STBC 0x0300 #define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 #define IEEE80211_HT_CAP_DELAY_BA 0x0400 #define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 #define IEEE80211_HT_CAP_DSSSCCK40 0x1000 #define IEEE80211_HT_CAP_RESERVED 0x2000 #define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 #define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 /* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */ #define IEEE80211_HT_EXT_CAP_PCO 0x0001 #define IEEE80211_HT_EXT_CAP_PCO_TIME 0x0006 #define IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT 1 #define IEEE80211_HT_EXT_CAP_MCS_FB 0x0300 #define IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT 8 #define IEEE80211_HT_EXT_CAP_HTC_SUP 0x0400 #define IEEE80211_HT_EXT_CAP_RD_RESPONDER 0x0800 /* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ #define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 #define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C #define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 /* * Maximum length of AMPDU that the STA can receive in high-throughput (HT). * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) */ enum ieee80211_max_ampdu_length_exp { IEEE80211_HT_MAX_AMPDU_8K = 0, IEEE80211_HT_MAX_AMPDU_16K = 1, IEEE80211_HT_MAX_AMPDU_32K = 2, IEEE80211_HT_MAX_AMPDU_64K = 3 }; /* * Maximum length of AMPDU that the STA can receive in VHT. * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) */ enum ieee80211_vht_max_ampdu_length_exp { IEEE80211_VHT_MAX_AMPDU_8K = 0, IEEE80211_VHT_MAX_AMPDU_16K = 1, IEEE80211_VHT_MAX_AMPDU_32K = 2, IEEE80211_VHT_MAX_AMPDU_64K = 3, IEEE80211_VHT_MAX_AMPDU_128K = 4, IEEE80211_VHT_MAX_AMPDU_256K = 5, IEEE80211_VHT_MAX_AMPDU_512K = 6, IEEE80211_VHT_MAX_AMPDU_1024K = 7 }; #define IEEE80211_HT_MAX_AMPDU_FACTOR 13 /* Minimum MPDU start spacing */ enum ieee80211_min_mpdu_spacing { IEEE80211_HT_MPDU_DENSITY_NONE = 0, /* No restriction */ IEEE80211_HT_MPDU_DENSITY_0_25 = 1, /* 1/4 usec */ IEEE80211_HT_MPDU_DENSITY_0_5 = 2, /* 1/2 usec */ IEEE80211_HT_MPDU_DENSITY_1 = 3, /* 1 usec */ IEEE80211_HT_MPDU_DENSITY_2 = 4, /* 2 usec */ IEEE80211_HT_MPDU_DENSITY_4 = 5, /* 4 usec */ IEEE80211_HT_MPDU_DENSITY_8 = 6, /* 8 usec */ IEEE80211_HT_MPDU_DENSITY_16 = 7 /* 16 usec */ }; /** * struct ieee80211_ht_operation - HT operation IE * @primary_chan: Primary Channel * @ht_param: HT Operation Information parameters * @operation_mode: HT Operation Information operation mode * @stbc_param: HT Operation Information STBC params * @basic_set: Basic HT-MCS Set * * This structure represents the payload of the "HT Operation * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. */ struct ieee80211_ht_operation { u8 primary_chan; u8 ht_param; __le16 operation_mode; __le16 stbc_param; u8 basic_set[16]; } __packed; /* for ht_param */ #define IEEE80211_HT_PARAM_CHA_SEC_OFFSET 0x03 #define IEEE80211_HT_PARAM_CHA_SEC_NONE 0x00 #define IEEE80211_HT_PARAM_CHA_SEC_ABOVE 0x01 #define IEEE80211_HT_PARAM_CHA_SEC_BELOW 0x03 #define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY 0x04 #define IEEE80211_HT_PARAM_RIFS_MODE 0x08 /* for operation_mode */ #define IEEE80211_HT_OP_MODE_PROTECTION 0x0003 #define IEEE80211_HT_OP_MODE_PROTECTION_NONE 0 #define IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER 1 #define IEEE80211_HT_OP_MODE_PROTECTION_20MHZ 2 #define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 #define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 #define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 #define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 #define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 /* for stbc_param */ #define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 #define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT 0x0080 #define IEEE80211_HT_STBC_PARAM_STBC_BEACON 0x0100 #define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT 0x0200 #define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE 0x0400 #define IEEE80211_HT_STBC_PARAM_PCO_PHASE 0x0800 /* block-ack parameters */ #define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C #define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 #define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 /* * A-MPDU buffer sizes * According to HT size varies from 8 to 64 frames * HE adds the ability to have up to 256 frames. * EHT adds the ability to have up to 1K frames. */ #define IEEE80211_MIN_AMPDU_BUF 0x8 #define IEEE80211_MAX_AMPDU_BUF_HT 0x40 #define IEEE80211_MAX_AMPDU_BUF_HE 0x100 #define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 /* Spatial Multiplexing Power Save Modes (for capability) */ #define WLAN_HT_CAP_SM_PS_STATIC 0 #define WLAN_HT_CAP_SM_PS_DYNAMIC 1 #define WLAN_HT_CAP_SM_PS_INVALID 2 #define WLAN_HT_CAP_SM_PS_DISABLED 3 /* for SM power control field lower two bits */ #define WLAN_HT_SMPS_CONTROL_DISABLED 0 #define WLAN_HT_SMPS_CONTROL_STATIC 1 #define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 /** * struct ieee80211_vht_mcs_info - VHT MCS information * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams * @rx_highest: Indicates highest long GI VHT PPDU data rate * STA can receive. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. * The top 3 bits of this field indicate the Maximum NSTS,total * (a beamformee capability.) * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams * @tx_highest: Indicates highest long GI VHT PPDU data rate * STA can transmit. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest TX data rate supported. * The top 2 bits of this field are reserved, the * 3rd bit from the top indiciates VHT Extended NSS BW * Capability. */ struct ieee80211_vht_mcs_info { __le16 rx_mcs_map; __le16 rx_highest; __le16 tx_mcs_map; __le16 tx_highest; } __packed; /* for rx_highest */ #define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 #define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) /* for tx_highest */ #define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) /** * enum ieee80211_vht_mcs_support - VHT MCS support definitions * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the * number of streams * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported * * These definitions are used in each 2-bit subfield of the @rx_mcs_map * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are * both split into 8 subfields by number of streams. These values indicate * which MCSes are supported for the number of streams the value appears * for. */ enum ieee80211_vht_mcs_support { IEEE80211_VHT_MCS_SUPPORT_0_7 = 0, IEEE80211_VHT_MCS_SUPPORT_0_8 = 1, IEEE80211_VHT_MCS_SUPPORT_0_9 = 2, IEEE80211_VHT_MCS_NOT_SUPPORTED = 3, }; /** * struct ieee80211_vht_cap - VHT capabilities * * This structure is the "VHT capabilities element" as * described in 802.11ac D3.0 8.4.2.160 * @vht_cap_info: VHT capability info * @supp_mcs: VHT MCS supported rates */ struct ieee80211_vht_cap { __le32 vht_cap_info; struct ieee80211_vht_mcs_info supp_mcs; } __packed; /** * enum ieee80211_vht_chanwidth - VHT channel width * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to * determine the channel width (20 or 40 MHz) * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth */ enum ieee80211_vht_chanwidth { IEEE80211_VHT_CHANWIDTH_USE_HT = 0, IEEE80211_VHT_CHANWIDTH_80MHZ = 1, IEEE80211_VHT_CHANWIDTH_160MHZ = 2, IEEE80211_VHT_CHANWIDTH_80P80MHZ = 3, }; /** * struct ieee80211_vht_operation - VHT operation IE * * This structure is the "VHT operation element" as * described in 802.11ac D3.0 8.4.2.161 * @chan_width: Operating channel width * @center_freq_seg0_idx: center freq segment 0 index * @center_freq_seg1_idx: center freq segment 1 index * @basic_mcs_set: VHT Basic MCS rate set */ struct ieee80211_vht_operation { u8 chan_width; u8 center_freq_seg0_idx; u8 center_freq_seg1_idx; __le16 basic_mcs_set; } __packed; /** * struct ieee80211_he_cap_elem - HE capabilities element * @mac_cap_info: HE MAC Capabilities Information * @phy_cap_info: HE PHY Capabilities Information * * This structure represents the fixed fields of the payload of the * "HE capabilities element" as described in IEEE Std 802.11ax-2021 * sections 9.4.2.248.2 and 9.4.2.248.3. */ struct ieee80211_he_cap_elem { u8 mac_cap_info[6]; u8 phy_cap_info[11]; } __packed; #define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 /** * enum ieee80211_he_mcs_support - HE MCS support definitions * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the * number of streams * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported * * These definitions are used in each 2-bit subfield of the rx_mcs_* * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are * both split into 8 subfields by number of streams. These values indicate * which MCSes are supported for the number of streams the value appears * for. */ enum ieee80211_he_mcs_support { IEEE80211_HE_MCS_SUPPORT_0_7 = 0, IEEE80211_HE_MCS_SUPPORT_0_9 = 1, IEEE80211_HE_MCS_SUPPORT_0_11 = 2, IEEE80211_HE_MCS_NOT_SUPPORTED = 3, }; /** * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field * * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field * described in P802.11ax_D2.0 section 9.4.2.237.4 * * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel * widths less than 80MHz. * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel * widths less than 80MHz. * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel * width 160MHz. * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel * width 160MHz. * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for * channel width 80p80MHz. * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for * channel width 80p80MHz. */ struct ieee80211_he_mcs_nss_supp { __le16 rx_mcs_80; __le16 tx_mcs_80; __le16 rx_mcs_160; __le16 tx_mcs_160; __le16 rx_mcs_80p80; __le16 tx_mcs_80p80; } __packed; /** * struct ieee80211_he_operation - HE Operation element * @he_oper_params: HE Operation Parameters + BSS Color Information * @he_mcs_nss_set: Basic HE-MCS And NSS Set * @optional: Optional fields VHT Operation Information, Max Co-Hosted * BSSID Indicator, and 6 GHz Operation Information * * This structure represents the payload of the "HE Operation * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. */ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; u8 optional[]; } __packed; /** * struct ieee80211_he_spr - Spatial Reuse Parameter Set element * @he_sr_control: SR Control * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color * Bitmap, and SRG Partial BSSID Bitmap * * This structure represents the payload of the "Spatial Reuse * Parameter Set element" as described in IEEE Std 802.11ax-2021 * section 9.4.2.252. */ struct ieee80211_he_spr { u8 he_sr_control; u8 optional[]; } __packed; /** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * @aifsn: ACI/AIFSN * @ecw_min_max: ECWmin/ECWmax * @mu_edca_timer: MU EDCA Timer * * This structure represents the "MU AC Parameter Record" as described * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. */ struct ieee80211_he_mu_edca_param_ac_rec { u8 aifsn; u8 ecw_min_max; u8 mu_edca_timer; } __packed; /** * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element * @mu_qos_info: QoS Info * @ac_be: MU AC_BE Parameter Record * @ac_bk: MU AC_BK Parameter Record * @ac_vi: MU AC_VI Parameter Record * @ac_vo: MU AC_VO Parameter Record * * This structure represents the payload of the "MU EDCA Parameter Set * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. */ struct ieee80211_mu_edca_param_set { u8 mu_qos_info; struct ieee80211_he_mu_edca_param_ac_rec ac_be; struct ieee80211_he_mu_edca_param_ac_rec ac_bk; struct ieee80211_he_mu_edca_param_ac_rec ac_vi; struct ieee80211_he_mu_edca_param_ac_rec ac_vo; } __packed; #define IEEE80211_EHT_MCS_NSS_RX 0x0f #define IEEE80211_EHT_MCS_NSS_TX 0xf0 /** * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max * supported NSS for per MCS. * * For each field below, bits 0 - 3 indicate the maximal number of spatial * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams * for Tx. * * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 0 - 7. * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 8 - 9. * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 10 - 11. * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 12 - 13. * @rx_tx_max_nss: array of the previous fields for easier loop access */ struct ieee80211_eht_mcs_nss_supp_20mhz_only { union { struct { u8 rx_tx_mcs7_max_nss; u8 rx_tx_mcs9_max_nss; u8 rx_tx_mcs11_max_nss; u8 rx_tx_mcs13_max_nss; }; u8 rx_tx_max_nss[4]; }; }; /** * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except * 20MHz only stations). * * For each field below, bits 0 - 3 indicate the maximal number of spatial * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams * for Tx. * * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 0 - 9. * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 10 - 11. * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams * supported for reception and the maximum number of spatial streams * supported for transmission for MCS 12 - 13. * @rx_tx_max_nss: array of the previous fields for easier loop access */ struct ieee80211_eht_mcs_nss_supp_bw { union { struct { u8 rx_tx_mcs9_max_nss; u8 rx_tx_mcs11_max_nss; u8 rx_tx_mcs13_max_nss; }; u8 rx_tx_max_nss[3]; }; }; /** * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data * * This structure is the "EHT Capabilities element" fixed fields as * described in P802.11be_D2.0 section 9.4.2.313. * * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* */ struct ieee80211_eht_cap_elem_fixed { u8 mac_cap_info[2]; u8 phy_cap_info[9]; } __packed; /** * struct ieee80211_eht_cap_elem - EHT capabilities element * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed * @optional: optional parts */ struct ieee80211_eht_cap_elem { struct ieee80211_eht_cap_elem_fixed fixed; /* * Followed by: * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. * EHT PPE Thresholds field: variable length. */ u8 optional[]; } __packed; #define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 #define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 #define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 #define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 #define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 /** * struct ieee80211_eht_operation - eht operation element * * This structure is the "EHT Operation Element" fields as * described in P802.11be_D2.0 section 9.4.2.311 * * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and * receive. * @optional: optional parts */ struct ieee80211_eht_operation { u8 params; struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss; u8 optional[]; } __packed; /** * struct ieee80211_eht_operation_info - eht operation information * * @control: EHT operation information control. * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz * EHT BSS. * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. * @optional: optional parts */ struct ieee80211_eht_operation_info { u8 control; u8 ccfs0; u8 ccfs1; u8 optional[]; } __packed; /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 #define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 #define IEEE80211_VHT_CAP_RXLDPC 0x00000010 #define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 #define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 #define IEEE80211_VHT_CAP_TXSTBC 0x00000080 #define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 #define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 #define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 #define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 #define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) #define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 #define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) #define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 #define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 #define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 #define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 #define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT 23 #define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK \ (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT) #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 #define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 #define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 /** * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS * @cap: VHT capabilities of the peer * @bw: bandwidth to use * @mcs: MCS index to use * @ext_nss_bw_capable: indicates whether or not the local transmitter * (rate scaling algorithm) can deal with the new logic * (dot11VHTExtendedNSSBWCapable) * @max_vht_nss: current maximum NSS as advertised by the STA in * operating mode notification, can be 0 in which case the * capability data will be used to derive this (from MCS support) * * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can * vary for a given BW/MCS. This function parses the data. * * Note: This function is exported by cfg80211. */ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss); /** * enum ieee80211_ap_reg_power - regulatory power for a Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode * @IEEE80211_REG_LPI_AP: Indoor Access Point * @IEEE80211_REG_SP_AP: Standard power Access Point * @IEEE80211_REG_VLP_AP: Very low power Access Point * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal * @IEEE80211_REG_AP_POWER_MAX: maximum value */ enum ieee80211_ap_reg_power { IEEE80211_REG_UNSET_AP, IEEE80211_REG_LPI_AP, IEEE80211_REG_SP_AP, IEEE80211_REG_VLP_AP, IEEE80211_REG_AP_POWER_AFTER_LAST, IEEE80211_REG_AP_POWER_MAX = IEEE80211_REG_AP_POWER_AFTER_LAST - 1, }; /** * enum ieee80211_client_reg_power - regulatory power for a client * * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode * @IEEE80211_REG_DEFAULT_CLIENT: Default Client * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value */ enum ieee80211_client_reg_power { IEEE80211_REG_UNSET_CLIENT, IEEE80211_REG_DEFAULT_CLIENT, IEEE80211_REG_SUBORDINATE_CLIENT, IEEE80211_REG_CLIENT_POWER_AFTER_LAST, IEEE80211_REG_CLIENT_POWER_MAX = IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1, }; /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 #define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 #define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 #define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 #define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 #define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 #define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 #define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 #define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 #define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 #define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 #define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 #define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 #define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 /* Link adaptation is split between byte HE_MAC_CAP1 and * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE * in which case the following values apply: * 0 = No feedback. * 1 = reserved. * 2 = Unsolicited feedback. * 3 = both */ #define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 #define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 #define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 #define IEEE80211_HE_MAC_CAP2_TRS 0x04 #define IEEE80211_HE_MAC_CAP2_BSR 0x08 #define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 #define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 #define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 #define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 #define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 #define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 /* The maximum length of an A-MDPU is defined by the combination of the Maximum * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the * same field in the HE capabilities. */ #define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0 0x00 #define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 0x08 #define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2 0x10 #define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3 0x18 #define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 #define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 #define IEEE80211_HE_MAC_CAP4_PSR_RESP 0x08 #define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 #define IEEE80211_HE_MAC_CAP4_OPS 0x20 #define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU 0x40 /* Multi TID agg TX is split between byte #4 and #5 * The value is a combination of B39,B40,B41 */ #define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 #define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 #define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 #define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION 0x04 #define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 #define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 #define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS 0x20 #define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 #define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 #define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 #define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 #define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 /* 802.11ax HE PHY capabilities */ #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe #define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 #define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 #define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 #define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 #define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f #define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 #define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 #define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 /* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ #define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 #define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 #define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 #define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 #define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 #define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 #define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 /* Note that the meaning of UL MU below is different between an AP and a non-AP * sta, where in the AP case it indicates support for Rx and in the non-AP sta * case it indicates support for Tx. */ #define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 #define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 #define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 #define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU 0x40 #define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 #define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 #define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 /* Minimal allowed value of Max STS under 80MHz is 3 */ #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c /* Minimal allowed value of Max STS above 80MHz is 3 */ #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 #define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 #define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 #define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 #define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 #define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 #define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 #define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB 0x04 #define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB 0x08 #define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 #define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 #define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 #define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 #define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR 0x01 #define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP 0x02 #define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 #define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 #define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 #define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 #define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 #define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 #define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 #define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 #define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 #define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 #define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 #define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 #define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 #define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242 0x00 #define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484 0x40 #define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996 0x80 #define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996 0xc0 #define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK 0xc0 #define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 #define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 #define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 #define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 #define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 #define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) #define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 #define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 /* TX/RX HE MCS Support field Highest MCS subfield encoding */ enum ieee80211_he_highest_mcs_supported_subfield_enc { HIGHEST_MCS_SUPPORTED_MCS7 = 0, HIGHEST_MCS_SUPPORTED_MCS8, HIGHEST_MCS_SUPPORTED_MCS9, HIGHEST_MCS_SUPPORTED_MCS10, HIGHEST_MCS_SUPPORTED_MCS11, }; /* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ static inline u8 ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) { u8 count = 4; if (he_cap->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) count += 4; if (he_cap->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) count += 4; return count; } /* 802.11ax HE PPE Thresholds */ #define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) #define IEEE80211_PPE_THRES_NSS_POS (0) #define IEEE80211_PPE_THRES_NSS_MASK (7) #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ (BIT(5) | BIT(6)) #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) #define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) #define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) /* * Calculate 802.11ax HE capabilities IE PPE field size * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* */ static inline u8 ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) { u8 n; if ((phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) return 0; n = hweight8(ppe_thres_hdr & IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> IEEE80211_PPE_THRES_NSS_POS)); /* * Each pair is 6 bits, and we need to add the 7 "header" bits to the * total size. */ n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; n = DIV_ROUND_UP(n, 8); return n; } static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) { const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; u8 needed = sizeof(*he_cap_ie_elem); if (len < needed) return false; needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); if (len < needed) return false; if (he_cap_ie_elem->phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { if (len < needed + 1) return false; needed += ieee80211_he_ppe_size(data[needed], he_cap_ie_elem->phy_cap_info); } return len >= needed; } /* HE Operation defines */ #define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 #define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 #define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 #define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 #define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 #define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 #define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 #define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field * @primary: primary channel * @control: control flags * @ccfs0: channel center frequency segment 0 * @ccfs1: channel center frequency segment 1 * @minrate: minimum rate (in 1 Mbps units) */ struct ieee80211_he_6ghz_oper { u8 primary; #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 #define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 #define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x38 u8 control; u8 ccfs0; u8 ccfs1; u8 minrate; } __packed; /* * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021", * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation * subfield encoding", and two category for each type in "Table E-12-Regulatory * Info subfield encoding in the United States". * So it it totally max 8 Transmit Power Envelope element. */ #define IEEE80211_TPE_MAX_IE_COUNT 8 /* * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield" * of "IEEE Std 802.11ax™‐2021", the max power level is 8. */ #define IEEE80211_MAX_NUM_PWR_LEVEL 8 #define IEEE80211_TPE_MAX_POWER_COUNT 8 /* transmit power interpretation type of transmit power envelope element */ enum ieee80211_tx_power_intrpt_type { IEEE80211_TPE_LOCAL_EIRP, IEEE80211_TPE_LOCAL_EIRP_PSD, IEEE80211_TPE_REG_CLIENT_EIRP, IEEE80211_TPE_REG_CLIENT_EIRP_PSD, }; /** * struct ieee80211_tx_pwr_env - Transmit Power Envelope * @tx_power_info: Transmit Power Information field * @tx_power: Maximum Transmit Power field * * This structure represents the payload of the "Transmit Power * Envelope element" as described in IEEE Std 802.11ax-2021 section * 9.4.2.161 */ struct ieee80211_tx_pwr_env { u8 tx_power_info; s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT]; } __packed; #define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 #define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 #define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte * after the ext ID byte. It is assumed that he_oper_ie has at least * sizeof(struct ieee80211_he_operation) bytes, the caller must have * validated this. * @return the actual size of the IE data (not including header), or 0 on error */ static inline u8 ieee80211_he_oper_size(const u8 *he_oper_ie) { const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; u8 oper_len = sizeof(struct ieee80211_he_operation); u32 he_oper_params; /* Make sure the input is not NULL */ if (!he_oper_ie) return 0; /* Calc required length */ he_oper_params = le32_to_cpu(he_oper->he_oper_params); if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) oper_len += 3; if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) oper_len++; if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) oper_len += sizeof(struct ieee80211_he_6ghz_oper); /* Add the first byte (extension ID) to the total length */ oper_len++; return oper_len; } /** * ieee80211_he_6ghz_oper - obtain 6 GHz operation field * @he_oper: HE operation element (must be pre-validated for size) * but may be %NULL * * Return: a pointer to the 6 GHz operation field, or %NULL */ static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { const u8 *ret; u32 he_oper_params; if (!he_oper) return NULL; ret = (const void *)&he_oper->optional; he_oper_params = le32_to_cpu(he_oper->he_oper_params); if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) return NULL; if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) ret += 3; if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) ret++; return (const void *)ret; } /* HE Spatial Reuse defines */ #define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) #define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) #define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) #define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) #define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) /* * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte * after the ext ID byte. It is assumed that he_spr_ie has at least * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated * this * @return the actual size of the IE data (not including header), or 0 on error */ static inline u8 ieee80211_he_spr_size(const u8 *he_spr_ie) { const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); u8 he_spr_params; /* Make sure the input is not NULL */ if (!he_spr_ie) return 0; /* Calc required length */ he_spr_params = he_spr->he_sr_control; if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) spr_len++; if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) spr_len += 18; /* Add the first byte (extension ID) to the total length */ spr_len++; return spr_len; } /* S1G Capabilities Information field */ #define IEEE80211_S1G_CAPABILITY_LEN 15 #define S1G_CAP0_S1G_LONG BIT(0) #define S1G_CAP0_SGI_1MHZ BIT(1) #define S1G_CAP0_SGI_2MHZ BIT(2) #define S1G_CAP0_SGI_4MHZ BIT(3) #define S1G_CAP0_SGI_8MHZ BIT(4) #define S1G_CAP0_SGI_16MHZ BIT(5) #define S1G_CAP0_SUPP_CH_WIDTH GENMASK(7, 6) #define S1G_SUPP_CH_WIDTH_2 0 #define S1G_SUPP_CH_WIDTH_4 1 #define S1G_SUPP_CH_WIDTH_8 2 #define S1G_SUPP_CH_WIDTH_16 3 #define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \ cap[0])) << 1) #define S1G_CAP1_RX_LDPC BIT(0) #define S1G_CAP1_TX_STBC BIT(1) #define S1G_CAP1_RX_STBC BIT(2) #define S1G_CAP1_SU_BFER BIT(3) #define S1G_CAP1_SU_BFEE BIT(4) #define S1G_CAP1_BFEE_STS GENMASK(7, 5) #define S1G_CAP2_SOUNDING_DIMENSIONS GENMASK(2, 0) #define S1G_CAP2_MU_BFER BIT(3) #define S1G_CAP2_MU_BFEE BIT(4) #define S1G_CAP2_PLUS_HTC_VHT BIT(5) #define S1G_CAP2_TRAVELING_PILOT GENMASK(7, 6) #define S1G_CAP3_RD_RESPONDER BIT(0) #define S1G_CAP3_HT_DELAYED_BA BIT(1) #define S1G_CAP3_MAX_MPDU_LEN BIT(2) #define S1G_CAP3_MAX_AMPDU_LEN_EXP GENMASK(4, 3) #define S1G_CAP3_MIN_MPDU_START GENMASK(7, 5) #define S1G_CAP4_UPLINK_SYNC BIT(0) #define S1G_CAP4_DYNAMIC_AID BIT(1) #define S1G_CAP4_BAT BIT(2) #define S1G_CAP4_TIME_ADE BIT(3) #define S1G_CAP4_NON_TIM BIT(4) #define S1G_CAP4_GROUP_AID BIT(5) #define S1G_CAP4_STA_TYPE GENMASK(7, 6) #define S1G_CAP5_CENT_AUTH_CONTROL BIT(0) #define S1G_CAP5_DIST_AUTH_CONTROL BIT(1) #define S1G_CAP5_AMSDU BIT(2) #define S1G_CAP5_AMPDU BIT(3) #define S1G_CAP5_ASYMMETRIC_BA BIT(4) #define S1G_CAP5_FLOW_CONTROL BIT(5) #define S1G_CAP5_SECTORIZED_BEAM GENMASK(7, 6) #define S1G_CAP6_OBSS_MITIGATION BIT(0) #define S1G_CAP6_FRAGMENT_BA BIT(1) #define S1G_CAP6_NDP_PS_POLL BIT(2) #define S1G_CAP6_RAW_OPERATION BIT(3) #define S1G_CAP6_PAGE_SLICING BIT(4) #define S1G_CAP6_TXOP_SHARING_IMP_ACK BIT(5) #define S1G_CAP6_VHT_LINK_ADAPT GENMASK(7, 6) #define S1G_CAP7_TACK_AS_PS_POLL BIT(0) #define S1G_CAP7_DUP_1MHZ BIT(1) #define S1G_CAP7_MCS_NEGOTIATION BIT(2) #define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) #define S1G_CAP7_NDP_BFING_REPORT_POLL BIT(4) #define S1G_CAP7_UNSOLICITED_DYN_AID BIT(5) #define S1G_CAP7_SECTOR_TRAINING_OPERATION BIT(6) #define S1G_CAP7_TEMP_PS_MODE_SWITCH BIT(7) #define S1G_CAP8_TWT_GROUPING BIT(0) #define S1G_CAP8_BDT BIT(1) #define S1G_CAP8_COLOR GENMASK(4, 2) #define S1G_CAP8_TWT_REQUEST BIT(5) #define S1G_CAP8_TWT_RESPOND BIT(6) #define S1G_CAP8_PV1_FRAME BIT(7) #define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) /* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ #define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 #define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 #define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 #define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 #define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 #define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 #define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 #define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 #define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 #define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 #define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 /* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ #define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 #define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 #define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 #define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 #define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 #define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 /* EHT beamformee number of spatial streams <= 80MHz is split */ #define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 #define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 #define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c #define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 #define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 #define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 /* EHT number of sounding dimensions for 320MHz is split */ #define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 #define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 #define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 #define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 #define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 #define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 #define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 #define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 #define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 #define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 #define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 #define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 #define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 #define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 #define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 #define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 #define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 #define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 #define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 #define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 #define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 #define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 #define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 /* Maximum number of supported EHT LTF is split */ #define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 #define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 #define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 #define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 #define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 #define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 #define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 #define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 #define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 #define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 #define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 #define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 #define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 #define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 #define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 /* * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 */ #define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 #define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 #define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 #define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 #define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 #define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 /* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ static inline u8 ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, const struct ieee80211_eht_cap_elem_fixed *eht_cap, bool from_ap) { u8 count = 0; /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ if (he_cap->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) return 3; /* on 2.4 GHz, these three bits are reserved, so should be 0 */ if (he_cap->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) count += 3; if (he_cap->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) count += 3; if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) count += 3; if (count) return count; return from_ap ? 3 : 4; } /* 802.11be EHT PPE Thresholds */ #define IEEE80211_EHT_PPE_THRES_NSS_POS 0 #define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf #define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 #define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 #define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 /* * Calculate 802.11be EHT capabilities IE EHT field size */ static inline u8 ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) { u32 n; if (!(phy_cap_info[5] & IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) return 0; n = hweight16(ppe_thres_hdr & IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); /* * Each pair is 6 bits, and we need to add the 9 "header" bits to the * total size. */ n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; return DIV_ROUND_UP(n, 8); } static inline bool ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, bool from_ap) { const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); if (len < needed || !he_capa) return false; needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, (const void *)data, from_ap); if (len < needed) return false; if (elem->phy_cap_info[5] & IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { u16 ppe_thres_hdr; if (len < needed + sizeof(ppe_thres_hdr)) return false; ppe_thres_hdr = get_unaligned_le16(data + needed); needed += ieee80211_eht_ppe_size(ppe_thres_hdr, elem->phy_cap_info); } return len >= needed; } static inline bool ieee80211_eht_oper_size_ok(const u8 *data, u8 len) { const struct ieee80211_eht_operation *elem = (const void *)data; u8 needed = sizeof(*elem); if (len < needed) return false; if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { needed += 3; if (elem->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) needed += 2; } return len >= needed; } #define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) struct ieee80211_bandwidth_indication { u8 params; struct ieee80211_eht_operation_info info; } __packed; static inline bool ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) { const struct ieee80211_bandwidth_indication *bwi = (const void *)data; if (len < sizeof(*bwi)) return false; if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && len < sizeof(*bwi) + 2) return false; return true; } #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) #define IEEE80211_MAX_USF FIELD_MAX(LISTEN_INT_USF) #define IEEE80211_MAX_UI FIELD_MAX(LISTEN_INT_UI) /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 #define WLAN_AUTH_FILS_SK 4 #define WLAN_AUTH_FILS_SK_PFS 5 #define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 #define WLAN_CAPABILITY_ESS (1<<0) #define WLAN_CAPABILITY_IBSS (1<<1) /* * A mesh STA sets the ESS and IBSS capability bits to zero. * however, this holds true for p2p probe responses (in the p2p_find * phase) as well. */ #define WLAN_CAPABILITY_IS_STA_BSS(cap) \ (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS))) #define WLAN_CAPABILITY_CF_POLLABLE (1<<2) #define WLAN_CAPABILITY_CF_POLL_REQUEST (1<<3) #define WLAN_CAPABILITY_PRIVACY (1<<4) #define WLAN_CAPABILITY_SHORT_PREAMBLE (1<<5) #define WLAN_CAPABILITY_PBCC (1<<6) #define WLAN_CAPABILITY_CHANNEL_AGILITY (1<<7) /* 802.11h */ #define WLAN_CAPABILITY_SPECTRUM_MGMT (1<<8) #define WLAN_CAPABILITY_QOS (1<<9) #define WLAN_CAPABILITY_SHORT_SLOT_TIME (1<<10) #define WLAN_CAPABILITY_APSD (1<<11) #define WLAN_CAPABILITY_RADIO_MEASURE (1<<12) #define WLAN_CAPABILITY_DSSS_OFDM (1<<13) #define WLAN_CAPABILITY_DEL_BACK (1<<14) #define WLAN_CAPABILITY_IMM_BACK (1<<15) /* DMG (60gHz) 802.11ad */ /* type - bits 0..1 */ #define WLAN_CAPABILITY_DMG_TYPE_MASK (3<<0) #define WLAN_CAPABILITY_DMG_TYPE_IBSS (1<<0) /* Tx by: STA */ #define WLAN_CAPABILITY_DMG_TYPE_PBSS (2<<0) /* Tx by: PCP */ #define WLAN_CAPABILITY_DMG_TYPE_AP (3<<0) /* Tx by: AP */ #define WLAN_CAPABILITY_DMG_CBAP_ONLY (1<<2) #define WLAN_CAPABILITY_DMG_CBAP_SOURCE (1<<3) #define WLAN_CAPABILITY_DMG_PRIVACY (1<<4) #define WLAN_CAPABILITY_DMG_ECPAC (1<<5) #define WLAN_CAPABILITY_DMG_SPECTRUM_MGMT (1<<8) #define WLAN_CAPABILITY_DMG_RADIO_MEASURE (1<<12) /* measurement */ #define IEEE80211_SPCT_MSR_RPRT_MODE_LATE (1<<0) #define IEEE80211_SPCT_MSR_RPRT_MODE_INCAPABLE (1<<1) #define IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED (1<<2) #define IEEE80211_SPCT_MSR_RPRT_TYPE_BASIC 0 #define IEEE80211_SPCT_MSR_RPRT_TYPE_CCA 1 #define IEEE80211_SPCT_MSR_RPRT_TYPE_RPI 2 #define IEEE80211_SPCT_MSR_RPRT_TYPE_LCI 8 #define IEEE80211_SPCT_MSR_RPRT_TYPE_CIVIC 11 /* 802.11g ERP information element */ #define WLAN_ERP_NON_ERP_PRESENT (1<<0) #define WLAN_ERP_USE_PROTECTION (1<<1) #define WLAN_ERP_BARKER_PREAMBLE (1<<2) /* WLAN_ERP_BARKER_PREAMBLE values */ enum { WLAN_ERP_PREAMBLE_SHORT = 0, WLAN_ERP_PREAMBLE_LONG = 1, }; /* Band ID, 802.11ad #8.4.1.45 */ enum { IEEE80211_BANDID_TV_WS = 0, /* TV white spaces */ IEEE80211_BANDID_SUB1 = 1, /* Sub-1 GHz (excluding TV white spaces) */ IEEE80211_BANDID_2G = 2, /* 2.4 GHz */ IEEE80211_BANDID_3G = 3, /* 3.6 GHz */ IEEE80211_BANDID_5G = 4, /* 4.9 and 5 GHz */ IEEE80211_BANDID_60G = 5, /* 60 GHz */ }; /* Status codes */ enum ieee80211_statuscode { WLAN_STATUS_SUCCESS = 0, WLAN_STATUS_UNSPECIFIED_FAILURE = 1, WLAN_STATUS_CAPS_UNSUPPORTED = 10, WLAN_STATUS_REASSOC_NO_ASSOC = 11, WLAN_STATUS_ASSOC_DENIED_UNSPEC = 12, WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG = 13, WLAN_STATUS_UNKNOWN_AUTH_TRANSACTION = 14, WLAN_STATUS_CHALLENGE_FAIL = 15, WLAN_STATUS_AUTH_TIMEOUT = 16, WLAN_STATUS_AP_UNABLE_TO_HANDLE_NEW_STA = 17, WLAN_STATUS_ASSOC_DENIED_RATES = 18, /* 802.11b */ WLAN_STATUS_ASSOC_DENIED_NOSHORTPREAMBLE = 19, WLAN_STATUS_ASSOC_DENIED_NOPBCC = 20, WLAN_STATUS_ASSOC_DENIED_NOAGILITY = 21, /* 802.11h */ WLAN_STATUS_ASSOC_DENIED_NOSPECTRUM = 22, WLAN_STATUS_ASSOC_REJECTED_BAD_POWER = 23, WLAN_STATUS_ASSOC_REJECTED_BAD_SUPP_CHAN = 24, /* 802.11g */ WLAN_STATUS_ASSOC_DENIED_NOSHORTTIME = 25, WLAN_STATUS_ASSOC_DENIED_NODSSSOFDM = 26, /* 802.11w */ WLAN_STATUS_ASSOC_REJECTED_TEMPORARILY = 30, WLAN_STATUS_ROBUST_MGMT_FRAME_POLICY_VIOLATION = 31, /* 802.11i */ WLAN_STATUS_INVALID_IE = 40, WLAN_STATUS_INVALID_GROUP_CIPHER = 41, WLAN_STATUS_INVALID_PAIRWISE_CIPHER = 42, WLAN_STATUS_INVALID_AKMP = 43, WLAN_STATUS_UNSUPP_RSN_VERSION = 44, WLAN_STATUS_INVALID_RSN_IE_CAP = 45, WLAN_STATUS_CIPHER_SUITE_REJECTED = 46, /* 802.11e */ WLAN_STATUS_UNSPECIFIED_QOS = 32, WLAN_STATUS_ASSOC_DENIED_NOBANDWIDTH = 33, WLAN_STATUS_ASSOC_DENIED_LOWACK = 34, WLAN_STATUS_ASSOC_DENIED_UNSUPP_QOS = 35, WLAN_STATUS_REQUEST_DECLINED = 37, WLAN_STATUS_INVALID_QOS_PARAM = 38, WLAN_STATUS_CHANGE_TSPEC = 39, WLAN_STATUS_WAIT_TS_DELAY = 47, WLAN_STATUS_NO_DIRECT_LINK = 48, WLAN_STATUS_STA_NOT_PRESENT = 49, WLAN_STATUS_STA_NOT_QSTA = 50, /* 802.11s */ WLAN_STATUS_ANTI_CLOG_REQUIRED = 76, WLAN_STATUS_FCG_NOT_SUPP = 78, WLAN_STATUS_STA_NO_TBTT = 78, /* 802.11ad */ WLAN_STATUS_REJECTED_WITH_SUGGESTED_CHANGES = 39, WLAN_STATUS_REJECTED_FOR_DELAY_PERIOD = 47, WLAN_STATUS_REJECT_WITH_SCHEDULE = 83, WLAN_STATUS_PENDING_ADMITTING_FST_SESSION = 86, WLAN_STATUS_PERFORMING_FST_NOW = 87, WLAN_STATUS_PENDING_GAP_IN_BA_WINDOW = 88, WLAN_STATUS_REJECT_U_PID_SETTING = 89, WLAN_STATUS_REJECT_DSE_BAND = 96, WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, /* 802.11ai */ WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, WLAN_STATUS_SAE_PK = 127, }; /* Reason codes */ enum ieee80211_reasoncode { WLAN_REASON_UNSPECIFIED = 1, WLAN_REASON_PREV_AUTH_NOT_VALID = 2, WLAN_REASON_DEAUTH_LEAVING = 3, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY = 4, WLAN_REASON_DISASSOC_AP_BUSY = 5, WLAN_REASON_CLASS2_FRAME_FROM_NONAUTH_STA = 6, WLAN_REASON_CLASS3_FRAME_FROM_NONASSOC_STA = 7, WLAN_REASON_DISASSOC_STA_HAS_LEFT = 8, WLAN_REASON_STA_REQ_ASSOC_WITHOUT_AUTH = 9, /* 802.11h */ WLAN_REASON_DISASSOC_BAD_POWER = 10, WLAN_REASON_DISASSOC_BAD_SUPP_CHAN = 11, /* 802.11i */ WLAN_REASON_INVALID_IE = 13, WLAN_REASON_MIC_FAILURE = 14, WLAN_REASON_4WAY_HANDSHAKE_TIMEOUT = 15, WLAN_REASON_GROUP_KEY_HANDSHAKE_TIMEOUT = 16, WLAN_REASON_IE_DIFFERENT = 17, WLAN_REASON_INVALID_GROUP_CIPHER = 18, WLAN_REASON_INVALID_PAIRWISE_CIPHER = 19, WLAN_REASON_INVALID_AKMP = 20, WLAN_REASON_UNSUPP_RSN_VERSION = 21, WLAN_REASON_INVALID_RSN_IE_CAP = 22, WLAN_REASON_IEEE8021X_FAILED = 23, WLAN_REASON_CIPHER_SUITE_REJECTED = 24, /* TDLS (802.11z) */ WLAN_REASON_TDLS_TEARDOWN_UNREACHABLE = 25, WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED = 26, /* 802.11e */ WLAN_REASON_DISASSOC_UNSPECIFIED_QOS = 32, WLAN_REASON_DISASSOC_QAP_NO_BANDWIDTH = 33, WLAN_REASON_DISASSOC_LOW_ACK = 34, WLAN_REASON_DISASSOC_QAP_EXCEED_TXOP = 35, WLAN_REASON_QSTA_LEAVE_QBSS = 36, WLAN_REASON_QSTA_NOT_USE = 37, WLAN_REASON_QSTA_REQUIRE_SETUP = 38, WLAN_REASON_QSTA_TIMEOUT = 39, WLAN_REASON_QSTA_CIPHER_NOT_SUPP = 45, /* 802.11s */ WLAN_REASON_MESH_PEER_CANCELED = 52, WLAN_REASON_MESH_MAX_PEERS = 53, WLAN_REASON_MESH_CONFIG = 54, WLAN_REASON_MESH_CLOSE = 55, WLAN_REASON_MESH_MAX_RETRIES = 56, WLAN_REASON_MESH_CONFIRM_TIMEOUT = 57, WLAN_REASON_MESH_INVALID_GTK = 58, WLAN_REASON_MESH_INCONSISTENT_PARAM = 59, WLAN_REASON_MESH_INVALID_SECURITY = 60, WLAN_REASON_MESH_PATH_ERROR = 61, WLAN_REASON_MESH_PATH_NOFORWARD = 62, WLAN_REASON_MESH_PATH_DEST_UNREACHABLE = 63, WLAN_REASON_MAC_EXISTS_IN_MBSS = 64, WLAN_REASON_MESH_CHAN_REGULATORY = 65, WLAN_REASON_MESH_CHAN = 66, }; /* Information Element IDs */ enum ieee80211_eid { WLAN_EID_SSID = 0, WLAN_EID_SUPP_RATES = 1, WLAN_EID_FH_PARAMS = 2, /* reserved now */ WLAN_EID_DS_PARAMS = 3, WLAN_EID_CF_PARAMS = 4, WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_COUNTRY = 7, /* 8, 9 reserved */ WLAN_EID_REQUEST = 10, WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, WLAN_EID_TSPEC = 13, WLAN_EID_TCLAS = 14, WLAN_EID_SCHEDULE = 15, WLAN_EID_CHALLENGE = 16, /* 17-31 reserved for challenge text extension */ WLAN_EID_PWR_CONSTRAINT = 32, WLAN_EID_PWR_CAPABILITY = 33, WLAN_EID_TPC_REQUEST = 34, WLAN_EID_TPC_REPORT = 35, WLAN_EID_SUPPORTED_CHANNELS = 36, WLAN_EID_CHANNEL_SWITCH = 37, WLAN_EID_MEASURE_REQUEST = 38, WLAN_EID_MEASURE_REPORT = 39, WLAN_EID_QUIET = 40, WLAN_EID_IBSS_DFS = 41, WLAN_EID_ERP_INFO = 42, WLAN_EID_TS_DELAY = 43, WLAN_EID_TCLAS_PROCESSING = 44, WLAN_EID_HT_CAPABILITY = 45, WLAN_EID_QOS_CAPA = 46, /* 47 reserved for Broadcom */ WLAN_EID_RSN = 48, WLAN_EID_802_15_COEX = 49, WLAN_EID_EXT_SUPP_RATES = 50, WLAN_EID_AP_CHAN_REPORT = 51, WLAN_EID_NEIGHBOR_REPORT = 52, WLAN_EID_RCPI = 53, WLAN_EID_MOBILITY_DOMAIN = 54, WLAN_EID_FAST_BSS_TRANSITION = 55, WLAN_EID_TIMEOUT_INTERVAL = 56, WLAN_EID_RIC_DATA = 57, WLAN_EID_DSE_REGISTERED_LOCATION = 58, WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59, WLAN_EID_EXT_CHANSWITCH_ANN = 60, WLAN_EID_HT_OPERATION = 61, WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, WLAN_EID_BSS_AVG_ACCESS_DELAY = 63, WLAN_EID_ANTENNA_INFO = 64, WLAN_EID_RSNI = 65, WLAN_EID_MEASUREMENT_PILOT_TX_INFO = 66, WLAN_EID_BSS_AVAILABLE_CAPACITY = 67, WLAN_EID_BSS_AC_ACCESS_DELAY = 68, WLAN_EID_TIME_ADVERTISEMENT = 69, WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, WLAN_EID_BSS_COEX_2040 = 72, WLAN_EID_BSS_INTOLERANT_CHL_REPORT = 73, WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, WLAN_EID_RIC_DESCRIPTOR = 75, WLAN_EID_MMIE = 76, WLAN_EID_ASSOC_COMEBACK_TIME = 77, WLAN_EID_EVENT_REQUEST = 78, WLAN_EID_EVENT_REPORT = 79, WLAN_EID_DIAGNOSTIC_REQUEST = 80, WLAN_EID_DIAGNOSTIC_REPORT = 81, WLAN_EID_LOCATION_PARAMS = 82, WLAN_EID_NON_TX_BSSID_CAP = 83, WLAN_EID_SSID_LIST = 84, WLAN_EID_MULTI_BSSID_IDX = 85, WLAN_EID_FMS_DESCRIPTOR = 86, WLAN_EID_FMS_REQUEST = 87, WLAN_EID_FMS_RESPONSE = 88, WLAN_EID_QOS_TRAFFIC_CAPA = 89, WLAN_EID_BSS_MAX_IDLE_PERIOD = 90, WLAN_EID_TSF_REQUEST = 91, WLAN_EID_TSF_RESPOSNE = 92, WLAN_EID_WNM_SLEEP_MODE = 93, WLAN_EID_TIM_BCAST_REQ = 94, WLAN_EID_TIM_BCAST_RESP = 95, WLAN_EID_COLL_IF_REPORT = 96, WLAN_EID_CHANNEL_USAGE = 97, WLAN_EID_TIME_ZONE = 98, WLAN_EID_DMS_REQUEST = 99, WLAN_EID_DMS_RESPONSE = 100, WLAN_EID_LINK_ID = 101, WLAN_EID_WAKEUP_SCHEDUL = 102, /* 103 reserved */ WLAN_EID_CHAN_SWITCH_TIMING = 104, WLAN_EID_PTI_CONTROL = 105, WLAN_EID_PU_BUFFER_STATUS = 106, WLAN_EID_INTERWORKING = 107, WLAN_EID_ADVERTISEMENT_PROTOCOL = 108, WLAN_EID_EXPEDITED_BW_REQ = 109, WLAN_EID_QOS_MAP_SET = 110, WLAN_EID_ROAMING_CONSORTIUM = 111, WLAN_EID_EMERGENCY_ALERT = 112, WLAN_EID_MESH_CONFIG = 113, WLAN_EID_MESH_ID = 114, WLAN_EID_LINK_METRIC_REPORT = 115, WLAN_EID_CONGESTION_NOTIFICATION = 116, WLAN_EID_PEER_MGMT = 117, WLAN_EID_CHAN_SWITCH_PARAM = 118, WLAN_EID_MESH_AWAKE_WINDOW = 119, WLAN_EID_BEACON_TIMING = 120, WLAN_EID_MCCAOP_SETUP_REQ = 121, WLAN_EID_MCCAOP_SETUP_RESP = 122, WLAN_EID_MCCAOP_ADVERT = 123, WLAN_EID_MCCAOP_TEARDOWN = 124, WLAN_EID_GANN = 125, WLAN_EID_RANN = 126, WLAN_EID_EXT_CAPABILITY = 127, /* 128, 129 reserved for Agere */ WLAN_EID_PREQ = 130, WLAN_EID_PREP = 131, WLAN_EID_PERR = 132, /* 133-136 reserved for Cisco */ WLAN_EID_PXU = 137, WLAN_EID_PXUC = 138, WLAN_EID_AUTH_MESH_PEER_EXCH = 139, WLAN_EID_MIC = 140, WLAN_EID_DESTINATION_URI = 141, WLAN_EID_UAPSD_COEX = 142, WLAN_EID_WAKEUP_SCHEDULE = 143, WLAN_EID_EXT_SCHEDULE = 144, WLAN_EID_STA_AVAILABILITY = 145, WLAN_EID_DMG_TSPEC = 146, WLAN_EID_DMG_AT = 147, WLAN_EID_DMG_CAP = 148, /* 149 reserved for Cisco */ WLAN_EID_CISCO_VENDOR_SPECIFIC = 150, WLAN_EID_DMG_OPERATION = 151, WLAN_EID_DMG_BSS_PARAM_CHANGE = 152, WLAN_EID_DMG_BEAM_REFINEMENT = 153, WLAN_EID_CHANNEL_MEASURE_FEEDBACK = 154, /* 155-156 reserved for Cisco */ WLAN_EID_AWAKE_WINDOW = 157, WLAN_EID_MULTI_BAND = 158, WLAN_EID_ADDBA_EXT = 159, WLAN_EID_NEXT_PCP_LIST = 160, WLAN_EID_PCP_HANDOVER = 161, WLAN_EID_DMG_LINK_MARGIN = 162, WLAN_EID_SWITCHING_STREAM = 163, WLAN_EID_SESSION_TRANSITION = 164, WLAN_EID_DYN_TONE_PAIRING_REPORT = 165, WLAN_EID_CLUSTER_REPORT = 166, WLAN_EID_RELAY_CAP = 167, WLAN_EID_RELAY_XFER_PARAM_SET = 168, WLAN_EID_BEAM_LINK_MAINT = 169, WLAN_EID_MULTIPLE_MAC_ADDR = 170, WLAN_EID_U_PID = 171, WLAN_EID_DMG_LINK_ADAPT_ACK = 172, /* 173 reserved for Symbol */ WLAN_EID_MCCAOP_ADV_OVERVIEW = 174, WLAN_EID_QUIET_PERIOD_REQ = 175, /* 176 reserved for Symbol */ WLAN_EID_QUIET_PERIOD_RESP = 177, /* 178-179 reserved for Symbol */ /* 180 reserved for ISO/IEC 20011 */ WLAN_EID_EPAC_POLICY = 182, WLAN_EID_CLISTER_TIME_OFF = 183, WLAN_EID_INTER_AC_PRIO = 184, WLAN_EID_SCS_DESCRIPTOR = 185, WLAN_EID_QLOAD_REPORT = 186, WLAN_EID_HCCA_TXOP_UPDATE_COUNT = 187, WLAN_EID_HL_STREAM_ID = 188, WLAN_EID_GCR_GROUP_ADDR = 189, WLAN_EID_ANTENNA_SECTOR_ID_PATTERN = 190, WLAN_EID_VHT_CAPABILITY = 191, WLAN_EID_VHT_OPERATION = 192, WLAN_EID_EXTENDED_BSS_LOAD = 193, WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, WLAN_EID_TX_POWER_ENVELOPE = 195, WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, WLAN_EID_AID = 197, WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201, WLAN_EID_AID_REQUEST = 210, WLAN_EID_AID_RESPONSE = 211, WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, WLAN_EID_S1G_TWT = 216, WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, WLAN_EID_S1G_OPERATION = 232, WLAN_EID_CAG_NUMBER = 237, WLAN_EID_AP_CSN = 239, WLAN_EID_FILS_INDICATION = 240, WLAN_EID_DILS = 241, WLAN_EID_FRAGMENT = 242, WLAN_EID_RSNX = 244, WLAN_EID_EXTENSION = 255 }; /* Element ID Extensions for Element ID 255 */ enum ieee80211_eid_ext { WLAN_EID_EXT_ASSOC_DELAY_INFO = 1, WLAN_EID_EXT_FILS_REQ_PARAMS = 2, WLAN_EID_EXT_FILS_KEY_CONFIRM = 3, WLAN_EID_EXT_FILS_SESSION = 4, WLAN_EID_EXT_FILS_HLP_CONTAINER = 5, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN = 6, WLAN_EID_EXT_KEY_DELIVERY = 7, WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, WLAN_EID_EXT_FILS_NONCE = 13, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14, WLAN_EID_EXT_HE_CAPABILITY = 35, WLAN_EID_EXT_HE_OPERATION = 36, WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_HE_SPR = 39, WLAN_EID_EXT_NDP_FEEDBACK_REPORT_PARAMSET = 41, WLAN_EID_EXT_BSS_COLOR_CHG_ANN = 42, WLAN_EID_EXT_QUIET_TIME_PERIOD_SETUP = 43, WLAN_EID_EXT_ESS_REPORT = 45, WLAN_EID_EXT_OPS = 46, WLAN_EID_EXT_HE_BSS_LOAD = 47, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, WLAN_EID_EXT_KNOWN_BSSID = 57, WLAN_EID_EXT_SHORT_SSID_LIST = 58, WLAN_EID_EXT_HE_6GHZ_CAPA = 59, WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, WLAN_EID_EXT_EHT_OPERATION = 106, WLAN_EID_EXT_EHT_MULTI_LINK = 107, WLAN_EID_EXT_EHT_CAPABILITY = 108, WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109, WLAN_EID_EXT_BANDWIDTH_INDICATION = 135, }; /* Action category code */ enum ieee80211_category { WLAN_CATEGORY_SPECTRUM_MGMT = 0, WLAN_CATEGORY_QOS = 1, WLAN_CATEGORY_DLS = 2, WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, WLAN_CATEGORY_WNM = 10, WLAN_CATEGORY_WNM_UNPROTECTED = 11, WLAN_CATEGORY_TDLS = 12, WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, WLAN_CATEGORY_SELF_PROTECTED = 15, WLAN_CATEGORY_DMG = 16, WLAN_CATEGORY_WMM = 17, WLAN_CATEGORY_FST = 18, WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VHT = 21, WLAN_CATEGORY_S1G = 22, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; /* SPECTRUM_MGMT action code */ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_MSR_REQ = 0, WLAN_ACTION_SPCT_MSR_RPRT = 1, WLAN_ACTION_SPCT_TPC_REQ = 2, WLAN_ACTION_SPCT_TPC_RPRT = 3, WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; /* HT action codes */ enum ieee80211_ht_actioncode { WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, WLAN_HT_ACTION_SMPS = 1, WLAN_HT_ACTION_PSMP = 2, WLAN_HT_ACTION_PCO_PHASE = 3, WLAN_HT_ACTION_CSI = 4, WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, WLAN_HT_ACTION_COMPRESSED_BF = 6, WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, }; /* VHT action codes */ enum ieee80211_vht_actioncode { WLAN_VHT_ACTION_COMPRESSED_BF = 0, WLAN_VHT_ACTION_GROUPID_MGMT = 1, WLAN_VHT_ACTION_OPMODE_NOTIF = 2, }; /* Self Protected Action codes */ enum ieee80211_self_protected_actioncode { WLAN_SP_RESERVED = 0, WLAN_SP_MESH_PEERING_OPEN = 1, WLAN_SP_MESH_PEERING_CONFIRM = 2, WLAN_SP_MESH_PEERING_CLOSE = 3, WLAN_SP_MGK_INFORM = 4, WLAN_SP_MGK_ACK = 5, }; /* Mesh action codes */ enum ieee80211_mesh_actioncode { WLAN_MESH_ACTION_LINK_METRIC_REPORT, WLAN_MESH_ACTION_HWMP_PATH_SELECTION, WLAN_MESH_ACTION_GATE_ANNOUNCEMENT, WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION, WLAN_MESH_ACTION_MCCA_SETUP_REQUEST, WLAN_MESH_ACTION_MCCA_SETUP_REPLY, WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST, WLAN_MESH_ACTION_MCCA_ADVERTISEMENT, WLAN_MESH_ACTION_MCCA_TEARDOWN, WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST, WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, }; /* Unprotected WNM action codes */ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIM = 0, WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, WLAN_KEY_LEN_WEP104 = 13, WLAN_KEY_LEN_CCMP = 16, WLAN_KEY_LEN_CCMP_256 = 32, WLAN_KEY_LEN_TKIP = 32, WLAN_KEY_LEN_AES_CMAC = 16, WLAN_KEY_LEN_SMS4 = 32, WLAN_KEY_LEN_GCMP = 16, WLAN_KEY_LEN_GCMP_256 = 32, WLAN_KEY_LEN_BIP_CMAC_256 = 32, WLAN_KEY_LEN_BIP_GMAC_128 = 16, WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; enum ieee80211_s1g_actioncode { WLAN_S1G_AID_SWITCH_REQUEST, WLAN_S1G_AID_SWITCH_RESPONSE, WLAN_S1G_SYNC_CONTROL, WLAN_S1G_STA_INFO_ANNOUNCE, WLAN_S1G_EDCA_PARAM_SET, WLAN_S1G_EL_OPERATION, WLAN_S1G_TWT_SETUP, WLAN_S1G_TWT_TEARDOWN, WLAN_S1G_SECT_GROUP_ID_LIST, WLAN_S1G_SECT_ID_FEEDBACK, WLAN_S1G_TWT_INFORMATION = 11, }; #define IEEE80211_WEP_IV_LEN 4 #define IEEE80211_WEP_ICV_LEN 4 #define IEEE80211_CCMP_HDR_LEN 8 #define IEEE80211_CCMP_MIC_LEN 8 #define IEEE80211_CCMP_PN_LEN 6 #define IEEE80211_CCMP_256_HDR_LEN 8 #define IEEE80211_CCMP_256_MIC_LEN 16 #define IEEE80211_CCMP_256_PN_LEN 6 #define IEEE80211_TKIP_IV_LEN 8 #define IEEE80211_TKIP_ICV_LEN 4 #define IEEE80211_CMAC_PN_LEN 6 #define IEEE80211_GMAC_PN_LEN 6 #define IEEE80211_GCMP_HDR_LEN 8 #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 #define FILS_NONCE_LEN 16 #define FILS_MAX_KEK_LEN 64 #define FILS_ERP_MAX_USERNAME_LEN 16 #define FILS_ERP_MAX_REALM_LEN 253 #define FILS_ERP_MAX_RRK_LEN 64 #define PMK_MAX_LEN 64 #define SAE_PASSWORD_MAX_LEN 128 /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_20_40_BSS_COEX = 0, WLAN_PUB_ACTION_DSE_ENABLEMENT = 1, WLAN_PUB_ACTION_DSE_DEENABLEMENT = 2, WLAN_PUB_ACTION_DSE_REG_LOC_ANN = 3, WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, WLAN_PUB_ACTION_DSE_MSMT_REQ = 5, WLAN_PUB_ACTION_DSE_MSMT_RESP = 6, WLAN_PUB_ACTION_MSMT_PILOT = 7, WLAN_PUB_ACTION_DSE_PC = 8, WLAN_PUB_ACTION_VENDOR_SPECIFIC = 9, WLAN_PUB_ACTION_GAS_INITIAL_REQ = 10, WLAN_PUB_ACTION_GAS_INITIAL_RESP = 11, WLAN_PUB_ACTION_GAS_COMEBACK_REQ = 12, WLAN_PUB_ACTION_GAS_COMEBACK_RESP = 13, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, WLAN_PUB_ACTION_LOC_TRACK_NOTI = 15, WLAN_PUB_ACTION_QAB_REQUEST_FRAME = 16, WLAN_PUB_ACTION_QAB_RESPONSE_FRAME = 17, WLAN_PUB_ACTION_QMF_POLICY = 18, WLAN_PUB_ACTION_QMF_POLICY_CHANGE = 19, WLAN_PUB_ACTION_QLOAD_REQUEST = 20, WLAN_PUB_ACTION_QLOAD_REPORT = 21, WLAN_PUB_ACTION_HCCA_TXOP_ADVERT = 22, WLAN_PUB_ACTION_HCCA_TXOP_RESPONSE = 23, WLAN_PUB_ACTION_PUBLIC_KEY = 24, WLAN_PUB_ACTION_CHANNEL_AVAIL_QUERY = 25, WLAN_PUB_ACTION_CHANNEL_SCHEDULE_MGMT = 26, WLAN_PUB_ACTION_CONTACT_VERI_SIGNAL = 27, WLAN_PUB_ACTION_GDD_ENABLEMENT_REQ = 28, WLAN_PUB_ACTION_GDD_ENABLEMENT_RESP = 29, WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, WLAN_PUB_ACTION_FTM_REQUEST = 32, WLAN_PUB_ACTION_FTM_RESPONSE = 33, WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; /* TDLS action codes */ enum ieee80211_tdls_actioncode { WLAN_TDLS_SETUP_REQUEST = 0, WLAN_TDLS_SETUP_RESPONSE = 1, WLAN_TDLS_SETUP_CONFIRM = 2, WLAN_TDLS_TEARDOWN = 3, WLAN_TDLS_PEER_TRAFFIC_INDICATION = 4, WLAN_TDLS_CHANNEL_SWITCH_REQUEST = 5, WLAN_TDLS_CHANNEL_SWITCH_RESPONSE = 6, WLAN_TDLS_PEER_PSM_REQUEST = 7, WLAN_TDLS_PEER_PSM_RESPONSE = 8, WLAN_TDLS_PEER_TRAFFIC_RESPONSE = 9, WLAN_TDLS_DISCOVERY_REQUEST = 10, }; /* Extended Channel Switching capability to be set in the 1st byte of * the @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING BIT(2) /* Multiple BSSID capability is set in the 6th bit of 3rd byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) /* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte * of the @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) #define WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH BIT(6) /* Interworking capabilities are set in 7th bit of 4th byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA4_INTERWORKING_ENABLED BIT(7) /* * TDLS capabililites to be enabled in the 5th byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA5_TDLS_ENABLED BIT(5) #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7) #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) /* Defines the maximal number of MSDUs in an A-MSDU. */ #define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) #define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) /* * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY * information element */ #define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) /* Defines support for TWT Requester and TWT Responder */ #define WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT BIT(5) #define WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT BIT(6) /* * When set, indicates that the AP is able to tolerate 26-tone RU UL * OFDMA transmissions using HE TB PPDU from OBSS (not falsely classify the * 26-tone RU UL OFDMA transmissions as radar pulses). */ #define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) /* Defines support for enhanced multi-bssid advertisement*/ #define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(3) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 /* BSS Coex IE information field bits */ #define WLAN_BSS_COEX_INFORMATION_REQUEST BIT(0) /** * enum ieee80211_mesh_sync_method - mesh synchronization method identifier * * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method * that will be specified in a vendor specific information element */ enum ieee80211_mesh_sync_method { IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, IEEE80211_SYNC_METHOD_VENDOR = 255, }; /** * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier * * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will * be specified in a vendor specific information element */ enum ieee80211_mesh_path_protocol { IEEE80211_PATH_PROTOCOL_HWMP = 1, IEEE80211_PATH_PROTOCOL_VENDOR = 255, }; /** * enum ieee80211_mesh_path_metric - mesh path selection metric identifier * * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be * specified in a vendor specific information element */ enum ieee80211_mesh_path_metric { IEEE80211_PATH_METRIC_AIRTIME = 1, IEEE80211_PATH_METRIC_VENDOR = 255, }; /** * enum ieee80211_root_mode_identifier - root mesh STA mode identifier * * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode * * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than * this value * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports * the proactive PREQ with proactive PREP subfield set to 0 * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA * supports the proactive PREQ with proactive PREP subfield set to 1 * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports * the proactive RANN */ enum ieee80211_root_mode_identifier { IEEE80211_ROOTMODE_NO_ROOT = 0, IEEE80211_ROOTMODE_ROOT = 1, IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, IEEE80211_PROACTIVE_RANN = 4, }; /* * IEEE 802.11-2007 7.3.2.9 Country information element * * Minimum length is 8 octets, ie len must be evenly * divisible by 2 */ /* Although the spec says 8 I'm seeing 6 in practice */ #define IEEE80211_COUNTRY_IE_MIN_LEN 6 /* The Country String field of the element shall be 3 octets in length */ #define IEEE80211_COUNTRY_STRING_LEN 3 /* * For regulatory extension stuff see IEEE 802.11-2007 * Annex I (page 1141) and Annex J (page 1147). Also * review 7.3.2.9. * * When dot11RegulatoryClassesRequired is true and the * first_channel/reg_extension_id is >= 201 then the IE * compromises of the 'ext' struct represented below: * * - Regulatory extension ID - when generating IE this just needs * to be monotonically increasing for each triplet passed in * the IE * - Regulatory class - index into set of rules * - Coverage class - index into air propagation time (Table 7-27), * in microseconds, you can compute the air propagation time from * the index by multiplying by 3, so index 10 yields a propagation * of 10 us. Valid values are 0-31, values 32-255 are not defined * yet. A value of 0 inicates air propagation of <= 1 us. * * See also Table I.2 for Emission limit sets and table * I.3 for Behavior limit sets. Table J.1 indicates how to map * a reg_class to an emission limit set and behavior limit set. */ #define IEEE80211_COUNTRY_EXTENSION_ID 201 /* * Channels numbers in the IE must be monotonically increasing * if dot11RegulatoryClassesRequired is not true. * * If dot11RegulatoryClassesRequired is true consecutive * subband triplets following a regulatory triplet shall * have monotonically increasing first_channel number fields. * * Channel numbers shall not overlap. * * Note that max_power is signed. */ struct ieee80211_country_ie_triplet { union { struct { u8 first_channel; u8 num_channels; s8 max_power; } __packed chans; struct { u8 reg_extension_id; u8 reg_class; u8 coverage_class; } __packed ext; }; } __packed; enum ieee80211_timeout_interval_type { WLAN_TIMEOUT_REASSOC_DEADLINE = 1 /* 802.11r */, WLAN_TIMEOUT_KEY_LIFETIME = 2 /* 802.11r */, WLAN_TIMEOUT_ASSOC_COMEBACK = 3 /* 802.11w */, }; /** * struct ieee80211_timeout_interval_ie - Timeout Interval element * @type: type, see &enum ieee80211_timeout_interval_type * @value: timeout interval value */ struct ieee80211_timeout_interval_ie { u8 type; __le32 value; } __packed; /** * enum ieee80211_idle_options - BSS idle options * @WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE: the station should send an RSN * protected frame to the AP to reset the idle timer at the AP for * the station. */ enum ieee80211_idle_options { WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE = BIT(0), }; /** * struct ieee80211_bss_max_idle_period_ie * * This structure refers to "BSS Max idle period element" * * @max_idle_period: indicates the time period during which a station can * refrain from transmitting frames to its associated AP without being * disassociated. In units of 1000 TUs. * @idle_options: indicates the options associated with the BSS idle capability * as specified in &enum ieee80211_idle_options. */ struct ieee80211_bss_max_idle_period_ie { __le16 max_idle_period; u8 idle_options; } __packed; /* BACK action code */ enum ieee80211_back_actioncode { WLAN_ACTION_ADDBA_REQ = 0, WLAN_ACTION_ADDBA_RESP = 1, WLAN_ACTION_DELBA = 2, }; /* BACK (block-ack) parties */ enum ieee80211_back_parties { WLAN_BACK_RECIPIENT = 0, WLAN_BACK_INITIATOR = 1, }; /* SA Query action */ enum ieee80211_sa_query_action { WLAN_ACTION_SA_QUERY_REQUEST = 0, WLAN_ACTION_SA_QUERY_RESPONSE = 1, }; /** * struct ieee80211_bssid_index * * This structure refers to "Multiple BSSID-index element" * * @bssid_index: BSSID index * @dtim_period: optional, overrides transmitted BSS dtim period * @dtim_count: optional, overrides transmitted BSS dtim count */ struct ieee80211_bssid_index { u8 bssid_index; u8 dtim_period; u8 dtim_count; }; /** * struct ieee80211_multiple_bssid_configuration * * This structure refers to "Multiple BSSID Configuration element" * * @bssid_count: total number of active BSSIDs in the set * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. */ struct ieee80211_multiple_bssid_configuration { u8 bssid_count; u8 profile_periodicity; }; #define SUITE(oui, id) (((oui) << 8) | (id)) /* cipher suite selectors */ #define WLAN_CIPHER_SUITE_USE_GROUP SUITE(0x000FAC, 0) #define WLAN_CIPHER_SUITE_WEP40 SUITE(0x000FAC, 1) #define WLAN_CIPHER_SUITE_TKIP SUITE(0x000FAC, 2) /* reserved: SUITE(0x000FAC, 3) */ #define WLAN_CIPHER_SUITE_CCMP SUITE(0x000FAC, 4) #define WLAN_CIPHER_SUITE_WEP104 SUITE(0x000FAC, 5) #define WLAN_CIPHER_SUITE_AES_CMAC SUITE(0x000FAC, 6) #define WLAN_CIPHER_SUITE_GCMP SUITE(0x000FAC, 8) #define WLAN_CIPHER_SUITE_GCMP_256 SUITE(0x000FAC, 9) #define WLAN_CIPHER_SUITE_CCMP_256 SUITE(0x000FAC, 10) #define WLAN_CIPHER_SUITE_BIP_GMAC_128 SUITE(0x000FAC, 11) #define WLAN_CIPHER_SUITE_BIP_GMAC_256 SUITE(0x000FAC, 12) #define WLAN_CIPHER_SUITE_BIP_CMAC_256 SUITE(0x000FAC, 13) #define WLAN_CIPHER_SUITE_SMS4 SUITE(0x001472, 1) /* AKM suite selectors */ #define WLAN_AKM_SUITE_8021X SUITE(0x000FAC, 1) #define WLAN_AKM_SUITE_PSK SUITE(0x000FAC, 2) #define WLAN_AKM_SUITE_FT_8021X SUITE(0x000FAC, 3) #define WLAN_AKM_SUITE_FT_PSK SUITE(0x000FAC, 4) #define WLAN_AKM_SUITE_8021X_SHA256 SUITE(0x000FAC, 5) #define WLAN_AKM_SUITE_PSK_SHA256 SUITE(0x000FAC, 6) #define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) #define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) #define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) #define WLAN_AKM_SUITE_AP_PEER_KEY SUITE(0x000FAC, 10) #define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11) #define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12) #define WLAN_AKM_SUITE_FT_8021X_SHA384 SUITE(0x000FAC, 13) #define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) #define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19) #define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20) #define WLAN_AKM_SUITE_WFA_DPP SUITE(WLAN_OUI_WFA, 2) #define WLAN_MAX_KEY_LEN 32 #define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 #define WLAN_PMK_LEN_EAP_LEAP 16 #define WLAN_PMK_LEN 32 #define WLAN_PMK_LEN_SUITE_B_192 48 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 #define WLAN_OUI_TYPE_WFA_DPP 0x1A #define WLAN_OUI_MICROSOFT 0x0050f2 #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 #define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element */ #define IEEE80211_WMM_IE_TSPEC_TID_MASK 0x0F #define IEEE80211_WMM_IE_TSPEC_TID_SHIFT 1 enum ieee80211_tspec_status_code { IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED = 0, IEEE80211_TSPEC_STATUS_ADDTS_INVAL_PARAMS = 0x1, }; struct ieee80211_tspec_ie { u8 element_id; u8 len; u8 oui[3]; u8 oui_type; u8 oui_subtype; u8 version; __le16 tsinfo; u8 tsinfo_resvd; __le16 nominal_msdu; __le16 max_msdu; __le32 min_service_int; __le32 max_service_int; __le32 inactivity_int; __le32 suspension_int; __le32 service_start_time; __le32 min_data_rate; __le32 mean_data_rate; __le32 peak_data_rate; __le32 max_burst_size; __le32 delay_bound; __le32 min_phy_rate; __le16 sba; __le16 medium_time; } __packed; struct ieee80211_he_6ghz_capa { /* uses IEEE80211_HE_6GHZ_CAP_* below */ __le16 capa; } __packed; /* HE 6 GHz band capabilities */ /* uses enum ieee80211_min_mpdu_spacing values */ #define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 /* uses enum ieee80211_vht_max_ampdu_length_exp values */ #define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 /* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ #define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 /* WLAN_HT_CAP_SM_PS_* values */ #define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 #define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 #define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 #define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame * * The qos ctrl bytes come after the frame_control, duration, seq_num * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose * between struct ieee80211_qos_hdr_4addr and struct ieee80211_qos_hdr. */ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) { union { struct ieee80211_qos_hdr addr3; struct ieee80211_qos_hdr_4addr addr4; } *qos; qos = (void *)hdr; if (ieee80211_has_a4(qos->addr3.frame_control)) return (u8 *)&qos->addr4.qos_ctrl; else return (u8 *)&qos->addr3.qos_ctrl; } /** * ieee80211_get_tid - get qos TID * @hdr: the frame */ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) { u8 *qc = ieee80211_get_qos_ctl(hdr); return qc[0] & IEEE80211_QOS_CTL_TID_MASK; } /** * ieee80211_get_SA - get pointer to SA * @hdr: the frame * * Given an 802.11 frame, this function returns the offset * to the source address (SA). It does not verify that the * header is long enough to contain the address, and the * header must be long enough to contain the frame control * field. */ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr) { if (ieee80211_has_a4(hdr->frame_control)) return hdr->addr4; if (ieee80211_has_fromds(hdr->frame_control)) return hdr->addr3; return hdr->addr2; } /** * ieee80211_get_DA - get pointer to DA * @hdr: the frame * * Given an 802.11 frame, this function returns the offset * to the destination address (DA). It does not verify that * the header is long enough to contain the address, and the * header must be long enough to contain the frame control * field. */ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) { if (ieee80211_has_tods(hdr->frame_control)) return hdr->addr3; else return hdr->addr1; } /** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @skb: the skb to check, starting with the 802.11 header */ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; __le16 fc = mgmt->frame_control; /* * IEEE 802.11 REVme D2.0 definition of bufferable MMPDU; * note that this ignores the IBSS special case. */ if (!ieee80211_is_mgmt(fc)) return false; if (ieee80211_is_disassoc(fc) || ieee80211_is_deauth(fc)) return true; if (!ieee80211_is_action(fc)) return false; if (skb->len < offsetofend(typeof(*mgmt), u.action.u.ftm.action_code)) return true; /* action frame - additionally check for non-bufferable FTM */ if (mgmt->u.action.category != WLAN_CATEGORY_PUBLIC && mgmt->u.action.category != WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION) return true; if (mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_REQUEST || mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_RESPONSE) return false; return true; } /** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) */ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) { if (ieee80211_is_disassoc(hdr->frame_control) || ieee80211_is_deauth(hdr->frame_control)) return true; if (ieee80211_is_action(hdr->frame_control)) { u8 *category; /* * Action frames, excluding Public Action frames, are Robust * Management Frames. However, if we are looking at a Protected * frame, skip the check since the data may be encrypted and * the frame has already been found to be a Robust Management * Frame (by the other end). */ if (ieee80211_has_protected(hdr->frame_control)) return true; category = ((u8 *) hdr) + 24; return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && *category != WLAN_CATEGORY_WNM_UNPROTECTED && *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && *category != WLAN_CATEGORY_S1G && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } return false; } /** * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame * @skb: the skb containing the frame, length will be checked */ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) { if (skb->len < IEEE80211_MIN_ACTION_SIZE) return false; return _ieee80211_is_robust_mgmt_frame((void *)skb->data); } /** * ieee80211_is_public_action - check if frame is a public action frame * @hdr: the frame * @len: length of the frame */ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, size_t len) { struct ieee80211_mgmt *mgmt = (void *)hdr; if (len < IEEE80211_MIN_ACTION_SIZE) return false; if (!ieee80211_is_action(hdr->frame_control)) return false; return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC; } /** * ieee80211_is_protected_dual_of_public_action - check if skb contains a * protected dual of public action management frame * @skb: the skb containing the frame, length will be checked * * Return: true if the skb contains a protected dual of public action * management frame, false otherwise. */ static inline bool ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) { u8 action; if (!ieee80211_is_public_action((void *)skb->data, skb->len) || skb->len < IEEE80211_MIN_ACTION_SIZE + 1) return false; action = *(u8 *)(skb->data + IEEE80211_MIN_ACTION_SIZE); return action != WLAN_PUB_ACTION_20_40_BSS_COEX && action != WLAN_PUB_ACTION_DSE_REG_LOC_ANN && action != WLAN_PUB_ACTION_MSMT_PILOT && action != WLAN_PUB_ACTION_TDLS_DISCOVER_RES && action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && action != WLAN_PUB_ACTION_FTM_REQUEST && action != WLAN_PUB_ACTION_FTM_RESPONSE && action != WLAN_PUB_ACTION_FILS_DISCOVERY && action != WLAN_PUB_ACTION_VENDOR_SPECIFIC; } /** * _ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @hdr: the frame */ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) { struct ieee80211_mgmt *mgmt = (void *)hdr; if (!ieee80211_is_action(hdr->frame_control) || !is_multicast_ether_addr(hdr->addr1)) return false; return mgmt->u.action.category == WLAN_CATEGORY_MESH_ACTION || mgmt->u.action.category == WLAN_CATEGORY_MULTIHOP_ACTION; } /** * ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @skb: the skb containing the frame, length will be checked */ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) { if (skb->len < IEEE80211_MIN_ACTION_SIZE) return false; return _ieee80211_is_group_privacy_action((void *)skb->data); } /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs */ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) { return 1024 * tu; } /** * ieee80211_check_tim - check if AID bit is set in TIM * @tim: the TIM IE * @tim_len: length of the TIM IE * @aid: the AID to look for */ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, u8 tim_len, u16 aid) { u8 mask; u8 index, indexn1, indexn2; if (unlikely(!tim || tim_len < sizeof(*tim))) return false; aid &= 0x3fff; index = aid / 8; mask = 1 << (aid & 7); indexn1 = tim->bitmap_ctrl & 0xfe; indexn2 = tim_len + indexn1 - 4; if (index < indexn1 || index > indexn2) return false; index -= indexn1; return !!(tim->virtual_map[index] & mask); } /** * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet) * @skb: the skb containing the frame, length will not be checked * * This function assumes the frame is a data frame, and that the network header * is in the correct place. */ static inline int ieee80211_get_tdls_action(struct sk_buff *skb) { if (!skb_is_nonlinear(skb) && skb->len > (skb_network_offset(skb) + 2)) { /* Point to where the indication of TDLS should start */ const u8 *tdls_data = skb_network_header(skb) - 2; if (get_unaligned_be16(tdls_data) == ETH_P_TDLS && tdls_data[2] == WLAN_TDLS_SNAP_RFTYPE && tdls_data[3] == WLAN_CATEGORY_TDLS) return tdls_data[4]; } return -1; } /* convert time units */ #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) /* convert frequencies */ #define MHZ_TO_KHZ(freq) ((freq) * 1000) #define KHZ_TO_MHZ(freq) ((freq) / 1000) #define PR_KHZ(f) KHZ_TO_MHZ(f), f % 1000 #define KHZ_F "%d.%03d" /* convert powers */ #define DBI_TO_MBI(gain) ((gain) * 100) #define MBI_TO_DBI(gain) ((gain) / 100) #define DBM_TO_MBM(gain) ((gain) * 100) #define MBM_TO_DBM(gain) ((gain) / 100) /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked * * This function checks if it's either TPC report action frame or Link * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5 * and 8.5.7.5 accordingly. */ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (!ieee80211_is_action(mgmt->frame_control)) return false; if (skb->len < IEEE80211_MIN_ACTION_SIZE + sizeof(mgmt->u.action.u.tpc_report)) return false; /* * TPC report - check that: * category = 0 (Spectrum Management) or 5 (Radio Measurement) * spectrum management action = 3 (TPC/Link Measurement report) * TPC report EID = 35 * TPC report element length = 2 * * The spectrum management's tpc_report struct is used here both for * parsing tpc_report and radio measurement's link measurement report * frame, since the relevant part is identical in both frames. */ if (mgmt->u.action.category != WLAN_CATEGORY_SPECTRUM_MGMT && mgmt->u.action.category != WLAN_CATEGORY_RADIO_MEASUREMENT) return false; /* both spectrum mgmt and link measurement have same action code */ if (mgmt->u.action.u.tpc_report.action_code != WLAN_ACTION_SPCT_TPC_RPRT) return false; if (mgmt->u.action.u.tpc_report.tpc_elem_id != WLAN_EID_TPC_REPORT || mgmt->u.action.u.tpc_report.tpc_elem_length != sizeof(struct ieee80211_tpc_report_ie)) return false; return true; } static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (skb->len < IEEE80211_MIN_ACTION_SIZE) return false; if (!ieee80211_is_action(mgmt->frame_control)) return false; if (mgmt->u.action.category == WLAN_CATEGORY_WNM_UNPROTECTED && mgmt->u.action.u.wnm_timing_msr.action_code == WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE && skb->len >= offsetofend(typeof(*mgmt), u.action.u.wnm_timing_msr)) return true; return false; } static inline bool ieee80211_is_ftm(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (!ieee80211_is_public_action((void *)mgmt, skb->len)) return false; if (mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_RESPONSE && skb->len >= offsetofend(typeof(*mgmt), u.action.u.ftm)) return true; return false; } struct element { u8 id; u8 datalen; u8 data[]; } __packed; /* element iteration helpers */ #define for_each_element(_elem, _data, _datalen) \ for (_elem = (const struct element *)(_data); \ (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >= \ (int)sizeof(*_elem) && \ (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >= \ (int)sizeof(*_elem) + _elem->datalen; \ _elem = (const struct element *)(_elem->data + _elem->datalen)) #define for_each_element_id(element, _id, data, datalen) \ for_each_element(element, data, datalen) \ if (element->id == (_id)) #define for_each_element_extid(element, extid, _data, _datalen) \ for_each_element(element, _data, _datalen) \ if (element->id == WLAN_EID_EXTENSION && \ element->datalen > 0 && \ element->data[0] == (extid)) #define for_each_subelement(sub, element) \ for_each_element(sub, (element)->data, (element)->datalen) #define for_each_subelement_id(sub, id, element) \ for_each_element_id(sub, id, (element)->data, (element)->datalen) #define for_each_subelement_extid(sub, extid, element) \ for_each_element_extid(sub, extid, (element)->data, (element)->datalen) /** * for_each_element_completed - determine if element parsing consumed all data * @element: element pointer after for_each_element() or friends * @data: same data pointer as passed to for_each_element() or friends * @datalen: same data length as passed to for_each_element() or friends * * This function returns %true if all the data was parsed or considered * while walking the elements. Only use this if your for_each_element() * loop cannot be broken out of, otherwise it always returns %false. * * If some data was malformed, this returns %false since the last parsed * element will not fill the whole remaining data. */ static inline bool for_each_element_completed(const struct element *element, const void *data, size_t datalen) { return (const u8 *)element == (const u8 *)data + datalen; } /* * RSNX Capabilities: * bits 0-3: Field length (n-1) */ #define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) #define WLAN_RSNX_CAPA_SAE_H2E BIT(5) /* * reduced neighbor report, based on Draft P802.11ax_D6.1, * section 9.4.2.170 and accepted contributions. */ #define IEEE80211_AP_INFO_TBTT_HDR_TYPE 0x03 #define IEEE80211_AP_INFO_TBTT_HDR_FILTERED 0x04 #define IEEE80211_AP_INFO_TBTT_HDR_COLOC 0x08 #define IEEE80211_AP_INFO_TBTT_HDR_COUNT 0xF0 #define IEEE80211_TBTT_INFO_TYPE_TBTT 0 #define IEEE80211_TBTT_INFO_TYPE_MLD 1 #define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED 0x01 #define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID 0x02 #define IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID 0x04 #define IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID 0x08 #define IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS 0x10 #define IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE 0x20 #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 #define IEEE80211_RNR_TBTT_PARAMS_PSD_NO_LIMIT 127 #define IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED -128 struct ieee80211_neighbor_ap_info { u8 tbtt_info_hdr; u8 tbtt_info_len; u8 op_class; u8 channel; } __packed; enum ieee80211_range_params_max_total_ltf { IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_4 = 0, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_8, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_16, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED, }; /* * reduced neighbor report, based on Draft P802.11be_D3.0, * section 9.4.2.170.2. */ struct ieee80211_rnr_mld_params { u8 mld_id; __le16 params; } __packed; #define IEEE80211_RNR_MLD_PARAMS_LINK_ID 0x000F #define IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT 0x0FF0 #define IEEE80211_RNR_MLD_PARAMS_UPDATES_INCLUDED 0x1000 #define IEEE80211_RNR_MLD_PARAMS_DISABLED_LINK 0x2000 /* Format of the TBTT information element if it has 7, 8 or 9 bytes */ struct ieee80211_tbtt_info_7_8_9 { u8 tbtt_offset; u8 bssid[ETH_ALEN]; /* The following element is optional, structure may not grow */ u8 bss_params; s8 psd_20; } __packed; /* Format of the TBTT information element if it has >= 11 bytes */ struct ieee80211_tbtt_info_ge_11 { u8 tbtt_offset; u8 bssid[ETH_ALEN]; __le32 short_ssid; /* The following elements are optional, structure may grow */ u8 bss_params; s8 psd_20; struct ieee80211_rnr_mld_params mld_params; } __packed; /* multi-link device */ #define IEEE80211_MLD_MAX_NUM_LINKS 15 #define IEEE80211_ML_CONTROL_TYPE 0x0007 #define IEEE80211_ML_CONTROL_TYPE_BASIC 0 #define IEEE80211_ML_CONTROL_TYPE_PREQ 1 #define IEEE80211_ML_CONTROL_TYPE_RECONF 2 #define IEEE80211_ML_CONTROL_TYPE_TDLS 3 #define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 #define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 struct ieee80211_multi_link_elem { __le16 control; u8 variable[]; } __packed; #define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 #define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 #define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 #define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 #define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 #define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 #define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff #define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 #define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 /* * Described in P802.11be_D3.0 * dot11MSDTimerDuration should default to 5484 (i.e. 171.375) * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0) * dot11MSDTXOPMAX defaults to 1 */ #define IEEE80211_MED_SYNC_DELAY_DEFAULT 0x10ac #define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 #define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 #define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 #define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 #define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 #define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 #define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 #define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 #define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 #define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 #define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 #define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f #define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 #define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 #define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 #define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 struct ieee80211_mle_basic_common_info { u8 len; u8 mld_mac_addr[ETH_ALEN]; u8 variable[]; } __packed; #define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 struct ieee80211_mle_preq_common_info { u8 len; u8 variable[]; } __packed; #define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 /* no fixed fields in RECONF */ struct ieee80211_mle_tdls_common_info { u8 len; u8 ap_mld_mac_addr[ETH_ALEN]; } __packed; #define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 /* no fixed fields in PRIO_ACCESS */ /** * ieee80211_mle_common_size - check multi-link element common size * @data: multi-link element, must already be checked for size using * ieee80211_mle_size_ok() */ static inline u8 ieee80211_mle_common_size(const u8 *data) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); u8 common = 0; switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: case IEEE80211_ML_CONTROL_TYPE_PREQ: case IEEE80211_ML_CONTROL_TYPE_TDLS: case IEEE80211_ML_CONTROL_TYPE_RECONF: /* * The length is the first octet pointed by mle->variable so no * need to add anything */ break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) common += ETH_ALEN; return common; default: WARN_ON(1); return 0; } return sizeof(*mle) + common + mle->variable[0]; } /** * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count * @mle: the basic multi link element * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). * * If the BSS parameter change count value can't be found (the presence bit * for it is clear), 0 will be returned. */ static inline u8 ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle) { u16 control = le16_to_cpu(mle->control); const u8 *common = mle->variable; /* common points now at the beginning of ieee80211_mle_basic_common_info */ common += sizeof(struct ieee80211_mle_basic_common_info); if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) return 0; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; return *common; } /** * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay * @data: pointer to the multi link EHT IE * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). * * If the medium synchronization is not present, then the default value is * returned. */ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); const u8 *common = mle->variable; /* common points now at the beginning of ieee80211_mle_basic_common_info */ common += sizeof(struct ieee80211_mle_basic_common_info); if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) return IEEE80211_MED_SYNC_DELAY_DEFAULT; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) common += 1; return get_unaligned_le16(common); } /** * ieee80211_mle_get_eml_cap - returns the EML capability * @data: pointer to the multi link EHT IE * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). * * If the EML capability is not present, 0 will be returned. */ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); const u8 *common = mle->variable; /* common points now at the beginning of ieee80211_mle_basic_common_info */ common += sizeof(struct ieee80211_mle_basic_common_info); if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)) return 0; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) common += 2; return get_unaligned_le16(common); } /** * ieee80211_mle_size_ok - validate multi-link element size * @data: pointer to the element data * @len: length of the containing element */ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u8 fixed = sizeof(*mle); u8 common = 0; bool check_common_len = false; u16 control; if (len < fixed) return false; control = le16_to_cpu(mle->control); switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: common += sizeof(struct ieee80211_mle_basic_common_info); check_common_len = true; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) common += 2; if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) common += 2; if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) common += 2; if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) common += 1; break; case IEEE80211_ML_CONTROL_TYPE_PREQ: common += sizeof(struct ieee80211_mle_preq_common_info); if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) common += 1; check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_RECONF: if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; break; case IEEE80211_ML_CONTROL_TYPE_TDLS: common += sizeof(struct ieee80211_mle_tdls_common_info); check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) common += ETH_ALEN; break; default: /* we don't know this type */ return true; } if (len < fixed + common) return false; if (!check_common_len) return true; /* if present, common length is the first octet there */ return mle->variable[0] >= common; } /** * ieee80211_mle_type_ok - validate multi-link element type and size * @data: pointer to the element data * @type: expected type of the element * @len: length of the containing element */ static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control; if (!ieee80211_mle_size_ok(data, len)) return false; control = le16_to_cpu(mle->control); if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type) return true; return false; } enum ieee80211_mle_subelems { IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, IEEE80211_MLE_SUBELEM_FRAGMENT = 254, }; #define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f #define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 #define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 #define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 #define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 #define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 #define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 #define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 #define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 struct ieee80211_mle_per_sta_profile { __le16 control; u8 sta_info_len; u8 variable[]; } __packed; /** * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta * profile size * @data: pointer to the sub element data * @len: length of the containing sub element */ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, size_t len) { const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; u16 control; u8 fixed = sizeof(*prof); u8 info_len = 1; if (len < fixed) return false; control = le16_to_cpu(prof->control); if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) info_len += 6; if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) info_len += 2; if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) info_len += 8; if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) info_len += 2; if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) info_len += 2; else info_len += 1; } if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) info_len += 1; return prof->sta_info_len >= info_len && fixed + prof->sta_info_len <= len; } /** * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS * parameter change count * @prof: the per-STA profile, having been checked with * ieee80211_mle_basic_sta_prof_size_ok() for the correct length * * Return: The BSS parameter change count value if present, 0 otherwise. */ static inline u8 ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof) { u16 control = le16_to_cpu(prof->control); const u8 *pos = prof->variable; if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)) return 0; if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) pos += 6; if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) pos += 2; if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) pos += 8; if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) pos += 2; if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) pos += 2; else pos += 1; } return *pos; } #define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID 0x000f #define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 #define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 #define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 #define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_UPDATE_TYPE 0x0780 #define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 /** * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link * element sta profile size. * @data: pointer to the sub element data * @len: length of the containing sub element */ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, size_t len) { const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; u16 control; u8 fixed = sizeof(*prof); u8 info_len = 1; if (len < fixed) return false; control = le16_to_cpu(prof->control); if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT) info_len += ETH_ALEN; if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) info_len += 2; if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT) info_len += 2; return prof->sta_info_len >= info_len && fixed + prof->sta_info_len - 1 <= len; } static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) { const struct ieee80211_ttlm_elem *t2l = (const void *)data; u8 control, fixed = sizeof(*t2l), elem_len = 0; if (len < fixed) return false; control = t2l->control; if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) elem_len += 2; if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) elem_len += 3; if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { u8 bm_size; elem_len += 1; if (len < fixed + elem_len) return false; if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) bm_size = 1; else bm_size = 2; elem_len += hweight8(t2l->optional[0]) * bm_size; } return len >= fixed + elem_len; } #define for_each_mle_subelement(_elem, _data, _len) \ if (ieee80211_mle_size_ok(_data, _len)) \ for_each_element(_elem, \ _data + ieee80211_mle_common_size(_data),\ _len - ieee80211_mle_common_size(_data)) #endif /* LINUX_IEEE80211_H */ |
| 20 4 17 16 16 2 2 1 1 1 1 2 1 1 1 62 9 56 54 3 15 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Author: * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <linux/seq_file.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; struct icmp6hdr _hdr; hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; tuple->dst.u.icmp.type = hp->icmp6_type; tuple->src.u.icmp.id = hp->icmp6_identifier; tuple->dst.u.icmp.code = hp->icmp6_code; return true; } /* Add 1; spaces filled with 0. */ static const u_int8_t invmap[] = { [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 }; static const u_int8_t noct_valid_new[] = { [ICMPV6_MGM_QUERY - 130] = 1, [ICMPV6_MGM_REPORT - 130] = 1, [ICMPV6_MGM_REDUCTION - 130] = 1, [NDISC_ROUTER_SOLICITATION - 130] = 1, [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, [ICMPV6_MLD2_REPORT - 130] = 1 }; bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { int type = orig->dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(invmap) || !invmap[type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; tuple->dst.u.icmp.type = invmap[type] - 1; tuple->dst.u.icmp.code = orig->dst.u.icmp.code; return true; } static unsigned int *icmpv6_get_timeouts(struct net *net) { return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_icmpv6_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u8 valid_new[] = { [ICMPV6_ECHO_REQUEST - 128] = 1, [ICMPV6_NI_QUERY - 128] = 1 }; if (state->pf != NFPROTO_IPV6) return -NF_ACCEPT; if (!nf_ct_is_confirmed(ct)) { int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { /* Can't create a new ICMPv6 `conn' with this. */ pr_debug("icmpv6: can't create new conn with type %u\n", type + 128); nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); return -NF_ACCEPT; } } if (!timeout) timeout = icmpv6_get_timeouts(nf_ct_net(ct)); /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_ICMPV6, "%s", msg); } static noinline_for_stack int nf_conntrack_icmpv6_redirect(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { u8 hl = ipv6_hdr(skb)->hop_limit; union nf_inet_addr outer_daddr; union { struct nd_opt_hdr nd_opt; struct rd_msg rd_msg; } tmp; const struct nd_opt_hdr *nd_opt; const struct rd_msg *rd_msg; rd_msg = skb_header_pointer(skb, dataoff, sizeof(*rd_msg), &tmp.rd_msg); if (!rd_msg) { icmpv6_error_log(skb, state, "short redirect"); return -NF_ACCEPT; } if (rd_msg->icmph.icmp6_code != 0) return NF_ACCEPT; if (hl != 255 || !(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { icmpv6_error_log(skb, state, "invalid saddr or hoplimit for redirect"); return -NF_ACCEPT; } dataoff += sizeof(*rd_msg); /* warning: rd_msg no longer usable after this call */ nd_opt = skb_header_pointer(skb, dataoff, sizeof(*nd_opt), &tmp.nd_opt); if (!nd_opt || nd_opt->nd_opt_len == 0) { icmpv6_error_log(skb, state, "redirect without options"); return -NF_ACCEPT; } /* We could call ndisc_parse_options(), but it would need * skb_linearize() and a bit more work. */ if (nd_opt->nd_opt_type != ND_OPT_REDIRECT_HDR) return NF_ACCEPT; memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, sizeof(outer_daddr.ip6)); dataoff += 8; return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMPV6, &outer_daddr); } int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { union nf_inet_addr outer_daddr; const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; int type; icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { icmpv6_error_log(skb, state, "short packet"); return -NF_ACCEPT; } if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_ip6_checksum(skb, state->hook, dataoff, IPPROTO_ICMPV6)) { icmpv6_error_log(skb, state, "ICMPv6 checksum failed"); return -NF_ACCEPT; } type = icmp6h->icmp6_type - 130; if (type >= 0 && type < sizeof(noct_valid_new) && noct_valid_new[type]) { nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return NF_ACCEPT; } if (icmp6h->icmp6_type == NDISC_REDIRECT) return nf_conntrack_icmpv6_redirect(tmpl, skb, dataoff, state); /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, sizeof(outer_daddr.ip6)); dataoff += sizeof(*icmp6h); return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMPV6, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, }; static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) { if (!tb[CTA_PROTO_ICMPV6_TYPE]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); if (tuple->dst.u.icmp.type < 128 || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type - 128]) return -EINVAL; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) { if (!tb[CTA_PROTO_ICMPV6_CODE]) return -EINVAL; tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) { if (!tb[CTA_PROTO_ICMPV6_ID]) return -EINVAL; tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); } return 0; } static unsigned int icmpv6_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(icmpv6_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 icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; } else { /* Set default ICMPv6 timeout. */ *timeout = in->timeout; } return 0; } static int icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_icmpv6_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmpv6_pernet(net); in->timeout = nf_ct_icmpv6_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l4proto = IPPROTO_ICMPV6, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_ICMP_MAX, .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 632 13 644 644 643 1 644 3039 3039 664 453 454 421 421 421 421 421 420 420 16 419 421 29 207 563 400 400 624 624 624 624 2 624 21 21 664 664 664 433 450 4 47 400 644 432 644 644 11 634 644 643 644 644 624 843 843 432 631 644 400 400 3051 3051 3051 3050 3039 20 860 433 446 21 22 22 19 22 20 21 22 22 22 21 22 22 22 21 22 8 22 22 17 16 17 20 20 20 20 20 13 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, } }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { /* Make sure we catch unsupported clockids */ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] static inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * We do not migrate the timer when it is expiring before the next * event on the target cpu. When high resolution is enabled, we cannot * reprogram the target cpu hardware and we would cause it to fire * late. To keep it simple, we handle the high resolution enabled and * disabled case similar. * * Called with cpu_base->lock of target cpu held. */ static int hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) { ktime_t expires; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires < new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ((struct hrtimer *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode); void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_init(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static inline int hrtimer_hres_active(void) { return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases)); } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } static void retrigger_next_event(void *arg); /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!__hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (__hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!__hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * Returns the number of overruns. * * Can be safely called from the callback function of @timer. If * called from other contexts @timer must neither be enqueued nor * running the callback and the caller needs to take care of * serialization. * * Note: This only updates the timer expiry value and does not requeue * the timer. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns 1 when the new timer is the leftmost timer in the tree. */ static int enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffie) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); force_local &= base->cpu_base->next_timer == timer; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) return first; /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling del_timer_sync() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!__hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (__hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { if (likely(clock_id < MAX_CLOCKS)) { int base = hrtimer_clock_to_base_table[clock_id]; if (likely(base != HRTIMER_MAX_CLOCK_BASES)) return base; } WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = timer->function; /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_softirq_irqoff(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } /* called with interrupts disabled */ static inline void __hrtimer_peek_ahead_timers(void) { struct tick_device *td; if (!hrtimer_hres_active()) return; td = this_cpu_ptr(&tick_cpu_device); if (td && td->evtdev) hrtimer_interrupt(td->evtdev); } #else /* CONFIG_HIGH_RES_TIMERS */ static inline void __hrtimer_peek_ahead_timers(void) { } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (__hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_softirq_irqoff(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = current; } /** * hrtimer_init_sleeper - initialize sleeper to the given clock * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; u64 slack; slack = current->timer_slack_ns; if (rt_task(current)) slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, slack); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; int i, ncpu = cpumask_first(cpu_active_mask); tick_cancel_sched_timer(dying_cpu); old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * @clock_id: timer clock to be used */ int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id) { struct hrtimer_sleeper t; /* * Optimize when a zero timeout value is given. It does not * matter whether this is an absolute or a relative time. */ if (expires && *expires == 0) { __set_current_state(TASK_RUNNING); return 0; } /* * A NULL parameter means "infinite" */ if (!expires) { schedule(); return -EINTR; } /* * Override any slack passed by the user if under * rt contraints. */ if (rt_task(current)) delta = 0; hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); if (likely(t.task)) schedule(); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); __set_current_state(TASK_RUNNING); return !t.task ? 0 : -EINTR; } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the * actual wakeup to a time that is both power and performance friendly * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, CLOCK_MONOTONIC); } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); /** * schedule_hrtimeout - sleep until timeout * @expires: timeout value (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode) { return schedule_hrtimeout_range(expires, 0, mode); } EXPORT_SYMBOL_GPL(schedule_hrtimeout); |
| 222 107 107 72 31 249 249 248 1552 1552 132 132 1396 187 282 1550 1551 1550 1 1551 135 1 1 1 1 1 1 1 1 129 129 129 129 136 136 136 136 137 138 119 31 138 58 137 99 81 119 138 2 136 118 29 135 136 109 29 108 1 107 1 136 2 107 107 107 107 105 32 32 1 31 1 1 13 7 4 1 1 1 1 1 1 1 5 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 20 2 18 9 2 1 6 1 6 9 7 3 3 3 3 105 105 114 187 180 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 151 10 6 6 6 2 10 10 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" #include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br = NULL; u32 num_cfm_peer_mep_infos; u32 num_cfm_mep_infos; size_t vinfo_sz = 0; int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && (p->flags & BR_VLAN_TUNNEL)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); if (p && vg && (filter_mask & RTEXT_FILTER_MST)) vinfo_sz += br_mst_info_size(vg); if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; if (!br) return vinfo_sz; /* CFM status info must be added */ br_cfm_mep_count(br, &num_cfm_mep_infos); br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ /* For each status struct the MEP instance (u32) is added */ /* MEP instance (u32) + br_cfm_mep_status */ vinfo_sz += num_cfm_mep_infos * /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + nla_total_size(sizeof(u32))); /* MEP instance (u32) + br_cfm_cc_peer_status */ vinfo_sz += num_cfm_peer_mep_infos * /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + nla_total_size(sizeof(u32))); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_BACKUP_NHID */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(p->flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(p->flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(p->flags & BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, !!(p->flags & BR_NEIGH_VLAN_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, p->multicast_eht_hosts_cnt) || nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, br_multicast_ngroups_get(&p->multicast_ctx)) || nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); if (p->backup_nhid && nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid)) return -EMSGSIZE; return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev, bool getlink) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_info event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS | RTEXT_FILTER_MST)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && (port->flags & BR_VLAN_TUNNEL)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_MRP) { int err; if (!br_mrp_enabled(br) || port) goto done; rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; if (!br_cfm_created(br) || port) goto done; cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); if (!cfm_nest) goto nla_put_failure; if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { rcu_read_lock(); err = br_cfm_config_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_CFM_STATUS) { rcu_read_lock(); err = br_cfm_status_fill_info(skb, br, getlink); rcu_read_unlock(); if (err) goto nla_put_failure; } nla_nest_end(skb, cfm_nest); } if ((filter_mask & RTEXT_FILTER_MST) && br_opt_get(br, BROPT_MST_ENABLED) && port) { const struct net_bridge_vlan_group *vg = nbp_vlan_group(port); struct nlattr *mst_nest; int err; if (!vg || !vg->num_vlans) goto done; mst_nest = nla_nest_start(skb, IFLA_BRIDGE_MST); if (!mst_nest) goto nla_put_failure; err = br_mst_fill_info(skb, vg); if (err) goto nla_put_failure; nla_nest_end(skb, mst_nest); } done: if (af) { if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) nla_nest_end(skb, af); else nla_nest_cancel(skb, af); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void br_info_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port, u32 filter) { struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; return br_info_notify(event, br, port, filter); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { int err, rtm_cmd; if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; /* needed for vlan-only NEWVLAN/DELVLAN notifications */ rtm_cmd = br_afspec_cmd_to_rtm(cmd); if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, v_change_start = 0; if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { bool curr_change = false; tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; if (curr_change) { *changed = curr_change; if (!v_change_start) v_change_start = v; } else { /* nothing to notify yet */ if (!v_change_start) continue; br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); v_change_start = 0; } cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); *vinfo_last = NULL; return err; } err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); if (*changed) br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); return err; } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; case IFLA_BRIDGE_MRP: err = br_mrp_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_CFM: err = br_cfm_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_MST: if (!p) { NL_SET_ERR_MSG(extack, "MST states can only be set on bridge ports"); return -EINVAL; } if (cmd != RTM_SETLINK) { NL_SET_ERR_MSG(extack, "MST states can only be set through RTM_SETLINK"); return -EINVAL; } err = br_mst_process(p, attr, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNSPEC] = { .strict_start_type = IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], int attrtype, unsigned long mask) { if (!tb[attrtype]) return; if (nla_get_u8(tb[attrtype])) p->flags |= mask; else p->flags &= ~mask; } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned long old_flags, changed_mask; bool br_vlan_tunnel_old; int err; old_flags = p->flags; br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, BR_NEIGH_VLAN_SUPPRESS); if ((p->flags & BR_PORT_MAB) && (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); p->flags = old_flags; return -EINVAL; } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { struct net_bridge_fdb_flush_desc desc = { .flags = BIT(BR_FDB_LOCKED), .flags_mask = BIT(BR_FDB_LOCKED), .port_ifindex = p->dev->ifindex, }; br_fdb_flush(p->br, &desc); } changed_mask = old_flags ^ p->flags; err = br_switchdev_set_port_flag(p, p->flags, changed_mask, extack); if (err) { p->flags = old_flags; return err; } if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); br_port_flags_change(p, changed_mask); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(&p->multicast_ctx, mcast_router); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { u32 hlimit; hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); err = br_multicast_eht_set_hosts_limit(p, hlimit); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { u32 max_groups; max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } if (tb[IFLA_BRPORT_BACKUP_NHID]) { u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]); WRITE_ONCE(p->backup_nhid, backup_nhid); } return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; spin_lock_bh(&p->br->lock); err = br_setport(p, tb, extack); spin_unlock_bh(&p->br->lock); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL] && !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; if (!data) return 0; spin_lock_bh(&br->lock); ret = br_setport(br_port_get_rtnl(dev), data, extack); spin_unlock_bh(&br->lock); return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_UNSPEC] = { .strict_start_type = IFLA_BR_FDB_N_LEARNED }, [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT }, [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); err = br_stp_set_enabled(br, stp_enabled, extack); if (err) return err; } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); err = __br_vlan_set_default_pvid(br, defpvid, extack); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_ENABLED]) { __u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]); err = br_vlan_set_stats(br, vlan_stats); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_PER_PORT]) { __u8 per_port = nla_get_u8(data[IFLA_BR_VLAN_STATS_PER_PORT]); err = br_vlan_set_stats_per_port(br, per_port); if (err) return err; } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = fwd_mask; } if (data[IFLA_BR_GROUP_ADDR]) { u8 new_addr[ETH_ALEN]; if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) return -EINVAL; memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); } if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); err = br_multicast_set_router(&br->multicast_ctx, multicast_router); if (err) return err; } if (data[IFLA_BR_MCAST_SNOOPING]) { u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); err = br_multicast_toggle(br, mcast_snooping, extack); if (err) return err; } if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { u8 val; val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); } if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); err = br_multicast_set_querier(&br->multicast_ctx, mcast_querier); if (err) return err; } if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", RHT_ELASTICITY); if (data[IFLA_BR_MCAST_HASH_MAX]) br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); br_multicast_set_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { __u8 mcast_stats; mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!mcast_stats); } if (data[IFLA_BR_MCAST_IGMP_VERSION]) { __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); err = br_multicast_set_igmp_version(&br->multicast_ctx, igmp_version); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BR_MCAST_MLD_VERSION]) { __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); err = br_multicast_set_mld_version(&br->multicast_ctx, mld_version); if (err) return err; } #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); } if (data[IFLA_BR_NF_CALL_IP6TABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); } if (data[IFLA_BR_NF_CALL_ARPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); } #endif if (data[IFLA_BR_MULTI_BOOLOPT]) { struct br_boolopt_multi *bm; bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]); err = br_boolopt_multi_toggle(br, bm, extack); if (err) return err; } if (data[IFLA_BR_FDB_MAX_LEARNED]) { u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]); WRITE_ONCE(br->fdb_max_learned, val); } return 0; } static int br_dev_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); int err; err = register_netdevice(dev); if (err) return err; if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } err = br_changelink(dev, tb, data, extack); if (err) br_dev_delete(dev, NULL); return err; } static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_PER_PORT */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u8 vlan_enabled = br_vlan_enabled(br->dev); struct br_boolopt_multi bm; u64 clockval; clockval = br_timer_value(&br->hello_timer); if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->tcn_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->topology_change_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; br_boolopt_multi_get(br, &bm); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id), &br->bridge_id) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id), &br->designated_root) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) || nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED, atomic_read(&br->fdb_n_learned)) || nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_ctx.multicast_igmp_version) || br_multicast_dump_querier_state(skb, &br->multicast_ctx, IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, br_opt_get(br, BROPT_NF_CALL_IPTABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, br_opt_get(br, BROPT_NF_CALL_IP6TABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, br_opt_get(br, BROPT_NF_CALL_ARPTABLES) ? 1 : 0)) return -EMSGSIZE; #endif return 0; } static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; int numvls = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; vg = nbp_vlan_group(p); break; default: return 0; } if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) numvls++; } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; struct nlattr *nest; int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; br = p->br; vg = nbp_vlan_group(p); break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; if (vg) { u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct pcpu_sw_netstats stats; if (++vl_idx < *prividx) continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = u64_stats_read(&stats.rx_bytes); vxi.rx_packets = u64_stats_read(&stats.rx_packets); vxi.tx_bytes = u64_stats_read(&stats.tx_bytes); vxi.tx_packets = u64_stats_read(&stats.tx_packets); if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; } } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (++vl_idx >= *prividx) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, sizeof(struct br_mcast_stats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; br_multicast_get_stats(br, p, nla_data(nla)); } #endif if (p) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, sizeof(p->stp_xstats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; spin_lock_bh(&br->lock); memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); spin_unlock_bh(&br->lock); } nla_nest_end(skb, nest); *prividx = 0; return 0; nla_put_failure: nla_nest_end(skb, nest); *prividx = vl_idx; return -EMSGSIZE; } static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, .changelink = br_changelink, .dellink = br_dev_delete, .get_size = br_get_size, .fill_info = br_fill_info, .fill_linkxstats = br_fill_linkxstats, .get_linkxstats_size = br_get_linkxstats_size, .slave_maxtype = IFLA_BRPORT_MAX, .slave_policy = br_port_policy, .slave_changelink = br_port_slave_changelink, .get_slave_size = br_port_get_slave_size, .fill_slave_info = br_port_fill_slave_info, }; int __init br_netlink_init(void) { int err; br_vlan_rtnl_init(); rtnl_af_register(&br_af_ops); err = rtnl_link_register(&br_link_ops); if (err) goto out_af; return 0; out_af: rtnl_af_unregister(&br_af_ops); return err; } void br_netlink_fini(void) { br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } |
| 306 306 352 124 124 124 124 124 123 124 124 123 336 337 306 306 306 306 337 337 6 6 337 337 330 323 337 337 337 321 337 337 330 321 321 321 321 337 337 321 321 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions implement the sctp_outq class. The outqueue handles * bundling and queueing of outgoing SCTP chunks. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Perry Melange <pmelange@null.cc.uic.edu> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/list.h> /* For struct list_head */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/slab.h> #include <net/sock.h> /* For skb_set_owner_w */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn); static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn, int count_of_newacks); static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { return q->sched->dequeue(q); } /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } /* * SFR-CACC algorithm: * D) If count_of_newacks is greater than or equal to 2 * and t was not sent to the current primary then the * sender MUST NOT increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks >= 2 && transport != primary) return 1; return 0; } /* * SFR-CACC algorithm: * F) If count_of_newacks is less than 2, let d be the * destination to which t was sent. If cacc_saw_newack * is 0 for destination d, then the sender MUST NOT * increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks < 2 && (transport && !transport->cacc.cacc_saw_newack)) return 1; return 0; } /* * SFR-CACC algorithm: * 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD * execute steps C, D, F. * * C has been implemented in sctp_outq_sack */ static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (!primary->cacc.cycling_changeover) { if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks)) return 1; if (sctp_cacc_skip_3_1_f(transport, count_of_newacks)) return 1; return 0; } return 0; } /* * SFR-CACC algorithm: * 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less * than next_tsn_at_change of the current primary, then * the sender MUST NOT increment missing report count * for t. */ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.cycling_changeover && TSN_lt(tsn, primary->cacc.next_tsn_at_change)) return 1; return 0; } /* * SFR-CACC algorithm: * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks, __u32 tsn) { if (primary->cacc.changeover_active && (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } /* Initialize an existing sctp_outq. This does the boring stuff. * You still need to define handlers if you really want to DO * something with this structure... */ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { memset(q, 0, sizeof(struct sctp_outq)); q->asoc = asoc; INIT_LIST_HEAD(&q->out_chunk_list); INIT_LIST_HEAD(&q->control_chunk_list); INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. */ static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; struct sctp_chunk *chunk, *tmp; /* Throw away unacknowledged chunks. */ list_for_each_entry(transport, &q->asoc->peer.transport_addr_list, transports) { while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* Mark as part of a failed message. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } } /* Throw away chunks that have been gap ACKed. */ list_for_each_safe(lchunk, temp, &q->sacked) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks in the retransmit queue. */ list_for_each_safe(lchunk, temp, &q->retransmit) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks that are in the abandoned queue. */ list_for_each_safe(lchunk, temp, &q->abandoned) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } } void sctp_outq_teardown(struct sctp_outq *q) { __sctp_outq_teardown(q); sctp_outq_init(q->asoc, q); } /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ __sctp_outq_teardown(q); } /* Put a new chunk in an sctp_outq. */ void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = q->asoc->base.net; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); /* If it is data, queue it up, otherwise, send it * immediately. */ if (sctp_chunk_is_data(chunk)) { pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); sctp_outq_tail_data(q, chunk); if (chunk->asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) chunk->asoc->sent_cnt_removable++; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); else SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); } else { list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } if (!q->cork) sctp_outq_flush(q, 0, gfp); } /* Insert a chunk into the sorted list based on the TSNs. The retransmit list * and the abandoned list are in ascending order. */ static void sctp_insert_list(struct list_head *head, struct list_head *new) { struct list_head *pos; struct sctp_chunk *nchunk, *lchunk; __u32 ntsn, ltsn; int done = 0; nchunk = list_entry(new, struct sctp_chunk, transmitted_list); ntsn = ntohl(nchunk->subh.data_hdr->tsn); list_for_each(pos, head) { lchunk = list_entry(pos, struct sctp_chunk, transmitted_list); ltsn = ntohl(lchunk->subh.data_hdr->tsn); if (TSN_lt(ntsn, ltsn)) { list_add(new, pos->prev); done = 1; break; } } if (!done) list_add_tail(new, head); } static int sctp_prsctp_prune_sent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct list_head *queue, int msg_len) { struct sctp_chunk *chk, *temp; list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; if (!chk->msg->abandoned && (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (queue != &asoc->outqueue.retransmit && !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); asoc->outqueue.outstanding_bytes -= sctp_data_size(chk); } msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); if (msg_len <= 0) break; } return msg_len; } static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!chk->msg->abandoned && (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; /* clear out_curr if all frag chunks are pruned */ if (asoc->stream.out_curr == sout && list_is_last(&chk->frag_list, &chk->msg->chunks)) asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); if (msg_len <= 0) break; } q->sched->sched_all(&asoc->stream); return msg_len; } /* Abandon the chunks according their priorities */ void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_transport *transport; if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable) return; msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &asoc->outqueue.retransmit, msg_len); if (msg_len <= 0) return; list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &transport->transmitted, msg_len); if (msg_len <= 0) return; } sctp_prsctp_prune_unsent(asoc, sinfo, msg_len); } /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; /* Walk through the specified transmitted queue. */ list_for_each_safe(lchunk, ltemp, &transport->transmitted) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(lchunk); sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been previousely acked, * stop considering it 'outstanding'. Our peer * will most likely never see it since it will * not be retransmitted */ if (!chunk->tsn_gap_acked) { if (chunk->transport) chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } /* If we are doing retransmission due to a timeout or pmtu * discovery, only the chunks that are not yet acked should * be added to the retransmit queue. */ if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for * retransmission (via either T3-rtx timer expiration * (Section 6.3.3) or via fast retransmit * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); /* sctpimpguide-05 Section 2.8.2 * M5) If a T3-rtx timer expires, the * 'TSN.Missing.Report' of all affected TSNs is set * to 0. */ chunk->tsn_missing_report = 0; /* If a chunk that is being used for RTT measurement * has to be retransmitted, we cannot use this chunk * anymore for RTT measurements. Reset rto_pending so * that a new RTT measurement is started when a new * data chunk is sent. */ if (chunk->rtt_in_progress) { chunk->rtt_in_progress = 0; transport->rto_pending = 0; } /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ list_del_init(lchunk); sctp_insert_list(&q->retransmit, lchunk); } } pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } /* Mark all the eligible packets on a transport for retransmission and force * one packet out. */ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason) { struct net *net = q->asoc->base.net; switch (reason) { case SCTP_RTXR_T3_RTX: SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); /* Update the retran path if the T3-rtx timer has expired for * the current retran path. */ if (transport == transport->asoc->peer.retran_path) sctp_assoc_update_retran_path(transport->asoc); transport->asoc->rtx_data_chunks += transport->asoc->unack_data; if (transport->pl.state == SCTP_PL_COMPLETE && transport->asoc->unack_data) sctp_transport_reset_probe_timer(transport); break; case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS); break; case SCTP_RTXR_T1_RTX: SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS); transport->asoc->init_retries++; break; default: BUG(); } sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ if (reason == SCTP_RTXR_T3_RTX) q->asoc->stream.si->generate_ftsn(q, q->asoc->ctsn_ack_point); /* Flush the queues only on timeout, since fast_rtx is only * triggered during sack processing and the queue * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); } /* * Transmit DATA chunks on the retransmit queue. Upon return from * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which * need to be transmitted by the caller. * We assume that pkt->transport has already been set. * * The return value is a normal kernel error return value. */ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer, gfp_t gfp) { struct sctp_transport *transport = pkt->transport; struct sctp_chunk *chunk, *chunk1; struct list_head *lqueue; enum sctp_xmit status; int error = 0; int timer = 0; int done = 0; int fast_rtx; lqueue = &q->retransmit; fast_rtx = q->fast_rtx; /* This loop handles time-out retransmissions, fast retransmissions, * and retransmissions due to opening of whindow. * * RFC 2960 6.3.3 Handle T3-rtx Expiration * * E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the * T3-rtx has expired will fit into a single packet, subject * to the MTU constraint for the path corresponding to the * destination transport address to which the retransmission * is being sent (this may be different from the address for * which the timer expires [see Section 6.4]). Call this value * K. Bundle and retransmit those K DATA chunks in a single * packet to the destination endpoint. * * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] * * For fast retransmissions we also send only ONE packet. However, * if we are just flushing the queue due to open window, we'll * try to send as much as possible. */ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(&chunk->transmitted_list); sctp_insert_list(&q->abandoned, &chunk->transmitted_list); continue; } /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the * way and into a 'transmitted' queue and skip to the * next chunk. */ if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); continue; } /* If we are doing fast retransmit, ignore non-fast_rtransmit * chunks */ if (fast_rtx && !chunk->fast_retransmit) continue; redo: /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: if (!pkt->has_data && !pkt->has_cookie_echo) { /* If this packet did not contain DATA then * retransmission did not happen, so do it * again. We'll ignore the error here since * control chunks are already freed so there * is nothing we can do. */ sctp_packet_transmit(pkt, gfp); goto redo; } /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* If we are retransmitting, we should only * send a single packet. * Otherwise, try appending this chunk again. */ if (rtx_timeout || fast_rtx) done = 1; else goto redo; /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA as there is no more room * at the receiver. */ done = 1; break; case SCTP_XMIT_DELAY: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA because of nagle delay. */ done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ list_move_tail(&chunk->transmitted_list, &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ if (chunk->fast_retransmit == SCTP_NEED_FRTX) chunk->fast_retransmit = SCTP_DONT_FRTX; q->asoc->stats.rtxchunks++; break; } /* Set the timer if there were no errors */ if (!error && !timer) timer = 1; if (done) break; } /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout || fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit == SCTP_NEED_FRTX) chunk1->fast_retransmit = SCTP_DONT_FRTX; } } *start_timer = timer; /* Clear fast retransmit hint */ if (fast_rtx) q->fast_rtx = 0; return error; } /* Cork the outqueue so queued chunks are really queued. */ void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; sctp_outq_flush(q, 0, gfp); } static int sctp_packet_singleton(struct sctp_transport *transport, struct sctp_chunk *chunk, gfp_t gfp) { const struct sctp_association *asoc = transport->asoc; const __u16 sport = asoc->base.bind_addr.port; const __u16 dport = asoc->peer.port; const __u32 vtag = asoc->peer.i.init_tag; struct sctp_packet singleton; sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { list_del_init(&chunk->list); sctp_chunk_free(chunk); return -ENOMEM; } return sctp_packet_transmit(&singleton, gfp); } /* Struct to hold the context during sctp outq flush */ struct sctp_flush_ctx { struct sctp_outq *q; /* Current transport being used. It's NOT the same as curr active one */ struct sctp_transport *transport; /* These transports have chunks to send. */ struct list_head transport_list; struct sctp_association *asoc; /* Packet on the current transport above */ struct sctp_packet *packet; gfp_t gfp; }; /* transport: current transport */ static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx, struct sctp_chunk *chunk) { struct sctp_transport *new_transport = chunk->transport; if (!new_transport) { if (!sctp_chunk_is_data(chunk)) { /* If we have a prior transport pointer, see if * the destination address of the chunk * matches the destination address of the * current transport. If not a match, then * try to look up the transport with a given * destination address. We do this because * after processing ASCONFs, we may have new * transports created. */ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest, &ctx->transport->ipaddr)) new_transport = ctx->transport; else new_transport = sctp_assoc_lookup_paddr(ctx->asoc, &chunk->dest); } /* if we still don't have a new transport, then * use the current active path. */ if (!new_transport) new_transport = ctx->asoc->peer.active_path; } else { __u8 type; switch (new_transport->state) { case SCTP_INACTIVE: case SCTP_UNCONFIRMED: case SCTP_PF: /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. * * 3.3.6 Heartbeat Acknowledgement: * ... * A HEARTBEAT ACK is always sent to the source IP * address of the IP datagram containing the * HEARTBEAT chunk to which this ack is responding. * ... * * ASCONF_ACKs also must be sent to the source. */ type = chunk->chunk_hdr->type; if (type != SCTP_CID_HEARTBEAT && type != SCTP_CID_HEARTBEAT_ACK && type != SCTP_CID_ASCONF_ACK) new_transport = ctx->asoc->peer.active_path; break; default: break; } } /* Are we switching transports? Take care of transport locks. */ if (new_transport != ctx->transport) { ctx->transport = new_transport; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); /* We've switched transports, so apply the * Burst limit to the new transport. */ sctp_transport_burst_limited(ctx->transport); } } static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) { struct sctp_chunk *chunk, *tmp; enum sctp_xmit status; int one_packet, error; list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) { one_packet = 0; /* RFC 5061, 5.3 * F1) This means that until such time as the ASCONF * containing the add is acknowledged, the sender MUST * NOT use the new IP address as a source for ANY SCTP * packet except on carrying an ASCONF Chunk. */ if (ctx->asoc->src_out_of_asoc_ok && chunk->chunk_hdr->type != SCTP_CID_ASCONF) continue; list_del_init(&chunk->list); /* Pick the right transport to use. Should always be true for * the first chunk as we don't have a transport by then. */ sctp_outq_select_transport(ctx, chunk); switch (chunk->chunk_hdr->type) { /* 6.10 Bundling * ... * An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN * COMPLETE with any other chunks. [Send them immediately.] */ case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (error < 0) { ctx->asoc->base.sk->sk_err = -error; return; } ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) ctx->packet->vtag = ctx->asoc->c.my_vtag; fallthrough; /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can * send only 1 packet containing these chunks. */ case SCTP_CID_HEARTBEAT_ACK: case SCTP_CID_SHUTDOWN_ACK: case SCTP_CID_COOKIE_ACK: case SCTP_CID_COOKIE_ECHO: case SCTP_CID_ERROR: case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; fallthrough; case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (!error) ctx->asoc->stats.octrlchunks++; break; } fallthrough; case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: case SCTP_CID_RECONF: status = sctp_packet_transmit_chunk(ctx->packet, chunk, one_packet, ctx->gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &ctx->q->control_chunk_list); break; } ctx->asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN || chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } if (chunk == ctx->asoc->strreset_chunk) sctp_transport_reset_reconf_timer(ctx->transport); break; default: /* We built a chunk with an illegal type! */ BUG(); } } } /* Returns false if new data shouldn't be sent */ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx, int rtx_timeout) { int error, start_timer = 0; if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED) return false; if (ctx->transport != ctx->asoc->peer.retran_path) { /* Switch transports & prepare the packet. */ ctx->transport = ctx->asoc->peer.retran_path; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); } error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout, &start_timer, ctx->gfp); if (error < 0) ctx->asoc->base.sk->sk_err = -error; if (start_timer) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. */ if (ctx->packet->has_cookie_echo) return false; /* Don't send new data if there is still data * waiting to retransmit. */ if (!list_empty(&ctx->q->retransmit)) return false; return true; } static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, int rtx_timeout) { struct sctp_chunk *chunk; enum sctp_xmit status; /* Is it OK to send data chunks? */ switch (ctx->asoc->state) { case SCTP_STATE_COOKIE_ECHOED: /* Only allow bundling when this packet has a COOKIE-ECHO * chunk. */ if (!ctx->packet || !ctx->packet->has_cookie_echo) return; fallthrough; case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: break; default: /* Do nothing. */ return; } /* RFC 2960 6.1 Transmission of DATA Chunks * * C) When the time comes for the sender to transmit, * before sending new DATA chunks, the sender MUST * first transmit any outstanding DATA chunks which * are marked for retransmission (limited by the * current cwnd). */ if (!list_empty(&ctx->q->retransmit) && !sctp_outq_flush_rtx(ctx, rtx_timeout)) return; /* Apply Max.Burst limitation to the current transport in * case it will be used for new data. We are going to * rest it before we return, but we want to apply the limit * to the currently queued data. */ if (ctx->transport) sctp_transport_burst_limited(ctx->transport); /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { sctp_sched_dequeue_done(ctx->q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; } if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } sctp_outq_select_transport(ctx, chunk); pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n", __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), chunk->skb ? chunk->skb->head : NULL, chunk->skb ? refcount_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0, ctx->gfp); if (status != SCTP_XMIT_OK) { /* We could not append this chunk, so put * the chunk back on the output queue. */ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", __func__, ntohl(chunk->subh.data_hdr->tsn), status); sctp_outq_head_data(ctx->q, chunk); break; } /* The sender is in the SHUTDOWN-PENDING state, * The sender MAY set the I-bit in the DATA * chunk header. */ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING) chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) ctx->asoc->stats.ouodchunks++; else ctx->asoc->stats.oodchunks++; /* Only now it's safe to consider this * chunk as sent, sched-wise. */ sctp_sched_dequeue_done(ctx->q, chunk); list_add_tail(&chunk->transmitted_list, &ctx->transport->transmitted); sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; /* Only let one DATA chunk get bundled with a * COOKIE-ECHO chunk. */ if (ctx->packet->has_cookie_echo) break; } } static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) { struct sock *sk = ctx->asoc->base.sk; struct list_head *ltransport; struct sctp_packet *packet; struct sctp_transport *t; int error = 0; while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) { t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { rcu_read_lock(); if (t->dst && __sk_dst_get(sk) != t->dst) { dst_hold(t->dst); sk_setup_caps(sk, t->dst); } rcu_read_unlock(); error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) ctx->q->asoc->base.sk->sk_err = -error; } /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); } } /* Try to flush an outqueue. * * Description: Send everything in q which we legally can, subject to * congestion limitations. * * Note: This function can be called from multiple contexts so appropriate * locking concerns must be made. Today we use the sock lock to protect * this function. */ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_flush_ctx ctx = { .q = q, .transport = NULL, .transport_list = LIST_HEAD_INIT(ctx.transport_list), .asoc = q->asoc, .packet = NULL, .gfp = gfp, }; /* 6.10 Bundling * ... * When bundling control chunks with DATA chunks, an * endpoint MUST place control chunks first in the outbound * SCTP packet. The transmitter MUST transmit DATA chunks * within a SCTP packet in increasing order of TSN. * ... */ sctp_outq_flush_ctrl(&ctx); if (q->asoc->src_out_of_asoc_ok) goto sctp_flush_out; sctp_outq_flush_data(&ctx, rtx_timeout); sctp_flush_out: sctp_outq_flush_transports(&ctx); } /* Update unack_data based on the incoming SACK chunk */ static void sctp_sack_update_unack_data(struct sctp_association *assoc, struct sctp_sackhdr *sack) { union sctp_sack_variable *frags; __u16 unack_data; int i; unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1; frags = (union sctp_sack_variable *)(sack + 1); for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) { unack_data -= ((ntohs(frags[i].gab.end) - ntohs(frags[i].gab.start) + 1)); } assoc->unack_data = unack_data; } /* This is where we REALLY process a SACK. * * Process the SACK against the outqueue. Mostly, this just frees * things off the transmitted queue. */ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) { struct sctp_association *asoc = q->asoc; struct sctp_sackhdr *sack = chunk->subh.sack_hdr; struct sctp_transport *transport; struct sctp_chunk *tchunk = NULL; struct list_head *lchunk, *transport_list, *temp; __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; unsigned int outstanding; struct sctp_transport *primary = asoc->peer.primary_path; int count_of_newacks = 0; int gap_ack_blocks; u8 accum_moved = 0; /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; /* SCTP path tracepoint for congestion control debugging. */ if (trace_sctp_probe_path_enabled()) { list_for_each_entry(transport, transport_list, transports) trace_sctp_probe_path(transport, asoc); } sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; /* * SFR-CACC algorithm: * On receipt of a SACK the sender SHOULD execute the * following statements. * * 1) If the cumulative ack in the SACK passes next tsn_at_change * on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be * cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for * all destinations. * 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE * is set the receiver of the SACK MUST take the following actions: * * A) Initialize the cacc_saw_newack to 0 for all destination * addresses. * * Only bother if changeover_active is set. Otherwise, this is * totally suboptimal to do on every SACK. */ if (primary->cacc.changeover_active) { u8 clear_cycling = 0; if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) { primary->cacc.changeover_active = 0; clear_cycling = 1; } if (clear_cycling || gap_ack_blocks) { list_for_each_entry(transport, transport_list, transports) { if (clear_cycling) transport->cacc.cycling_changeover = 0; if (gap_ack_blocks) transport->cacc.cacc_saw_newack = 0; } } } /* Get the highest TSN in the sack. */ highest_tsn = sack_ctsn; if (gap_ack_blocks) { union sctp_sack_variable *frags = (union sctp_sack_variable *)(sack + 1); highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end); } if (TSN_lt(asoc->highest_sacked, highest_tsn)) asoc->highest_sacked = highest_tsn; highest_new_tsn = sack_ctsn; /* Run through the retransmit queue. Credit bytes received * and free those chunks that we can. */ sctp_check_transmitted(q, &q->retransmit, NULL, NULL, sack, &highest_new_tsn); /* Run through the transmitted queue. * Credit bytes received and free those chunks which we can. * * This is a MASSIVE candidate for optimization. */ list_for_each_entry(transport, transport_list, transports) { sctp_check_transmitted(q, &transport->transmitted, transport, &chunk->source, sack, &highest_new_tsn); /* * SFR-CACC algorithm: * C) Let count_of_newacks be the number of * destinations for which cacc_saw_newack is set. */ if (transport->cacc.cacc_saw_newack) count_of_newacks++; } /* Move the Cumulative TSN Ack Point if appropriate. */ if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) { asoc->ctsn_ack_point = sack_ctsn; accum_moved = 1; } if (gap_ack_blocks) { if (asoc->fast_recovery && accum_moved) highest_new_tsn = highest_tsn; list_for_each_entry(transport, transport_list, transports) sctp_mark_missing(q, &transport->transmitted, transport, highest_new_tsn, count_of_newacks); } /* Update unack_data field in the assoc. */ sctp_sack_update_unack_data(asoc, sack); ctsn = asoc->ctsn_ack_point; /* Throw away stuff rotting on the sack queue. */ list_for_each_safe(lchunk, temp, &q->sacked) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(tchunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(&tchunk->transmitted_list); if (asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) asoc->sent_cnt_removable--; sctp_chunk_free(tchunk); } } /* ii) Set rwnd equal to the newly received a_rwnd minus the * number of bytes still outstanding after processing the * Cumulative TSN Ack and the Gap Ack Blocks. */ sack_a_rwnd = ntohl(sack->a_rwnd); asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) sack_a_rwnd -= outstanding; else sack_a_rwnd = 0; asoc->peer.rwnd = sack_a_rwnd; asoc->stream.si->generate_ftsn(q, sack_ctsn); pr_debug("%s: sack cumulative tsn ack:0x%x\n", __func__, sack_ctsn); pr_debug("%s: cumulative tsn ack of assoc:%p is 0x%x, " "advertised peer ack point:0x%x\n", __func__, asoc, ctsn, asoc->adv_peer_ack_point); return sctp_outq_is_empty(q); } /* Is the outqueue empty? * The queue is empty when we have not pending data, no in-flight data * and nothing pending retransmissions. */ int sctp_outq_is_empty(const struct sctp_outq *q) { return q->out_qlen == 0 && q->outstanding_bytes == 0 && list_empty(&q->retransmit); } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Go through a transport's transmitted list or the association's retransmit * list and move chunks that are acked by the Cumulative TSN Ack to q->sacked. * The retransmit list will not have an associated transport. * * I added coherent debug information output. --xguo * * Instead of printing 'sacked' or 'kept' for each TSN on the * transmitted_queue, we print a range: SACKED: TSN1-TSN2, TSN3, TSN4-TSN5. * KEPT TSN6-TSN7, etc. */ static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn_in_sack) { struct list_head *lchunk; struct sctp_chunk *tchunk; struct list_head tlist; __u32 tsn; __u32 sack_ctsn; __u32 rtt; __u8 restart_timer = 0; int bytes_acked = 0; int migrate_bytes = 0; bool forward_progress = false; sack_ctsn = ntohl(sack->cum_tsn_ack); INIT_LIST_HEAD(&tlist); /* The while loop will skip empty transmitted queues. */ while (NULL != (lchunk = sctp_list_dequeue(transmitted_queue))) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); if (sctp_chunk_abandoned(tchunk)) { /* Move the chunk to abandoned list. */ sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ if (transmitted_queue != &q->retransmit && !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); q->outstanding_bytes -= sctp_data_size(tchunk); } continue; } tsn = ntohl(tchunk->subh.data_hdr->tsn); if (sctp_acked(sack, tsn)) { /* If this queue is the retransmit queue, the * retransmit timer has already reclaimed * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. * * 6.3.1 C5) Karn's algorithm: RTT measurements * MUST NOT be made using packets that were * retransmitted (and thus for which it is * ambiguous whether the reply was for the * first instance of the packet or a later * instance). */ if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } if (TSN_lte(tsn, sack_ctsn)) { /* * SFR-CACC algorithm: * 2) If the SACK contains gap acks * and the flag CHANGEOVER_ACTIVE is * set the receiver of the SACK MUST * take the following action: * * B) For each TSN t being acked that * has not been acked in any SACK so * far, set cacc_saw_newack to 1 for * the destination that the TSN was * sent to. */ if (sack->num_gap_ack_blocks && q->asoc->peer.primary_path->cacc. changeover_active) transport->cacc.cacc_saw_newack = 1; } } /* If the chunk hasn't been marked as ACKED, * mark it and account bytes_acked if the * chunk had a valid transport (it will not * have a transport if ASCONF had deleted it * while DATA was outstanding). */ if (!tchunk->tsn_gap_acked) { tchunk->tsn_gap_acked = 1; if (TSN_lt(*highest_new_tsn_in_sack, tsn)) *highest_new_tsn_in_sack = tsn; bytes_acked += sctp_data_size(tchunk); if (!tchunk->transport) migrate_bytes += sctp_data_size(tchunk); forward_progress = true; } if (TSN_lte(tsn, sack_ctsn)) { /* RFC 2960 6.3.2 Retransmission Timer Rules * * R3) Whenever a SACK is received * that acknowledges the DATA chunk * with the earliest outstanding TSN * for that address, restart T3-rtx * timer for that address with its * current RTO. */ restart_timer = 1; forward_progress = true; list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { /* RFC2960 7.2.4, sctpimpguide-05 2.8.2 * M2) Each time a SACK arrives reporting * 'Stray DATA chunk(s)' record the highest TSN * reported as newly acknowledged, call this * value 'HighestTSNinSack'. A newly * acknowledged DATA chunk is one not * previously acknowledged in a SACK. * * When the SCTP sender of data receives a SACK * chunk that acknowledges, for the first time, * the receipt of a DATA chunk, all the still * unacknowledged DATA chunks whose TSN is * older than that newly acknowledged DATA * chunk, are qualified as 'Stray DATA chunks'. */ list_add_tail(lchunk, &tlist); } } else { if (tchunk->tsn_gap_acked) { pr_debug("%s: receiver reneged on data TSN:0x%x\n", __func__, tsn); tchunk->tsn_gap_acked = 0; if (tchunk->transport) bytes_acked -= sctp_data_size(tchunk); /* RFC 2960 6.3.2 Retransmission Timer Rules * * R4) Whenever a SACK is received missing a * TSN that was previously acknowledged via a * Gap Ack Block, start T3-rtx for the * destination address to which the DATA * chunk was originally * transmitted if it is not already running. */ restart_timer = 1; } list_add_tail(lchunk, &tlist); } } if (transport) { if (bytes_acked) { struct sctp_association *asoc = transport->asoc; /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never * send on this transport and shouldn't be * credited to this transport. */ bytes_acked -= migrate_bytes; /* 8.2. When an outstanding TSN is acknowledged, * the endpoint shall clear the error counter of * the destination transport address to which the * DATA chunk was last sent. * The association's overall error counter is * also cleared. */ transport->error_count = 0; transport->asoc->overall_error_count = 0; forward_progress = true; /* * While in SHUTDOWN PENDING, we may have started * the T5 shutdown guard timer after reaching the * retransmission limit. Stop that timer as soon * as the receiver acknowledged any data. */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && del_timer(&asoc->timers [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) sctp_association_put(asoc); /* Mark the destination transport address as * active if it is not so marked. */ if ((transport->state == SCTP_INACTIVE || transport->state == SCTP_UNCONFIRMED) && sctp_cmp_addr_exact(&transport->ipaddr, saddr)) { sctp_assoc_control_transport( transport->asoc, transport, SCTP_TRANSPORT_UP, SCTP_RECEIVED_SACK); } sctp_transport_raise_cwnd(transport, sack_ctsn, bytes_acked); transport->flight_size -= bytes_acked; if (transport->flight_size == 0) transport->partial_bytes_acked = 0; q->outstanding_bytes -= bytes_acked + migrate_bytes; } else { /* RFC 2960 6.1, sctpimpguide-06 2.15.2 * When a sender is doing zero window probing, it * should not timeout the association if it continues * to receive new packets from the receiver. The * reason is that the receiver MAY keep its window * closed for an indefinite time. * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. * * Allow the association to timeout while in SHUTDOWN * PENDING or SHUTDOWN RECEIVED in case the receiver * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && (sack_ctsn+2 == q->asoc->next_tsn) && q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { pr_debug("%s: sack received for zero window " "probe:%u\n", __func__, sack_ctsn); q->asoc->overall_error_count = 0; transport->error_count = 0; } } /* RFC 2960 6.3.2 Retransmission Timer Rules * * R2) Whenever all outstanding data sent to an address have * been acknowledged, turn off the T3-rtx timer of that * address. */ if (!transport->flight_size) { if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } if (forward_progress) { if (transport->dst) sctp_transport_dst_confirm(transport); } } list_splice(&tlist, transmitted_queue); } /* Mark chunks as missing and consequently may get retransmitted. */ static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn_in_sack, int count_of_newacks) { struct sctp_chunk *chunk; __u32 tsn; char do_fast_retransmit = 0; struct sctp_association *asoc = q->asoc; struct sctp_transport *primary = asoc->peer.primary_path; list_for_each_entry(chunk, transmitted_queue, transmitted_list) { tsn = ntohl(chunk->subh.data_hdr->tsn); /* RFC 2960 7.2.4, sctpimpguide-05 2.8.2 M3) Examine all * 'Unacknowledged TSN's', if the TSN number of an * 'Unacknowledged TSN' is smaller than the 'HighestTSNinSack' * value, increment the 'TSN.Missing.Report' count on that * chunk if it has NOT been fast retransmitted or marked for * fast retransmit already. */ if (chunk->fast_retransmit == SCTP_CAN_FRTX && !chunk->tsn_gap_acked && TSN_lt(tsn, highest_new_tsn_in_sack)) { /* SFR-CACC may require us to skip marking * this chunk as missing. */ if (!transport || !sctp_cacc_skip(primary, chunk->transport, count_of_newacks, tsn)) { chunk->tsn_missing_report++; pr_debug("%s: tsn:0x%x missing counter:%d\n", __func__, tsn, chunk->tsn_missing_report); } } /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = SCTP_NEED_FRTX; do_fast_retransmit = 1; } } if (transport) { if (do_fast_retransmit) sctp_retransmit(q, transport, SCTP_RTXR_FAST_RTX); pr_debug("%s: transport:%p, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } } /* Is the given TSN acked by this packet? */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) { __u32 ctsn = ntohl(sack->cum_tsn_ack); union sctp_sack_variable *frags; __u16 tsn_offset, blocks; int i; if (TSN_lte(tsn, ctsn)) goto pass; /* 3.3.4 Selective Acknowledgment (SACK) (3): * * Gap Ack Blocks: * These fields contain the Gap Ack Blocks. They are repeated * for each Gap Ack Block up to the number of Gap Ack Blocks * defined in the Number of Gap Ack Blocks field. All DATA * chunks with TSNs greater than or equal to (Cumulative TSN * Ack + Gap Ack Block Start) and less than or equal to * (Cumulative TSN Ack + Gap Ack Block End) of each Gap Ack * Block are assumed to have been received correctly. */ frags = (union sctp_sack_variable *)(sack + 1); blocks = ntohs(sack->num_gap_ack_blocks); tsn_offset = tsn - ctsn; for (i = 0; i < blocks; ++i) { if (tsn_offset >= ntohs(frags[i].gab.start) && tsn_offset <= ntohs(frags[i].gab.end)) goto pass; } return 0; pass: return 1; } static inline int sctp_get_skip_pos(struct sctp_fwdtsn_skip *skiplist, int nskips, __be16 stream) { int i; for (i = 0; i < nskips; i++) { if (skiplist[i].stream == stream) return i; } return i; } /* Create and add a fwdtsn chunk to the outq's control queue if needed. */ void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct sctp_fwdtsn_skip ftsn_skip_arr[10]; int nskips = 0; int skip_pos = 0; __u32 tsn; struct sctp_chunk *chunk; struct list_head *lchunk, *temp; if (!asoc->peer.prsctp_capable) return; /* PR-SCTP C1) Let SackCumAck be the Cumulative TSN ACK carried in the * received SACK. * * If (Advanced.Peer.Ack.Point < SackCumAck), then update * Advanced.Peer.Ack.Point to be equal to SackCumAck. */ if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; /* PR-SCTP C2) Try to further advance the "Advanced.Peer.Ack.Point" * locally, that is, to move "Advanced.Peer.Ack.Point" up as long as * the chunk next in the out-queue space is marked as "abandoned" as * shown in the following example: * * Assuming that a SACK arrived with the Cumulative TSN ACK 102 * and the Advanced.Peer.Ack.Point is updated to this value: * * out-queue at the end of ==> out-queue after Adv.Ack.Point * normal SACK processing local advancement * ... ... * Adv.Ack.Pt-> 102 acked 102 acked * 103 abandoned 103 abandoned * 104 abandoned Adv.Ack.P-> 104 abandoned * 105 105 * 106 acked 106 acked * ... ... * * In this example, the data sender successfully advanced the * "Advanced.Peer.Ack.Point" from 102 to 104 locally. */ list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); /* Remove any chunks in the abandoned queue that are acked by * the ctsn. */ if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else { if (TSN_lte(tsn, asoc->adv_peer_ack_point+1)) { asoc->adv_peer_ack_point = tsn; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) continue; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, chunk->subh.data_hdr->stream); ftsn_skip_arr[skip_pos].stream = chunk->subh.data_hdr->stream; ftsn_skip_arr[skip_pos].ssn = chunk->subh.data_hdr->ssn; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else break; } } /* PR-SCTP C3) If, after step C1 and C2, the "Advanced.Peer.Ack.Point" * is greater than the Cumulative TSN ACK carried in the received * SACK, the data sender MUST send the data receiver a FORWARD TSN * chunk containing the latest value of the * "Advanced.Peer.Ack.Point". * * C4) For each "abandoned" TSN the sender of the FORWARD TSN SHOULD * list each stream and sequence number in the forwarded TSN. This * information will enable the receiver to easily find any * stranded TSN's waiting on stream reorder queues. Each stream * SHOULD only be reported once; this means that if multiple * abandoned messages occur in the same stream then only the * highest abandoned stream sequence number is reported. If the * total size of the FORWARD TSN does NOT fit in a single MTU then * the sender of the FORWARD TSN SHOULD lower the * Advanced.Peer.Ack.Point to the last TSN that will fit in a * single MTU. */ if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_fwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } |
| 145 145 14 14 13 14 14 14 14 14 14 14 14 14 7 7 7 7 7 7 7 148 147 17 17 259 1392 1392 1693 1694 1694 1865 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/iversion.h> #include <linux/writeback.h> #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/uaccess.h> #include "internal.h" int simple_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); const struct dentry_operations simple_dentry_operations = { .d_delete = always_delete_dentry, }; EXPORT_SYMBOL(simple_dentry_operations); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_sb->s_d_op) d_set_d_op(dentry, &simple_dentry_operations); d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while (*p) { struct dentry *d = hlist_entry(*p, struct dentry, d_sib); p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { if (!hlist_unhashed(&cursor->d_sib)) __hlist_del(&cursor->d_sib); hlist_add_behind(&cursor->d_sib, &d->d_sib); p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (to) hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct dentry *next = NULL; struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = &dentry->d_children.first; else p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; p = &next->d_sib.next; } spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (next) hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); static void offset_set(struct dentry *dentry, u32 offset) { dentry->d_fsdata = (void *)((uintptr_t)(offset)); } static u32 dentry2offset(struct dentry *dentry) { return (u32)((uintptr_t)(dentry->d_fsdata)); } static struct lock_class_key simple_offset_xa_lock; /** * simple_offset_init - initialize an offset_ctx * @octx: directory offset map to be initialized * */ void simple_offset_init(struct offset_ctx *octx) { xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1); lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock); /* 0 is '.', 1 is '..', so always start with offset 2 */ octx->next_offset = 2; } /** * simple_offset_add - Add an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: new dentry being added * * Returns zero on success. @so_ctx and the dentry offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { static const struct xa_limit limit = XA_LIMIT(2, U32_MAX); u32 offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit, &octx->next_offset, GFP_KERNEL); if (ret < 0) return ret; offset_set(dentry, offset); return 0; } /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: dentry being removed * */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { u32 offset; offset = dentry2offset(dentry); if (offset == 0) return; xa_erase(&octx->xa, offset); offset_set(dentry, 0); } /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved * @old_dentry: dentry being moved * @new_dir: destination parent * @new_dentry: destination dentry * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); u32 old_index = dentry2offset(old_dentry); u32 new_index = dentry2offset(new_dentry); int ret; simple_offset_remove(old_ctx, old_dentry); simple_offset_remove(new_ctx, new_dentry); ret = simple_offset_add(new_ctx, old_dentry); if (ret) goto out_restore; ret = simple_offset_add(old_ctx, new_dentry); if (ret) { simple_offset_remove(new_ctx, old_dentry); goto out_restore; } ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (ret) { simple_offset_remove(new_ctx, old_dentry); simple_offset_remove(old_ctx, new_dentry); goto out_restore; } return 0; out_restore: offset_set(old_dentry, old_index); xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL); offset_set(new_dentry, new_index); xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL); return ret; } /** * simple_offset_destroy - Release offset map * @octx: directory offset ctx that is about to be destroyed * * During fs teardown (eg. umount), a directory's offset map might still * contain entries. xa_destroy() cleans out anything that remains. */ void simple_offset_destroy(struct offset_ctx *octx) { xa_destroy(&octx->xa); } /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated * @offset: a byte offset * @whence: enumerator describing the starting position for this update * * SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories. * * Returns the updated read position if successful; otherwise a * negative errno is returned and the read position remains unchanged. */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_CUR: offset += file->f_pos; fallthrough; case SEEK_SET: if (offset >= 0) break; fallthrough; default: return -EINVAL; } /* In this case, ->private_data is protected by f_pos_lock */ file->private_data = NULL; return vfs_setpos(file, offset, U32_MAX); } static struct dentry *offset_find_next(struct xa_state *xas) { struct dentry *child, *found = NULL; rcu_read_lock(); child = xas_next_entry(xas, U32_MAX); if (!child) goto out; spin_lock(&child->d_lock); if (simple_positive(child)) found = dget_dlock(child); spin_unlock(&child->d_lock); out: rcu_read_unlock(); return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { u32 offset = dentry2offset(dentry); struct inode *inode = d_inode(dentry); return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode); XA_STATE(xas, &so_ctx->xa, ctx->pos); struct dentry *dentry; while (true) { dentry = offset_find_next(&xas); if (!dentry) return ERR_PTR(-ENOENT); if (!offset_dir_emit(ctx, dentry)) { dput(dentry); break; } dput(dentry); ctx->pos = xas.xa_index + 1; } return NULL; } /** * offset_readdir - Emit entries starting at offset @ctx->pos * @file: an open directory to iterate over * @ctx: directory iteration context * * Caller must hold @file's i_rwsem to prevent insertion or removal of * entries during this call. * * On entry, @ctx->pos contains an offset that represents the first entry * to be read from the directory. * * The operation continues until there are no more entries to read, or * until the ctx->actor indicates there is no more space in the caller's * output buffer. * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. * * Return values: * %0 - Complete */ static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; /* In this case, ->private_data is protected by f_pos_lock */ if (ctx->pos == 2) file->private_data = NULL; else if (file->private_data == ERR_PTR(-ENOENT)) return 0; file->private_data = offset_iterate_dir(d_inode(dir), ctx); return 0; } const struct file_operations simple_offset_dir_operations = { .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, .fsync = noop_fsync, }; static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); d = prev ? d_next_sibling(prev) : d_first_child(parent); hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock(inode); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode_set_ctime_current(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; inode_lock(inode); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (d_is_dir(victim)) fsnotify_rmdir(inode, victim); else fsnotify_unlink(inode, victim); if (callback) callback(victim); dput(victim); // unpin it } if (victim == dentry) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } EXPORT_SYMBOL(simple_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; s->s_d_op = ctx->dops; return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock); hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); goto out; } spin_unlock(&child->d_lock); } ret = 1; out: spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(simple_empty); int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); dput(dentry); return 0; } EXPORT_SYMBOL(simple_unlink); int simple_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); simple_unlink(dir, dentry); drop_nlink(dir); return 0; } EXPORT_SYMBOL(simple_rmdir); /** * simple_rename_timestamp - update the various inode timestamps for rename * @old_dir: old parent directory * @old_dentry: dentry that is being renamed * @new_dir: new parent directory * @new_dentry: target for rename * * POSIX mandates that the old and new parent directories have their ctime and * mtime updated, and that inodes of @old_dentry and @new_dentry (if any), have * their ctime updated. */ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode *newino = d_inode(new_dentry); inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); } EXPORT_SYMBOL_GPL(simple_rename_timestamp); int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL_GPL(simple_rename_exchange); int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int they_are_dirs = d_is_dir(old_dentry); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; if (flags & RENAME_EXCHANGE) return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (d_really_is_positive(new_dentry)) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem * @idmap: idmap of the target mount * @dentry: dentry * @iattr: iattr structure * * Returns 0 on success, -error on failure. * * simple_setattr is a simple ->setattr implementation without a proper * implementation of size changes. * * It can either be used for in-memory filesystems or special files * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; error = setattr_prepare(idmap, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); setattr_copy(idmap, inode, iattr); mark_inode_dirty(inode); return 0; } EXPORT_SYMBOL(simple_setattr); static int simple_read_folio(struct file *file, struct folio *folio) { folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); folio_unlock(folio); return 0; } int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct folio *folio; folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); *pagep = &folio->page; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); folio_zero_segments(folio, 0, from, from + len, folio_size(folio)); } return 0; } EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " * @copied: " * @page: " * @fsdata: " * * simple_write_end does the minimum needed for updating a page after writing is * done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_mutex is assumed to be held. * Block based filesystems should use generic_write_end(). * NOTE: Even though i_size might get updated by this function, mark_inode_dirty * is not called, so a filesystem that actually does store data in .write_inode * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * * Use *ONLY* with simple_read_folio() */ static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct folio *folio = page_folio(page); struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; /* zero the stale part of the folio if we did a short copy */ if (!folio_test_uptodate(folio)) { if (copied < len) { size_t from = offset_in_folio(folio, pos); folio_zero_range(folio, from + copied, len - copied); } folio_mark_uptodate(folio); } /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold the i_mutex. */ if (last_pos > inode->i_size) i_size_write(inode, last_pos); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } /* * Provides ramfs-style behavior: data in the pagecache, but no writeback. */ const struct address_space_operations ram_aops = { .read_folio = simple_read_folio, .write_begin = simple_write_begin, .write_end = simple_write_end, .dirty_folio = noop_dirty_folio, }; EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate * unique inode values later for this filesystem, then you must take care * to pass it an appropriate max_reserved value to avoid collisions. */ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; struct dentry *dentry; int i; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; inode = new_inode(s); if (!inode) return -ENOMEM; /* * because the root inode is 1, the files array must not contain an * entry at index 1 */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); s->s_root = d_make_root(inode); if (!s->s_root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) continue; /* warn if it tries to conflict with the root inode */ if (unlikely(i == 1)) printk(KERN_WARNING "%s: %s passed in a files array" "with an index of 1!\n", __func__, s->s_type->name); dentry = d_alloc_name(s->s_root, files->name); if (!dentry) return -ENOMEM; inode = new_inode(s); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_mode = S_IFREG | files->mode; simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); } return 0; } EXPORT_SYMBOL(simple_fill_super); static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; } mntget(*mount); ++*count; spin_unlock(&pin_fs_lock); mntput(mnt); return 0; } EXPORT_SYMBOL(simple_pin_fs); void simple_release_fs(struct vfsmount **mount, int *count) { struct vfsmount *mnt; spin_lock(&pin_fs_lock); mnt = *mount; if (!--*count) *mount = NULL; spin_unlock(&pin_fs_lock); mntput(mnt); } EXPORT_SYMBOL(simple_release_fs); /** * simple_read_from_buffer - copy data from the buffer to user space * @to: the user space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The simple_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the user space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; size_t ret; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; ret = copy_to_user(to, from + pos, count); if (ret == count) return -EFAULT; count -= ret; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_read_from_buffer); /** * simple_write_to_buffer - copy data from user space to the buffer * @to: the buffer to write to * @available: the size of the buffer * @ppos: the current position in the buffer * @from: the user space buffer to read from * @count: the maximum number of bytes to read * * The simple_write_to_buffer() function reads up to @count bytes from the user * space address starting at @from into the buffer @to at offset @ppos. * * On success, the number of bytes written is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count) { loff_t pos = *ppos; size_t res; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; res = copy_from_user(to + pos, from, count); if (res == count) return -EFAULT; count -= res; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_write_to_buffer); /** * memory_read_from_buffer - copy data from the buffer * @to: the kernel space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The memory_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the kernel space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; if (pos < 0) return -EINVAL; if (pos >= available) return 0; if (count > available - pos) count = available - pos; memcpy(to, from + pos, count); *ppos = pos + count; return count; } EXPORT_SYMBOL(memory_read_from_buffer); /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then * possibly a read which collects the result - which is stored in a * file-local buffer. */ void simple_transaction_set(struct file *file, size_t n) { struct simple_transaction_argresp *ar = file->private_data; BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); /* * The barrier ensures that ar->size will really remain zero until * ar->data is ready for reading. */ smp_mb(); ar->size = n; } EXPORT_SYMBOL(simple_transaction_set); char *simple_transaction_get(struct file *file, const char __user *buf, size_t size) { struct simple_transaction_argresp *ar; static DEFINE_SPINLOCK(simple_transaction_lock); if (size > SIMPLE_TRANSACTION_LIMIT - 1) return ERR_PTR(-EFBIG); ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL); if (!ar) return ERR_PTR(-ENOMEM); spin_lock(&simple_transaction_lock); /* only one write allowed per open */ if (file->private_data) { spin_unlock(&simple_transaction_lock); free_page((unsigned long)ar); return ERR_PTR(-EBUSY); } file->private_data = ar; spin_unlock(&simple_transaction_lock); if (copy_from_user(ar->data, buf, size)) return ERR_PTR(-EFAULT); return ar->data; } EXPORT_SYMBOL(simple_transaction_get); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { struct simple_transaction_argresp *ar = file->private_data; if (!ar) return 0; return simple_read_from_buffer(buf, size, pos, ar->data, ar->size); } EXPORT_SYMBOL(simple_transaction_read); int simple_transaction_release(struct inode *inode, struct file *file) { free_page((unsigned long)file->private_data); return 0; } EXPORT_SYMBOL(simple_transaction_release); /* Simple attribute files */ struct simple_attr { int (*get)(void *, u64 *); int (*set)(void *, u64); char get_buf[24]; /* enough to store a u64 and "\n\0" */ char set_buf[24]; void *data; const char *fmt; /* format for read operation */ struct mutex mutex; /* protects access to these buffers */ }; /* simple_attr_open is called by an actual attribute open file operation * to set the attribute specific access operations. */ int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { struct simple_attr *attr; attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) return -ENOMEM; attr->get = get; attr->set = set; attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); file->private_data = attr; return nonseekable_open(inode, file); } EXPORT_SYMBOL_GPL(simple_attr_open); int simple_attr_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */ /* read from the buffer that is filled with the get function */ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; size_t size; ssize_t ret; attr = file->private_data; if (!attr->get) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; if (*ppos && attr->get_buf[0]) { /* continued read */ size = strlen(attr->get_buf); } else { /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) goto out; size = scnprintf(attr->get_buf, sizeof(attr->get_buf), attr->fmt, (unsigned long long)val); } ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size); out: mutex_unlock(&attr->mutex); return ret; } EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; size_t size; ssize_t ret; attr = file->private_data; if (!attr->set) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; ret = -EFAULT; size = min(sizeof(attr->set_buf) - 1, len); if (copy_from_user(attr->set_buf, buf, size)) goto out; attr->set_buf[size] = '\0'; if (is_signed) ret = kstrtoll(attr->set_buf, 0, &val); else ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ out: mutex_unlock(&attr->mutex); return ret; } ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(simple_attr_write); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(simple_attr_write_signed); /** * generic_encode_ino32_fh - generic export_operations->encode_fh function * @inode: the object to encode * @fh: where to store the file handle fragment * @max_len: maximum length to store there (in 4 byte units) * @parent: parent directory inode, if wanted * * This generic encode_fh function assumes that the 32 inode number * is suitable for locating an inode, and that the generation number * can be used to check that it is still valid. It places them in the * filehandle fragment where export_decode_fh expects to find them. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent) { struct fid *fid = (void *)fh; int len = *max_len; int type = FILEID_INO32_GEN; if (parent && (len < 4)) { *max_len = 4; return FILEID_INVALID; } else if (len < 2) { *max_len = 2; return FILEID_INVALID; } len = 2; fid->i32.ino = inode->i_ino; fid->i32.gen = inode->i_generation; if (parent) { fid->i32.parent_ino = parent->i_ino; fid->i32.parent_gen = parent->i_generation; len = 4; type = FILEID_INO32_GEN_PARENT; } *max_len = len; return type; } EXPORT_SYMBOL_GPL(generic_encode_ino32_fh); /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the object specified in the file handle. */ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.ino, fid->i32.gen); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); /** * generic_fh_to_parent - generic helper for the fh_to_parent export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the _parent_ object specified in the file handle if it * is specified in the file handle, or NULL otherwise. */ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len <= 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.parent_ino, (fh_len > 3 ? fid->i32.parent_gen : 0)); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** * __generic_file_fsync - generic fsync implementation for simple filesystems * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; inode_lock(inode); ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: inode_unlock(inode); /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(__generic_file_fsync); /** * generic_file_fsync - generic fsync implementation for simple filesystems * with flush * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * */ int generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; err = __generic_file_fsync(file, start, end, datasync); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev); } EXPORT_SYMBOL(generic_file_fsync); /** * generic_check_addressable - Check addressability of file system * @blocksize_bits: log of file system block size * @num_blocks: number of blocks in file system * * Determine whether a file system with @num_blocks blocks (and a * block size of 2**@blocksize_bits) is addressable by the sector_t * and page cache of the system. Return 0 if so and -EFBIG otherwise. */ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page = last_fs_block >> (PAGE_SHIFT - blocksize_bits); if (unlikely(num_blocks == 0)) return 0; if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT)) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { return -EFBIG; } return 0; } EXPORT_SYMBOL(generic_check_addressable); /* * No-op implementation of ->fsync for in-memory filesystems. */ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return 0; } EXPORT_SYMBOL(noop_fsync); ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* * iomap based filesystems support direct I/O without need for * this callback. However, it still needs to be set in * inode->a_ops so that open/fcntl know that direct I/O is * generally supported. */ return -EINVAL; } EXPORT_SYMBOL_GPL(noop_direct_IO); /* Because kfree isn't assignment-compatible with void(void*) ;-/ */ void kfree_link(void *p) { kfree(p); } EXPORT_SYMBOL(kfree_link); struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { .dirty_folio = noop_dirty_folio, }; struct inode *inode = new_inode_pseudo(s); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &anon_aops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); /** * simple_nosetlease - generic helper for prohibiting leases * @filp: file pointer * @arg: type of lease to obtain * @flp: new lease supplied for insertion * @priv: private data for lm_setup operation * * Generic helper for filesystems that do not wish to allow leases to be set. * All arguments are ignored and it just returns -EINVAL. */ int simple_nosetlease(struct file *filp, int arg, struct file_lock **flp, void **priv) { return -EINVAL; } EXPORT_SYMBOL(simple_nosetlease); /** * simple_get_link - generic helper to get the target of "fast" symlinks * @dentry: not used here * @inode: the symlink inode * @done: not used here * * Generic helper for filesystems to use for symlink inodes where a pointer to * the symlink target is stored in ->i_link. NOTE: this isn't normally called, * since as an optimization the path lookup code uses any non-NULL ->i_link * directly, without calling ->get_link(). But ->get_link() still must be set, * to mark the inode_operations as being for a symlink. * * Return: the symlink target */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return inode->i_link; } EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { .get_link = simple_get_link, }; EXPORT_SYMBOL(simple_symlink_inode_operations); /* * Operations for a permanently empty directory. */ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-ENOENT); } static int empty_dir_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } static int empty_dir_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EPERM; } static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) { return -EOPNOTSUPP; } static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, .permission = generic_permission, .setattr = empty_dir_setattr, .getattr = empty_dir_getattr, .listxattr = empty_dir_listxattr, }; static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) { /* An empty directory has two entries . and .. at offsets 0 and 1 */ return generic_file_llseek_size(file, offset, whence, 2, 2); } static int empty_dir_readdir(struct file *file, struct dir_context *ctx) { dir_emit_dots(file, ctx); return 0; } static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; void make_empty_dir_inode(struct inode *inode) { set_nlink(inode, 2); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; inode->i_op = &empty_dir_inode_operations; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &empty_dir_operations; } bool is_empty_dir_inode(struct inode *inode) { return (inode->i_fop == &empty_dir_operations) && (inode->i_op == &empty_dir_inode_operations); } #if IS_ENABLED(CONFIG_UNICODE) /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against * @len: len of name of dentry * @str: str pointer to name of dentry * @name: Name to compare against * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const struct dentry *parent = READ_ONCE(dentry->d_parent); const struct inode *dir = READ_ONCE(parent->d_inode); const struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; struct qstr qstr = QSTR_INIT(str, len); char strbuf[DNAME_INLINE_LEN]; int ret; if (!dir || !IS_CASEFOLDED(dir)) goto fallback; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. */ if (len <= DNAME_INLINE_LEN - 1) { memcpy(strbuf, str, len); strbuf[len] = 0; qstr.name = strbuf; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } ret = utf8_strncasecmp(um, name, &qstr); if (ret >= 0) return ret; if (sb_has_strict_encoding(sb)) return -EINVAL; fallback: if (len != name->len) return 1; return !!memcmp(str, name->name, len); } /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems * @dentry: dentry of the parent directory * @str: qstr of name whose hash we should fill in * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; int ret = 0; if (!dir || !IS_CASEFOLDED(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); if (ret < 0 && sb_has_strict_encoding(sb)) return -EINVAL; return 0; } static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, }; #endif #ifdef CONFIG_FS_ENCRYPTION static const struct dentry_operations generic_encrypted_dentry_ops = { .d_revalidate = fscrypt_d_revalidate, }; #endif #if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) static const struct dentry_operations generic_encrypted_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, .d_revalidate = fscrypt_d_revalidate, }; #endif /** * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry * @dentry: dentry to set ops on * * Casefolded directories need d_hash and d_compare set, so that the dentries * contained in them are handled case-insensitively. Note that these operations * are needed on the parent directory rather than on the dentries in it, and * while the casefolding flag can be toggled on and off on an empty directory, * dentry_operations can't be changed later. As a result, if the filesystem has * casefolding support enabled at all, we have to give all dentries the * casefolding operations even if their inode doesn't have the casefolding flag * currently (and thus the casefolding ops would be no-ops for now). * * Encryption works differently in that the only dentry operation it needs is * d_revalidate, which it only needs on dentries that have the no-key name flag. * The no-key flag can't be set "later", so we don't have to worry about that. * * Finally, to maximize compatibility with overlayfs (which isn't compatible * with certain dentry operations) and to avoid taking an unnecessary * performance hit, we use custom dentry_operations for each possible * combination rather than always installing all operations. */ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) { #ifdef CONFIG_FS_ENCRYPTION bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME; #endif #if IS_ENABLED(CONFIG_UNICODE) bool needs_ci_ops = dentry->d_sb->s_encoding; #endif #if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) if (needs_encrypt_ops && needs_ci_ops) { d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops); return; } #endif #ifdef CONFIG_FS_ENCRYPTION if (needs_encrypt_ops) { d_set_d_op(dentry, &generic_encrypted_dentry_ops); return; } #endif #if IS_ENABLED(CONFIG_UNICODE) if (needs_ci_ops) { d_set_d_op(dentry, &generic_ci_dentry_ops); return; } #endif } EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops); /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * Here, we add full memory barriers to ensure that any de-facto * ordering with other info is preserved. * * This barrier pairs with the barrier in inode_query_iversion() */ smp_mb(); cur = inode_peek_iversion_raw(inode); do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ u64 inode_query_iversion(struct inode *inode) { u64 cur, new; cur = inode_peek_iversion_raw(inode); do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* * This barrier (and the implicit barrier in the * cmpxchg below) pairs with the barrier in * inode_maybe_inc_iversion(). */ smp_mb(); break; } new = cur | I_VERSION_QUERIED; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } EXPORT_SYMBOL(inode_query_iversion); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos - buffered_written; loff_t end = iocb->ki_pos - 1; int err; /* * If the buffered write fallback returned an error, we want to return * the number of bytes which were written by direct I/O, or the error * code if that was zero. * * Note that this differs from normal direct-io semantics, which will * return -EFOO even if some bytes were written. */ if (unlikely(buffered_written < 0)) { if (direct_written) return direct_written; return buffered_written; } /* * We need to ensure that the page cache pages are written to disk and * invalidated to preserve the expected O_DIRECT semantics. */ err = filemap_write_and_wait_range(mapping, pos, end); if (err < 0) { /* * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; } invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); /** * simple_inode_init_ts - initialize the timestamps for a new inode * @inode: inode to be initialized * * When a new inode is created, most filesystems set the timestamps to the * current time. Add a helper to do this. */ struct timespec64 simple_inode_init_ts(struct inode *inode) { struct timespec64 ts = inode_set_ctime_current(inode); inode_set_atime_to_ts(inode, ts); inode_set_mtime_to_ts(inode, ts); return ts; } EXPORT_SYMBOL(simple_inode_init_ts); |
| 1403 167 1422 1422 1420 1418 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/fsync.c * * Copyright (C) 1993 Stephen Tweedie (sct@redhat.com) * from * Copyright (C) 1992 Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * from * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds * * ext4fs fsync primitive * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Removed unnecessary code duplication for little endian machines * and excessive __inline__s. * Andi Kleen, 1997 * * Major simplications and cleanup - we only need to do the metadata, because * we can depend on generic_block_fdatasync() to sync the data blocks. */ #include <linux/time.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include "ext4.h" #include "ext4_jbd2.h" #include <trace/events/ext4.h> /* * If we're not journaling and this is a just-created file, we have to * sync our parent directory (if it was freshly created) since * otherwise it will only be written by writeback, leaving a huge * window during which a crash may lose the file. This may apply for * the parent directory's parent as well, and so on recursively, if * they are also freshly created. */ static int ext4_sync_parent(struct inode *inode) { struct dentry *dentry, *next; int ret = 0; if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) return 0; dentry = d_find_any_alias(inode); if (!dentry) return 0; while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); next = dget_parent(dentry); dput(dentry); dentry = next; inode = dentry->d_inode; /* * The directory inode may have gone through rmdir by now. But * the inode itself and its blocks are still allocated (we hold * a reference to the inode via its dentry), so it didn't go * through ext4_evict_inode()) and so we are safe to flush * metadata blocks and the inode. */ ret = sync_mapping_buffers(inode->i_mapping); if (ret) break; ret = sync_inode_metadata(inode, 1); if (ret) break; } dput(dentry); return ret; } static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end, int datasync, bool *needs_barrier) { struct inode *inode = file->f_inode; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) *needs_barrier = true; return ret; } static int ext4_fsync_journal(struct inode *inode, bool datasync, bool *needs_barrier) { struct ext4_inode_info *ei = EXT4_I(inode); journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; /* * Fastcommit does not really support fsync on directories or other * special files. Force a full commit. */ if (!S_ISREG(inode->i_mode)) return ext4_force_commit(inode->i_sb); if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) *needs_barrier = true; return ext4_fc_commit(journal, commit_tid); } /* * akpm: A new design for ext4_sync_file(). * * This is only called from sys_fsync(), sys_fdatasync() and sys_msync(). * There cannot be a transaction open by this task. * Another task could have dirtied this inode. Its data can be in any * state in the journalling system. * * What we do is just kick off a commit and wait on it. This will snapshot the * inode to disk. */ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { int ret = 0, err; bool needs_barrier = false; struct inode *inode = file->f_mapping->host; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; ASSERT(ext4_journal_current_handle() == NULL); trace_ext4_sync_file_enter(file, datasync); if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_ext4_flags value */ smp_rmb(); if (ext4_forced_shutdown(inode->i_sb)) ret = -EROFS; goto out; } if (!EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fsync_nojournal(file, start, end, datasync, &needs_barrier); if (needs_barrier) goto issue_flush; goto out; } ret = file_write_and_wait_range(file, start, end); if (ret) goto out; /* * The caller's filemap_fdatawrite()/wait will sync the data. * Metadata is in the journal, we wait for proper transaction to * commit here. */ ret = ext4_fsync_journal(inode, datasync, &needs_barrier); issue_flush: if (needs_barrier) { err = blkdev_issue_flush(inode->i_sb->s_bdev); if (!ret) ret = err; } out: err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; trace_ext4_sync_file_exit(inode, ret); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Definitions for SMC Connections, Link Groups and Links * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #ifndef _SMC_CORE_H #define _SMC_CORE_H #include <linux/atomic.h> #include <linux/smc.h> #include <linux/pci.h> #include <rdma/ib_verbs.h> #include <net/genetlink.h> #include <net/smc.h> #include "smc.h" #include "smc_ib.h" #include "smc_clc.h" #define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */ #define SMC_CONN_PER_LGR_MIN 16 /* min. # of connections per link group */ #define SMC_CONN_PER_LGR_MAX 255 /* max. # of connections per link group, * also is the default value for SMC-R v1 and v2.0 */ #define SMC_CONN_PER_LGR_PREFER 255 /* Preferred connections per link group used for * SMC-R v2.1 and later negotiation, vendors or * distrubutions may modify it to a value between * 16-255 as needed. */ struct smc_lgr_list { /* list of link group definition */ struct list_head list; spinlock_t lock; /* protects list of link groups */ u32 num; /* unique link group number */ }; enum smc_lgr_role { /* possible roles of a link group */ SMC_CLNT, /* client */ SMC_SERV /* server */ }; enum smc_link_state { /* possible states of a link */ SMC_LNK_UNUSED, /* link is unused */ SMC_LNK_INACTIVE, /* link is inactive */ SMC_LNK_ACTIVATING, /* link is being activated */ SMC_LNK_ACTIVE, /* link is active */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ #define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */ struct smc_wr_buf { u8 raw[SMC_WR_BUF_SIZE]; }; struct smc_wr_v2_buf { u8 raw[SMC_WR_BUF_V2_SIZE]; }; #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { POSTED, /* ib_wr_reg_mr request posted */ CONFIRMED, /* ib_wr_reg_mr response: successful */ FAILED /* ib_wr_reg_mr response: failure */ }; struct smc_rdma_sge { /* sges for RDMA writes */ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; }; #define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per * message send */ struct smc_rdma_sges { /* sges per message send */ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; }; struct smc_rdma_wr { /* work requests per message * send */ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; }; #define SMC_LGR_ID_SIZE 4 struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ struct ib_pd *roce_pd; /* IB protection domain, * unique for every RoCE QP */ struct ib_qp *roce_qp; /* IB queue pair */ struct ib_qp_attr qp_attr; /* IB queue pair attributes */ struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ struct completion *wr_tx_compl; /* WR send CQE completion */ /* above four vectors have wr_tx_cnt elements and use the same index */ struct ib_send_wr *wr_tx_v2_ib; /* WR send v2 meta data */ struct ib_sge *wr_tx_v2_sge; /* WR send v2 gather meta data*/ struct smc_wr_tx_pend *wr_tx_v2_pend; /* WR send v2 waiting for CQE */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ dma_addr_t wr_tx_v2_dma_addr; /* DMA address of v2 tx buf*/ atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ struct { struct percpu_ref wr_tx_refs; } ____cacheline_aligned_in_smp; struct completion tx_ref_comp; struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ u64 wr_rx_id_compl; /* seq # of last completed WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ struct { struct percpu_ref wr_reg_refs; } ____cacheline_aligned_in_smp; struct completion reg_ref_comp; enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ u8 sgid_index; /* gid index for vlan id */ u32 peer_qpn; /* QP number of peer */ enum ib_mtu path_mtu; /* used mtu */ enum ib_mtu peer_mtu; /* mtu size of peer */ u32 psn_initial; /* QP tx initial packet seqno */ u32 peer_psn; /* QP rx initial packet seqno */ u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */ u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/ u8 link_id; /* unique # within link group */ u8 link_uid[SMC_LGR_ID_SIZE]; /* unique lnk id */ u8 peer_link_uid[SMC_LGR_ID_SIZE]; /* peer uid */ u8 link_idx; /* index in lgr link array */ u8 link_is_asym; /* is link asymmetric? */ u8 clearing : 1; /* link is being cleared */ refcount_t refcnt; /* link reference count */ struct smc_link_group *lgr; /* parent link group */ struct work_struct link_down_wrk; /* wrk to bring link down */ char ibname[IB_DEVICE_NAME_MAX]; /* ib device name */ int ndev_ifidx; /* network device ifindex */ enum smc_link_state state; /* state of link */ struct delayed_work llc_testlink_wrk; /* testlink worker */ struct completion llc_testlink_resp; /* wait for rx of testlink */ int llc_testlink_time; /* testlink interval */ atomic_t conn_cnt; /* connections on this link */ }; /* For now we just allow one parallel link per link group. The SMC protocol * allows more (up to 8). */ #define SMC_LINKS_PER_LGR_MAX 3 #define SMC_SINGLE_LINK 0 #define SMC_LINKS_ADD_LNK_MIN 1 /* min. # of links per link group */ #define SMC_LINKS_ADD_LNK_MAX 2 /* max. # of links per link group, also is the * default value for smc-r v1.0 and v2.0 */ #define SMC_LINKS_PER_LGR_MAX_PREFER 2 /* Preferred max links per link group used for * SMC-R v2.1 and later negotiation, vendors or * distrubutions may modify it to a value between * 1-2 as needed. */ /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */ struct smc_buf_desc { struct list_head list; void *cpu_addr; /* virtual address of buffer */ struct page *pages; int len; /* length of buffer */ u32 used; /* currently used / unused */ union { struct { /* SMC-R */ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX]; /* virtual buffer */ struct ib_mr *mr[SMC_LINKS_PER_LGR_MAX]; /* memory region: for rmb and * vzalloced sndbuf * incl. rkey provided to peer * and lkey provided to local */ u32 order; /* allocation order */ u8 is_conf_rkey; /* confirm_rkey done */ u8 is_reg_mr[SMC_LINKS_PER_LGR_MAX]; /* mem region registered */ u8 is_map_ib[SMC_LINKS_PER_LGR_MAX]; /* mem region mapped to lnk */ u8 is_dma_need_sync; u8 is_reg_err; /* buffer registration err */ u8 is_vm; /* virtually contiguous */ }; struct { /* SMC-D */ unsigned short sba_idx; /* SBA index number */ u64 token; /* DMB token number */ dma_addr_t dma_addr; /* DMA address */ }; }; }; struct smc_rtoken { /* address/key of remote RMB */ u64 dma_addr; u32 rkey; }; #define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */ #define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */ /* theoretically, the RFC states that largest size would be 512K, * i.e. compressed 5 and thus 6 sizes (0..5), despite * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) */ struct smcd_dev; enum smc_lgr_type { /* redundancy state of lgr */ SMC_LGR_NONE, /* no active links, lgr to be deleted */ SMC_LGR_SINGLE, /* 1 active RNIC on each peer */ SMC_LGR_SYMMETRIC, /* 2 active RNICs on each peer */ SMC_LGR_ASYMMETRIC_PEER, /* local has 2, peer 1 active RNICs */ SMC_LGR_ASYMMETRIC_LOCAL, /* local has 1, peer 2 active RNICs */ }; enum smcr_buf_type { /* types of SMC-R sndbufs and RMBs */ SMCR_PHYS_CONT_BUFS = 0, SMCR_VIRT_CONT_BUFS = 1, SMCR_MIXED_BUFS = 2, }; enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, SMC_LLC_FLOW_REQ_ADD_LINK = 5, SMC_LLC_FLOW_RKEY = 6, }; struct smc_llc_qentry; struct smc_llc_flow { enum smc_llc_flowtype type; struct smc_llc_qentry *qentry; }; struct smc_link_group { struct list_head list; struct rb_root conns_all; /* connection tree */ rwlock_t conns_lock; /* protects conns_all */ unsigned int conns_num; /* current # of connections */ unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ struct work_struct terminate_work; /* abnormal lgr termination */ struct workqueue_struct *tx_wq; /* wq for conn. tx workers */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ u8 freeing : 1; /* lgr is being freed */ refcount_t refcnt; /* lgr reference count */ bool is_smcd; /* SMC-R or SMC-D */ u8 smc_version; u8 negotiated_eid[SMC_MAX_EID_LEN]; u8 peer_os; /* peer operating system */ u8 peer_smc_release; u8 peer_hostname[SMC_MAX_HOSTNAME_LEN]; union { struct { /* SMC-R */ enum smc_lgr_role role; /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ struct smc_wr_v2_buf *wr_rx_buf_v2; /* WR v2 recv payload buffer */ struct smc_wr_v2_buf *wr_tx_buf_v2; /* WR v2 send payload buffer */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] [SMC_LINKS_PER_LGR_MAX]; /* remote addr/key pairs */ DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX); /* used rtoken elements */ u8 next_link_id; enum smc_lgr_type type; enum smcr_buf_type buf_type; /* redundancy state */ u8 pnet_id[SMC_MAX_PNETID_LEN + 1]; /* pnet id of this lgr */ struct list_head llc_event_q; /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ struct rw_semaphore llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; struct work_struct llc_event_work; /* llc event worker */ wait_queue_head_t llc_flow_waiter; /* w4 next llc event */ wait_queue_head_t llc_msg_waiter; /* w4 next llc msg */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; /* llc remote control field */ struct smc_llc_qentry *delayed_event; /* arrived when flow active */ spinlock_t llc_flow_lock; /* protects llc flow */ int llc_testlink_time; /* link keep alive time */ u32 llc_termination_rsn; /* rsn code for termination */ u8 nexthop_mac[ETH_ALEN]; u8 uses_gateway; __be32 saddr; /* net namespace */ struct net *net; u8 max_conns; /* max conn can be assigned to lgr */ u8 max_links; /* max links can be added in lgr */ }; struct { /* SMC-D */ struct smcd_gid peer_gid; /* Peer GID (remote) */ struct smcd_dev *smcd; /* ISM device for VLAN reg. */ u8 peer_shutdown : 1; /* peer triggered shutdownn */ }; }; }; struct smc_clc_msg_local; #define GID_LIST_SIZE 2 struct smc_gidlist { u8 len; u8 list[GID_LIST_SIZE][SMC_GID_SIZE]; }; struct smc_init_info_smcrv2 { /* Input fields */ __be32 saddr; struct sock *clc_sk; __be32 daddr; /* Output fields when saddr is set */ struct smc_ib_device *ib_dev_v2; u8 ib_port_v2; u8 ib_gid_v2[SMC_GID_SIZE]; /* Additional output fields when clc_sk and daddr is set as well */ u8 uses_gateway; u8 nexthop_mac[ETH_ALEN]; struct smc_gidlist gidlist; }; #define SMC_MAX_V2_ISM_DEVS SMCD_CLC_MAX_V2_GID_ENTRIES /* max # of proposed non-native ISM devices, * which can't exceed the max # of CHID-GID * entries in CLC proposal SMC-Dv2 extension. */ struct smc_init_info { u8 is_smcd; u8 smc_type_v1; u8 smc_type_v2; u8 release_nr; u8 max_conns; u8 max_links; u8 first_contact_peer; u8 first_contact_local; u16 feature_mask; unsigned short vlan_id; u32 rc; u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ u8 smcr_version; u8 check_smcrv2; u8 peer_gid[SMC_GID_SIZE]; u8 peer_mac[ETH_ALEN]; u8 peer_systemid[SMC_SYSTEMID_LEN]; struct smc_ib_device *ib_dev; u8 ib_gid[SMC_GID_SIZE]; u8 ib_port; u32 ib_clcqpn; struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ struct smcd_gid ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1]; struct smcd_dev *ism_dev[SMC_MAX_V2_ISM_DEVS + 1]; u16 ism_chid[SMC_MAX_V2_ISM_DEVS + 1]; u8 ism_offered_cnt; /* # of ISM devices offered */ u8 ism_selected; /* index of selected ISM dev*/ u8 smcd_version; }; /* Find the connection associated with the given alert token in the link group. * To use rbtrees we have to implement our own search core. * Requires @conns_lock * @token alert token to search for * @lgr link group to search in * Returns connection associated with token if found, NULL otherwise. */ static inline struct smc_connection *smc_lgr_find_conn( u32 token, struct smc_link_group *lgr) { struct smc_connection *res = NULL; struct rb_node *node; node = lgr->conns_all.rb_node; while (node) { struct smc_connection *cur = rb_entry(node, struct smc_connection, alert_node); if (cur->alert_token_local > token) { node = node->rb_left; } else { if (cur->alert_token_local < token) { node = node->rb_right; } else { res = cur; break; } } } return res; } static inline bool smc_conn_lgr_valid(struct smc_connection *conn) { return conn->lgr && conn->alert_token_local; } /* * Returns true if the specified link is usable. * * usable means the link is ready to receive RDMA messages, map memory * on the link, etc. This doesn't ensure we are able to send RDMA messages * on this link, if sending RDMA messages is needed, use smc_link_sendable() */ static inline bool smc_link_usable(struct smc_link *lnk) { if (lnk->state == SMC_LNK_UNUSED || lnk->state == SMC_LNK_INACTIVE) return false; return true; } /* * Returns true if the specified link is ready to receive AND send RDMA * messages. * * For the client side in first contact, the underlying QP may still in * RESET or RTR when the link state is ACTIVATING, checks in smc_link_usable() * is not strong enough. For those places that need to send any CDC or LLC * messages, use smc_link_sendable(), otherwise, use smc_link_usable() instead */ static inline bool smc_link_sendable(struct smc_link *lnk) { return smc_link_usable(lnk) && lnk->qp_attr.cur_qp_state == IB_QPS_RTS; } static inline bool smc_link_active(struct smc_link *lnk) { return lnk->state == SMC_LNK_ACTIVE; } static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) { sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", be16_to_cpu(((__be16 *)gid_raw)[0]), be16_to_cpu(((__be16 *)gid_raw)[1]), be16_to_cpu(((__be16 *)gid_raw)[2]), be16_to_cpu(((__be16 *)gid_raw)[3]), be16_to_cpu(((__be16 *)gid_raw)[4]), be16_to_cpu(((__be16 *)gid_raw)[5]), be16_to_cpu(((__be16 *)gid_raw)[6]), be16_to_cpu(((__be16 *)gid_raw)[7])); } struct smc_pci_dev { __u32 pci_fid; __u16 pci_pchid; __u16 pci_vendor; __u16 pci_device; __u8 pci_id[SMC_PCI_ID_STR_LEN]; }; static inline void smc_set_pci_values(struct pci_dev *pci_dev, struct smc_pci_dev *smc_dev) { smc_dev->pci_vendor = pci_dev->vendor; smc_dev->pci_device = pci_dev->device; snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s", pci_name(pci_dev)); #if IS_ENABLED(CONFIG_S390) { /* Set s390 specific PCI information */ struct zpci_dev *zdev; zdev = to_zpci(pci_dev); smc_dev->pci_fid = zdev->fid; smc_dev->pci_pchid = zdev->pchid; } #endif } struct smc_sock; struct smc_clc_msg_accept_confirm; void smc_lgr_cleanup_early(struct smc_link_group *lgr); void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smc_lgr_hold(struct smc_link_group *lgr); void smc_lgr_put(struct smc_link_group *lgr); void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport); void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan); void smc_smcd_terminate_all(struct smcd_dev *dev); void smc_smcr_terminate_all(struct smc_ib_device *smcibdev); int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link, struct smc_clc_msg_accept_confirm *clc); int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey); int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey); void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey); void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); int smc_core_init(void); void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); void smcr_link_hold(struct smc_link *lnk); void smcr_link_put(struct smc_link *lnk); void smc_switch_link_and_count(struct smc_connection *conn, struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx); int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *rmb_desc); struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err); void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb); int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { return link->lgr; } #endif |
| 1525 1525 | 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 | /* Copyright (c) 2018, Mellanox Technologies 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 <crypto/aead.h> #include <linux/highmem.h> #include <linux/module.h> #include <linux/netdevice.h> #include <net/dst.h> #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/tls.h> #include "tls.h" #include "trace.h" /* device_offload_lock is used to synchronize tls_dev_add * against NETDEV_DOWN notifications. */ static DECLARE_RWSEM(device_offload_lock); static struct workqueue_struct *destruct_wq __read_mostly; static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); static struct page *dummy_page; static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) kfree(tls_offload_ctx_tx(ctx)); if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); tls_ctx_free(NULL, ctx); } static void tls_device_tx_del_task(struct work_struct *work) { struct tls_offload_context_tx *offload_ctx = container_of(work, struct tls_offload_context_tx, destruct_work); struct tls_context *ctx = offload_ctx->ctx; struct net_device *netdev; /* Safe, because this is the destroy flow, refcount is 0, so * tls_device_down can't store this field in parallel. */ netdev = rcu_dereference_protected(ctx->netdev, !refcount_read(&ctx->refcount)); netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); dev_put(netdev); ctx->netdev = NULL; tls_device_free_ctx(ctx); } static void tls_device_queue_ctx_destruction(struct tls_context *ctx) { struct net_device *netdev; unsigned long flags; bool async_cleanup; spin_lock_irqsave(&tls_device_lock, flags); if (unlikely(!refcount_dec_and_test(&ctx->refcount))) { spin_unlock_irqrestore(&tls_device_lock, flags); return; } list_del(&ctx->list); /* Remove from tls_device_list / tls_device_down_list */ /* Safe, because this is the destroy flow, refcount is 0, so * tls_device_down can't store this field in parallel. */ netdev = rcu_dereference_protected(ctx->netdev, !refcount_read(&ctx->refcount)); async_cleanup = netdev && ctx->tx_conf == TLS_HW; if (async_cleanup) { struct tls_offload_context_tx *offload_ctx = tls_offload_ctx_tx(ctx); /* queue_work inside the spinlock * to make sure tls_device_down waits for that work. */ queue_work(destruct_wq, &offload_ctx->destruct_work); } spin_unlock_irqrestore(&tls_device_lock, flags); if (!async_cleanup) tls_device_free_ctx(ctx); } /* We assume that the socket is already connected */ static struct net_device *get_netdev_for_sock(struct sock *sk) { struct dst_entry *dst = sk_dst_get(sk); struct net_device *netdev = NULL; if (likely(dst)) { netdev = netdev_sk_get_lowest_dev(dst->dev, sk); dev_hold(netdev); } dst_release(dst); return netdev; } static void destroy_record(struct tls_record_info *record) { int i; for (i = 0; i < record->num_frags; i++) __skb_frag_unref(&record->frags[i], false); kfree(record); } static void delete_all_records(struct tls_offload_context_tx *offload_ctx) { struct tls_record_info *info, *temp; list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) { list_del(&info->list); destroy_record(info); } offload_ctx->retransmit_hint = NULL; } static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_record_info *info, *temp; struct tls_offload_context_tx *ctx; u64 deleted_records = 0; unsigned long flags; if (!tls_ctx) return; ctx = tls_offload_ctx_tx(tls_ctx); spin_lock_irqsave(&ctx->lock, flags); info = ctx->retransmit_hint; if (info && !before(acked_seq, info->end_seq)) ctx->retransmit_hint = NULL; list_for_each_entry_safe(info, temp, &ctx->records_list, list) { if (before(acked_seq, info->end_seq)) break; list_del(&info->list); destroy_record(info); deleted_records++; } ctx->unacked_record_sn += deleted_records; spin_unlock_irqrestore(&ctx->lock, flags); } /* At this point, there should be no references on this * socket and no in-flight SKBs associated with this * socket, so it is safe to free all the resources. */ void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); tls_ctx->sk_destruct(sk); if (tls_ctx->tx_conf == TLS_HW) { if (ctx->open_record) destroy_record(ctx->open_record); delete_all_records(ctx); crypto_free_aead(ctx->aead_send); clean_acked_data_disable(inet_csk(sk)); } tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); void tls_device_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); tls_free_partial_record(sk, tls_ctx); } void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); trace_tls_device_tx_resync_req(sk, got_seq, exp_seq); WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); } EXPORT_SYMBOL_GPL(tls_offload_tx_resync_request); static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx, u32 seq) { struct net_device *netdev; struct sk_buff *skb; int err = 0; u8 *rcd_sn; skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; rcd_sn = tls_ctx->tx.rec_seq; trace_tls_device_tx_resync_send(sk, seq, rcd_sn); down_read(&device_offload_lock); netdev = rcu_dereference_protected(tls_ctx->netdev, lockdep_is_held(&device_offload_lock)); if (netdev) err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_TX); up_read(&device_offload_lock); if (err) return; clear_bit_unlock(TLS_TX_SYNC_SCHED, &tls_ctx->flags); } static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) { skb_frag_t *frag; frag = &record->frags[record->num_frags - 1]; if (skb_frag_page(frag) == pfrag->page && skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) { skb_frag_size_add(frag, size); } else { ++frag; skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, size); ++record->num_frags; get_page(pfrag->page); } pfrag->offset += size; record->len += size; } static int tls_push_record(struct sock *sk, struct tls_context *ctx, struct tls_offload_context_tx *offload_ctx, struct tls_record_info *record, int flags) { struct tls_prot_info *prot = &ctx->prot_info; struct tcp_sock *tp = tcp_sk(sk); skb_frag_t *frag; int i; record->end_seq = tp->write_seq + record->len; list_add_tail_rcu(&record->list, &offload_ctx->records_list); offload_ctx->open_record = NULL; if (test_bit(TLS_TX_SYNC_SCHED, &ctx->flags)) tls_device_resync_tx(sk, ctx, tp->write_seq); tls_advance_record_sn(sk, prot, &ctx->tx); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); /* all ready, send */ return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } static void tls_device_record_close(struct sock *sk, struct tls_context *ctx, struct tls_record_info *record, struct page_frag *pfrag, unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) * if we can't allocate memory now use the dummy page */ if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { dummy_tag_frag.page = dummy_page; dummy_tag_frag.offset = 0; pfrag = &dummy_tag_frag; } tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { struct tls_record_info *record; skb_frag_t *frag; record = kmalloc(sizeof(*record), GFP_KERNEL); if (!record) return -ENOMEM; frag = &record->frags[0]; skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, prepend_size); get_page(pfrag->page); pfrag->offset += prepend_size; record->num_frags = 1; record->len = prepend_size; offload_ctx->open_record = record; return 0; } static int tls_do_allocation(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { int ret; if (!offload_ctx->open_record) { if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, sk->sk_allocation))) { READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return -ENOMEM; } ret = tls_create_new_record(offload_ctx, pfrag, prepend_size); if (ret) return ret; if (pfrag->size > pfrag->offset) return 0; } if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; return 0; } static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i) { size_t pre_copy, nocache; pre_copy = ~((unsigned long)addr - 1) & (SMP_CACHE_BYTES - 1); if (pre_copy) { pre_copy = min(pre_copy, bytes); if (copy_from_iter(addr, pre_copy, i) != pre_copy) return -EFAULT; bytes -= pre_copy; addr += pre_copy; } nocache = round_down(bytes, SMP_CACHE_BYTES); if (copy_from_iter_nocache(addr, nocache, i) != nocache) return -EFAULT; bytes -= nocache; addr += nocache; if (bytes && copy_from_iter(addr, bytes, i) != bytes) return -EFAULT; return 0; } static int tls_push_data(struct sock *sk, struct iov_iter *iter, size_t size, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); struct tls_record_info *record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; bool more = false; bool done = false; int copy, rc = 0; long timeo; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES | MSG_EOR)) return -EOPNOTSUPP; if ((flags & (MSG_MORE | MSG_EOR)) == (MSG_MORE | MSG_EOR)) return -EINVAL; if (unlikely(sk->sk_err)) return -sk->sk_err; flags |= MSG_SENDPAGE_DECRYPTED; tls_push_record_flags = flags | MSG_MORE; timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (tls_is_partially_sent_record(tls_ctx)) { rc = tls_push_partial_record(sk, tls_ctx, flags); if (rc < 0) return rc; } pfrag = sk_page_frag(sk); /* TLS_HEADER_SIZE is not counted as part of the TLS record, and * we need to leave room for an authentication tag. */ max_open_record_len = TLS_MAX_PAYLOAD_SIZE + prot->prepend_size; do { rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size); if (unlikely(rc)) { rc = sk_stream_wait_memory(sk, &timeo); if (!rc) continue; record = ctx->open_record; if (!record) break; handle_error: if (record_type != TLS_RECORD_TYPE_DATA) { /* avoid sending partial * record with type != * application_data */ size = orig_size; destroy_record(record); ctx->open_record = NULL; } else if (record->len > prot->prepend_size) { goto last_record; } break; } record = ctx->open_record; copy = min_t(size_t, size, max_open_record_len - record->len); if (copy && (flags & MSG_SPLICE_PAGES)) { struct page_frag zc_pfrag; struct page **pages = &zc_pfrag.page; size_t off; rc = iov_iter_extract_pages(iter, &pages, copy, 1, 0, &off); if (rc <= 0) { if (rc == 0) rc = -EIO; goto handle_error; } copy = rc; if (WARN_ON_ONCE(!sendpage_ok(zc_pfrag.page))) { iov_iter_revert(iter, copy); rc = -EIO; goto handle_error; } zc_pfrag.offset = off; zc_pfrag.size = copy; tls_append_frag(record, &zc_pfrag, copy); } else if (copy) { copy = min_t(size_t, copy, pfrag->size - pfrag->offset); rc = tls_device_copy_data(page_address(pfrag->page) + pfrag->offset, copy, iter); if (rc) goto handle_error; tls_append_frag(record, pfrag, copy); } size -= copy; if (!size) { last_record: tls_push_record_flags = flags; if (flags & MSG_MORE) { more = true; break; } done = true; } if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { tls_device_record_close(sk, tls_ctx, record, pfrag, record_type); rc = tls_push_record(sk, tls_ctx, ctx, record, tls_push_record_flags); if (rc < 0) break; } } while (!done); tls_ctx->pending_open_record_frags = more; if (orig_size - size > 0) rc = orig_size - size; return rc; } int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; if (!tls_ctx->zerocopy_sendfile) msg->msg_flags &= ~MSG_SPLICE_PAGES; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { rc = tls_process_cmsg(sk, msg, &record_type); if (rc) goto out; } rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags, record_type); out: release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); return rc; } void tls_device_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter iter = {}; if (!tls_is_partially_sent_record(tls_ctx)) return; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (tls_is_partially_sent_record(tls_ctx)) { iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0); tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA); } release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); } struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || before(seq, info->end_seq - info->len)) { /* if retransmit_hint is irrelevant start * from the beginning of the list */ info = list_first_entry_or_null(&context->records_list, struct tls_record_info, list); if (!info) return NULL; /* send the start_marker record if seq number is before the * tls offload start marker sequence number. This record is * required to handle TCP packets which are before TLS offload * started. * And if it's not start marker, look if this seq number * belongs to the list. */ if (likely(!tls_record_is_start_marker(info))) { /* we have the first record, get the last record to see * if this seq number belongs to the list. */ last = list_last_entry(&context->records_list, struct tls_record_info, list); if (!between(seq, tls_record_start_seq(info), last->end_seq)) return NULL; } record_sn = context->unacked_record_sn; } /* We just need the _rcu for the READ_ONCE() */ rcu_read_lock(); list_for_each_entry_from_rcu(info, &context->records_list, list) { if (before(seq, info->end_seq)) { if (!context->retransmit_hint || after(info->end_seq, context->retransmit_hint->end_seq)) { context->hint_record_sn = record_sn; context->retransmit_hint = info; } *p_record_sn = record_sn; goto exit_rcu_unlock; } record_sn++; } info = NULL; exit_rcu_unlock: rcu_read_unlock(); return info; } EXPORT_SYMBOL(tls_get_record); static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, NULL, 0, 0); return tls_push_data(sk, &iter, 0, flags, TLS_RECORD_TYPE_DATA); } void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; WARN_ON_ONCE(sk->sk_write_pending); sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_DECRYPTED); sk->sk_allocation = sk_allocation; } } static void tls_device_resync_rx(struct tls_context *tls_ctx, struct sock *sk, u32 seq, u8 *rcd_sn) { struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); struct net_device *netdev; trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type); rcu_read_lock(); netdev = rcu_dereference(tls_ctx->netdev); if (netdev) netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_RX); rcu_read_unlock(); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC); } static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); u16 i; *rcd_delta = 0; if (is_async) { /* shouldn't get to wraparound: * too long in async stage, something bad happened */ if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) return false; /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ if (before(*seq, req_seq)) return false; if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; resync_async->rcd_delta++; return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ for (i = 0; i < resync_async->loglen; i++) if (req_seq == resync_async->log[i] && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; resync_async->loglen = 0; resync_async->rcd_delta = 0; return true; } resync_async->loglen = 0; resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) return true; return false; } void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) return; if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) return; prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); switch (rx_ctx->resync_type) { case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ: resync_req = atomic64_read(&rx_ctx->resync_req); req_seq = resync_req >> 32; seq += TLS_HEADER_SIZE - 1; is_req_pending = resync_req; if (likely(!is_req_pending) || req_seq != seq || !atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) return; break; case TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT: if (likely(!rx_ctx->resync_nh_do_now)) return; /* head of next rec is already in, note that the sock_inq will * include the currently parsed message when called from parser */ sock_data = tcp_inq(sk); if (sock_data > rcd_len) { trace_tls_device_rx_resync_nh_delay(sk, sock_data, rcd_len); return; } rx_ctx->resync_nh_do_now = 0; seq += rcd_len; tls_bigint_increment(rcd_sn, prot->rec_seq_size); break; case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC: resync_req = atomic64_read(&rx_ctx->resync_async->req); is_req_pending = resync_req; if (likely(!is_req_pending)) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, resync_req, &seq, &rcd_delta)) return; tls_bigint_subtract(rcd_sn, rcd_delta); break; } tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); } static void tls_device_core_ctrl_rx_resync(struct tls_context *tls_ctx, struct tls_offload_context_rx *ctx, struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm; /* device will request resyncs by itself based on stream scan */ if (ctx->resync_type != TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT) return; /* already scheduled */ if (ctx->resync_nh_do_now) return; /* seen decrypted fragments since last fully-failed record */ if (ctx->resync_nh_reset) { ctx->resync_nh_reset = 0; ctx->resync_nh.decrypted_failed = 1; ctx->resync_nh.decrypted_tgt = TLS_DEVICE_RESYNC_NH_START_IVAL; return; } if (++ctx->resync_nh.decrypted_failed <= ctx->resync_nh.decrypted_tgt) return; /* doing resync, bump the next target in case it fails */ if (ctx->resync_nh.decrypted_tgt < TLS_DEVICE_RESYNC_NH_MAX_IVAL) ctx->resync_nh.decrypted_tgt *= 2; else ctx->resync_nh.decrypted_tgt += TLS_DEVICE_RESYNC_NH_MAX_IVAL; rxm = strp_msg(skb); /* head of next rec is already in, parser will sync for us */ if (tcp_inq(sk) > rxm->full_len) { trace_tls_device_rx_resync_nh_schedule(sk); ctx->resync_nh_do_now = 1; } else { struct tls_prot_info *prot = &tls_ctx->prot_info; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); tls_bigint_increment(rcd_sn, prot->rec_seq_size); tls_device_resync_rx(tls_ctx, sk, tcp_sk(sk)->copied_seq, rcd_sn); } } static int tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx) { struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); const struct tls_cipher_desc *cipher_desc; int err, offset, copy, data_len, pos; struct sk_buff *skb, *skb_iter; struct scatterlist sg[1]; struct strp_msg *rxm; char *orig_buf, *buf; cipher_desc = get_cipher_desc(tls_ctx->crypto_recv.info.cipher_type); DEBUG_NET_WARN_ON_ONCE(!cipher_desc || !cipher_desc->offloadable); rxm = strp_msg(tls_strp_msg(sw_ctx)); orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv, sk->sk_allocation); if (!orig_buf) return -ENOMEM; buf = orig_buf; err = tls_strp_msg_cow(sw_ctx); if (unlikely(err)) goto free_buf; skb = tls_strp_msg(sw_ctx); rxm = strp_msg(skb); offset = rxm->offset; sg_init_table(sg, 1); sg_set_buf(&sg[0], buf, rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv); err = skb_copy_bits(skb, offset, buf, TLS_HEADER_SIZE + cipher_desc->iv); if (err) goto free_buf; /* We are interested only in the decrypted data not the auth */ err = decrypt_skb(sk, sg); if (err != -EBADMSG) goto free_buf; else err = 0; data_len = rxm->full_len - cipher_desc->tag; if (skb_pagelen(skb) > offset) { copy = min_t(int, skb_pagelen(skb) - offset, data_len); if (skb->decrypted) { err = skb_store_bits(skb, offset, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; } pos = skb_pagelen(skb); skb_walk_frags(skb, skb_iter) { int frag_pos; /* Practically all frags must belong to msg if reencrypt * is needed with current strparser and coalescing logic, * but strparser may "get optimized", so let's be safe. */ if (pos + skb_iter->len <= offset) goto done_with_frag; if (pos >= data_len + rxm->offset) break; frag_pos = offset - pos; copy = min_t(int, skb_iter->len - frag_pos, data_len + rxm->offset - offset); if (skb_iter->decrypted) { err = skb_store_bits(skb_iter, frag_pos, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; done_with_frag: pos += skb_iter->len; } free_buf: kfree(orig_buf); return err; } int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) { struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx); struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); int is_decrypted, is_encrypted; if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { is_decrypted = skb->decrypted; is_encrypted = !is_decrypted; } else { is_decrypted = 0; is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, tls_ctx->rx.rec_seq, rxm->full_len, is_encrypted, is_decrypted); if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) { if (likely(is_encrypted || is_decrypted)) return is_decrypted; /* After tls_device_down disables the offload, the next SKB will * likely have initial fragments decrypted, and final ones not * decrypted. We need to reencrypt that single SKB. */ return tls_device_reencrypt(sk, tls_ctx); } /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. */ if (is_decrypted) { ctx->resync_nh_reset = 1; return is_decrypted; } if (is_encrypted) { tls_device_core_ctrl_rx_resync(tls_ctx, ctx, sk, skb); return 0; } ctx->resync_nh_reset = 1; return tls_device_reencrypt(sk, tls_ctx); } static void tls_device_attach(struct tls_context *ctx, struct sock *sk, struct net_device *netdev) { if (sk->sk_destruct != tls_device_sk_destruct) { refcount_set(&ctx->refcount, 1); dev_hold(netdev); RCU_INIT_POINTER(ctx->netdev, netdev); spin_lock_irq(&tls_device_lock); list_add_tail(&ctx->list, &tls_device_list); spin_unlock_irq(&tls_device_lock); ctx->sk_destruct = sk->sk_destruct; smp_store_release(&sk->sk_destruct, tls_device_sk_destruct); } } static struct tls_offload_context_tx *alloc_offload_ctx_tx(struct tls_context *ctx) { struct tls_offload_context_tx *offload_ctx; __be64 rcd_sn; offload_ctx = kzalloc(sizeof(*offload_ctx), GFP_KERNEL); if (!offload_ctx) return NULL; INIT_WORK(&offload_ctx->destruct_work, tls_device_tx_del_task); INIT_LIST_HEAD(&offload_ctx->records_list); spin_lock_init(&offload_ctx->lock); sg_init_table(offload_ctx->sg_tx_data, ARRAY_SIZE(offload_ctx->sg_tx_data)); /* start at rec_seq - 1 to account for the start marker record */ memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn)); offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1; offload_ctx->ctx = ctx; return offload_ctx; } int tls_set_device_offload(struct sock *sk) { struct tls_record_info *start_marker_record; struct tls_offload_context_tx *offload_ctx; const struct tls_cipher_desc *cipher_desc; struct tls_crypto_info *crypto_info; struct tls_prot_info *prot; struct net_device *netdev; struct tls_context *ctx; struct sk_buff *skb; char *iv, *rec_seq; int rc; ctx = tls_get_ctx(sk); prot = &ctx->prot_info; if (ctx->priv_ctx_tx) return -EEXIST; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { rc = -EOPNOTSUPP; goto release_netdev; } crypto_info = &ctx->crypto_send.info; if (crypto_info->version != TLS_1_2_VERSION) { rc = -EOPNOTSUPP; goto release_netdev; } cipher_desc = get_cipher_desc(crypto_info->cipher_type); if (!cipher_desc || !cipher_desc->offloadable) { rc = -EINVAL; goto release_netdev; } rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto release_netdev; iv = crypto_info_iv(crypto_info, cipher_desc); rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc); memcpy(ctx->tx.iv + cipher_desc->salt, iv, cipher_desc->iv); memcpy(ctx->tx.rec_seq, rec_seq, cipher_desc->rec_seq); start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); if (!start_marker_record) { rc = -ENOMEM; goto release_netdev; } offload_ctx = alloc_offload_ctx_tx(ctx); if (!offload_ctx) { rc = -ENOMEM; goto free_marker_record; } rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); if (rc) goto free_offload_ctx; start_marker_record->end_seq = tcp_sk(sk)->write_seq; start_marker_record->len = 0; start_marker_record->num_frags = 0; list_add_tail(&start_marker_record->list, &offload_ctx->records_list); clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); ctx->push_pending_record = tls_device_push_pending_record; /* TLS offload is greatly simplified if we don't send * SKBs where only part of the payload needs to be encrypted. * So mark the last skb in the write queue as end of record. */ skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, &ctx->crypto_send.info, tcp_sk(sk)->write_seq); trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_TX, tcp_sk(sk)->write_seq, rec_seq, rc); if (rc) goto release_lock; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); /* following this assignment tls_is_skb_tx_device_offloaded * will return true and the context might be accessed * by the netdev's xmit function. */ smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb); dev_put(netdev); return 0; release_lock: up_read(&device_offload_lock); clean_acked_data_disable(inet_csk(sk)); crypto_free_aead(offload_ctx->aead_send); free_offload_ctx: kfree(offload_ctx); ctx->priv_ctx_tx = NULL; free_marker_record: kfree(start_marker_record); release_netdev: dev_put(netdev); return rc; } int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) { struct tls12_crypto_info_aes_gcm_128 *info; struct tls_offload_context_rx *context; struct net_device *netdev; int rc = 0; if (ctx->crypto_recv.info.version != TLS_1_2_VERSION) return -EOPNOTSUPP; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { rc = -EOPNOTSUPP; goto release_netdev; } /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) { rc = -ENOMEM; goto release_lock; } context->resync_nh_reset = 1; ctx->priv_ctx_rx = context; rc = tls_set_sw_offload(sk, 0); if (rc) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); info = (void *)&ctx->crypto_recv.info; trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_RX, tcp_sk(sk)->copied_seq, info->rec_seq, rc); if (rc) goto free_sw_resources; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); dev_put(netdev); return 0; free_sw_resources: up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_lock: up_read(&device_offload_lock); release_netdev: dev_put(netdev); return rc; } void tls_device_offload_cleanup_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct net_device *netdev; down_read(&device_offload_lock); netdev = rcu_dereference_protected(tls_ctx->netdev, lockdep_is_held(&device_offload_lock)); if (!netdev) goto out; netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx, TLS_OFFLOAD_CTX_DIR_RX); if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); rcu_assign_pointer(tls_ctx->netdev, NULL); } else { set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); tls_sw_release_resources_rx(sk); } static int tls_device_down(struct net_device *netdev) { struct tls_context *ctx, *tmp; unsigned long flags; LIST_HEAD(list); /* Request a write lock to block new offload attempts */ down_write(&device_offload_lock); spin_lock_irqsave(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) { struct net_device *ctx_netdev = rcu_dereference_protected(ctx->netdev, lockdep_is_held(&device_offload_lock)); if (ctx_netdev != netdev || !refcount_inc_not_zero(&ctx->refcount)) continue; list_move(&ctx->list, &list); } spin_unlock_irqrestore(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &list, list) { /* Stop offloaded TX and switch to the fallback. * tls_is_skb_tx_device_offloaded will return false. */ WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw); /* Stop the RX and TX resync. * tls_dev_resync must not be called after tls_dev_del. */ rcu_assign_pointer(ctx->netdev, NULL); /* Start skipping the RX resync logic completely. */ set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags); /* Sync with inflight packets. After this point: * TX: no non-encrypted packets will be passed to the driver. * RX: resync requests from the driver will be ignored. */ synchronize_net(); /* Release the offload context on the driver side. */ if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); if (ctx->rx_conf == TLS_HW && !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); dev_put(netdev); /* Move the context to a separate list for two reasons: * 1. When the context is deallocated, list_del is called. * 2. It's no longer an offloaded context, so we don't want to * run offload-specific code on this context. */ spin_lock_irqsave(&tls_device_lock, flags); list_move_tail(&ctx->list, &tls_device_down_list); spin_unlock_irqrestore(&tls_device_lock, flags); /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. * Now release the ref taken above. */ if (refcount_dec_and_test(&ctx->refcount)) { /* sk_destruct ran after tls_device_down took a ref, and * it returned early. Complete the destruction here. */ list_del(&ctx->list); tls_device_free_ctx(ctx); } } up_write(&device_offload_lock); flush_workqueue(destruct_wq); return NOTIFY_DONE; } static int tls_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!dev->tlsdev_ops && !(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: if (netif_is_bond_master(dev)) return NOTIFY_DONE; if ((dev->features & NETIF_F_HW_TLS_RX) && !dev->tlsdev_ops->tls_dev_resync) return NOTIFY_BAD; if (dev->tlsdev_ops && dev->tlsdev_ops->tls_dev_add && dev->tlsdev_ops->tls_dev_del) return NOTIFY_DONE; else return NOTIFY_BAD; case NETDEV_DOWN: return tls_device_down(dev); } return NOTIFY_DONE; } static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; int __init tls_device_init(void) { int err; dummy_page = alloc_page(GFP_KERNEL); if (!dummy_page) return -ENOMEM; destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); if (!destruct_wq) { err = -ENOMEM; goto err_free_dummy; } err = register_netdevice_notifier(&tls_dev_notifier); if (err) goto err_destroy_wq; return 0; err_destroy_wq: destroy_workqueue(destruct_wq); err_free_dummy: put_page(dummy_page); return err; } void __exit tls_device_cleanup(void) { unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); put_page(dummy_page); } |
| 3 32 49 49 49 49 23 26 96 4 93 94 92 90 3 3 3 3 3 3 67 63 6 56 2 4 8 8 8 8 8 8 370 368 2 2 2 2 254 234 21 21 21 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lwtunnel Infrastructure for light weight tunnels like mpls * * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/lwtunnel.h> #include <linux/in.h> #include <linux/init.h> #include <linux/err.h> #include <net/lwtunnel.h> #include <net/rtnetlink.h> #include <net/ip6_fib.h> #include <net/rtnh.h> DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); #ifdef CONFIG_MODULES static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) { /* Only lwt encaps implemented without using an interface for * the encap need to return a string here. */ switch (encap_type) { case LWTUNNEL_ENCAP_MPLS: return "MPLS"; case LWTUNNEL_ENCAP_ILA: return "ILA"; case LWTUNNEL_ENCAP_SEG6: return "SEG6"; case LWTUNNEL_ENCAP_BPF: return "BPF"; case LWTUNNEL_ENCAP_SEG6_LOCAL: return "SEG6LOCAL"; case LWTUNNEL_ENCAP_RPL: return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; case LWTUNNEL_ENCAP_XFRM: /* module autoload not supported for encap type */ return NULL; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ WARN_ON(1); break; } return NULL; } #endif /* CONFIG_MODULES */ struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) { struct lwtunnel_state *lws; lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); return lws; } EXPORT_SYMBOL_GPL(lwtunnel_state_alloc); static const struct lwtunnel_encap_ops __rcu * lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, unsigned int num) { if (num > LWTUNNEL_ENCAP_MAX) return -ERANGE; return !cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL_GPL(lwtunnel_encap_add_ops); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, unsigned int encap_type) { int ret; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) return -ERANGE; ret = (cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[encap_type], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG_ATTR(extack, encap, "Unknown LWT encapsulation type"); return ret; } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) found = true; rcu_read_unlock(); if (found) { ret = ops->build_state(net, encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } else { /* don't rely on -EOPNOTSUPP to detect match as build_state * handlers could return it */ NL_SET_ERR_MSG_ATTR(extack, encap, "LWT encapsulation type not supported"); } return ret; } EXPORT_SYMBOL_GPL(lwtunnel_build_state); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); rtnl_lock(); rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); } } #endif ret = ops ? 0 : -EOPNOTSUPP; if (ret < 0) NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; u16 encap_type; int attrlen; while (rtnh_ok(rtnh, remaining)) { attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { if (nla_len(nla_entype) < sizeof(u16)) { NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE"); return -EINVAL; } encap_type = nla_get_u16(nla_entype); if (lwtunnel_valid_encap_type(encap_type, extack) != 0) return -EOPNOTSUPP; } } rtnh = rtnh_next(rtnh, &remaining); } return 0; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type_attr); void lwtstate_free(struct lwtunnel_state *lws) { const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type]; if (ops->destroy_state) { ops->destroy_state(lws); kfree_rcu(lws, rcu); } else { kfree(lws); } module_put(ops->owner); } EXPORT_SYMBOL_GPL(lwtstate_free); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { const struct lwtunnel_encap_ops *ops; struct nlattr *nest; int ret; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; nest = nla_nest_start_noflag(skb, encap_attr); if (!nest) return -EMSGSIZE; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->fill_encap)) ret = ops->fill_encap(skb, lwtstate); rcu_read_unlock(); if (ret) goto nla_put_failure; nla_nest_end(skb, nest); ret = nla_put_u16(skb, encap_type_attr, lwtstate->type); if (ret) goto nla_put_failure; return 0; nla_put_failure: nla_nest_cancel(skb, nest); return (ret == -EOPNOTSUPP ? 0 : ret); } EXPORT_SYMBOL_GPL(lwtunnel_fill_encap); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->get_encap_size)) ret = nla_total_size(ops->get_encap_size(lwtstate)); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_get_encap_size); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!a && !b) return 0; if (!a || !b) return 1; if (a->type != b->type) return 1; if (a->type == LWTUNNEL_ENCAP_NONE || a->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[a->type]); if (likely(ops && ops->cmp_encap)) ret = ops->cmp_encap(a, b); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->xmit)) ret = ops->xmit(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->input)) ret = ops->input(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_input); |
| 1288 2569 267 267 73 1771 2854 2852 2854 3726 1839 3725 1286 361 2608 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_chksum_driver: * * Reference to checksum algorithm driver via cryptoapi. */ struct crypto_shash *j_chksum_driver; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); } static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) { return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); } static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) { return (journal->j_total_len - journal->j_fc_wbufsize) / 4; } /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) { return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); } static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && journal->j_chksum_driver == NULL); return journal->j_chksum_driver != NULL; } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); desc.shash.tfm = journal->j_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 200 1743 200 200 200 200 200 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 1559 396 106 106 2 1035 1035 1035 3 373 373 373 3 3 3 3 3 3 3 3 3 3 3 2670 2672 2670 2672 2671 2672 1100 1084 310 1100 1100 1100 | 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 | /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * page->flags PG_locked (lock_page) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * folio_lock_memcg move_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * page->flags PG_locked (lock_page) */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <asm/tlbflush.h> #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include <trace/events/migrate.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_lock held for reading. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by vma_expand(), vma_merge(), __split_vma(), * copy_vma() and anon_vma_fork(). The first four want an exact copy of src, * while the last one, anon_vma_fork(), may try to reuse an existing anon_vma to * prevent endless growth of anon_vma. Since dst->anon_vma is set to NULL before * call, we can identify this case by checking (!dst->anon_vma && * src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if it has no vma and only one * anon_vma child. * * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its num_active_vmas can * be incorrectly decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) { vma->anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; } unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should normally hold folio lock when calling this. If * not, the caller needs to double check the anon_vma didn't change after * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; retry: rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * folio_move_anon_rmap() might have changed the anon_vma as we * might not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { up_read(&root_anon_vma->rwsem); rcu_read_unlock(); goto retry; } /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); /* * folio_move_anon_rmap() might have changed the anon_vma as we might * not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { anon_vma_unlock_read(anon_vma); put_anon_vma(anon_vma); anon_vma = NULL; goto retry; } if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { arch_flush_tlb_batched_pending(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { struct folio *folio = page_folio(page); if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } return vma_address(page, vma); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; 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); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { if (!folio_test_large(folio) || !pvmw.pte) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * For large folio fully mapped to VMA, will * be handled after the pvmw loop. * * For large folio cross VMA boundaries, it's * expected to be picked by page reclaim. But * should skip reference of pages which are in * the range of VM_LOCKED vma. As page reclaim * should just count the reference of pages out * the range of VM_LOCKED vma. */ ptes++; pra->mapcount--; continue; } if (pvmw.pte) { if (lru_gen_enabled() && pte_young(ptep_get(pvmw.pte))) { lru_gen_look_around(&pvmw); referenced++; } if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } pra->mapcount--; } if ((vma->vm_flags & VM_LOCKED) && folio_test_large(folio) && folio_within_vma(folio, vma)) { unsigned long s_align, e_align; s_align = ALIGN_DOWN(start, PMD_SIZE); e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); /* folio doesn't cross page table boundary and fully mapped */ if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { int we_locked = 0; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } int folio_total_mapcount(struct folio *folio) { int mapcount = folio_entire_mapcount(folio); int nr_pages; int i; /* In the common case, avoid the loop when no pages mapped by PTE */ if (folio_nr_pages_mapped(folio) == 0) return mapcount; /* * Add all the PTE mappings of those pages mapped by PTE. * Limit the loop to folio_nr_pages_mapped()? * Perhaps: given all the raciness, that may be a good or a bad idea. */ nr_pages = folio_nr_pages(folio); for (i = 0; i < nr_pages; i++) mapcount += atomic_read(&folio_page(folio, i)->_mapcount); /* But each of those _mapcounts was based on -1 */ mapcount += nr_pages; return mapcount; } static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { atomic_t *mapped = &folio->_nr_pages_mapped; int first, nr = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: do { first = atomic_inc_and_test(&page->_mapcount); if (first && folio_test_large(folio)) { first = atomic_inc_return_relaxed(mapped); first = (first < ENTIRELY_MAPPED); } if (first) nr++; } while (page++, --nr_pages > 0); break; case RMAP_LEVEL_PMD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { *nr_pmdmapped = folio_nr_pages(folio); nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } break; } return nr; } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum rmap_level level) { int i, nr, nr_pmdmapped = 0; nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped); if (nr) __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); if (unlikely(!folio_test_anon(folio))) { VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); /* * For a PTE-mapped large folio, we only know that the single * PTE is exclusive. Further, __folio_set_anon() might not get * folio->index right when not given the address of the head * page. */ VM_WARN_ON_FOLIO(folio_test_large(folio) && level != RMAP_LEVEL_PMD, folio); __folio_set_anon(folio, vma, address, !!(flags & RMAP_EXCLUSIVE)); } else if (likely(!folio_test_ksm(folio))) { __page_check_anon_rmap(folio, page, vma, address); } if (flags & RMAP_EXCLUSIVE) { switch (level) { case RMAP_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case RMAP_LEVEL_PMD: SetPageAnonExclusive(page); break; } } for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 || (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && PageAnonExclusive(cur_page), folio); } /* * For large folio, only mlock it if it's fully mapped to VMA. It's * not easy to check whether the large folio is fully mapped to VMA * here. Only mlock normal 4K folio and leave page reclaim to handle * large folio. */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, RMAP_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio does not have to be locked. * * If the folio is pmd-mappable, it is accounted as a THP. As the folio * is new, it's assumed to be mapped exclusively by a single process. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { int nr = folio_nr_pages(folio); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, true); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); SetPageAnonExclusive(page); } atomic_set(&folio->_nr_pages_mapped, nr); } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); SetPageAnonExclusive(&folio->page); __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr); } __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { int nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED, nr_pmdmapped); if (nr) __lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr); /* See comments in folio_add_anon_rmap_*() */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last, nr = 0, nr_pmdmapped = 0; enum node_stat_item idx; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: do { last = atomic_add_negative(-1, &page->_mapcount); if (last && folio_test_large(folio)) { last = atomic_dec_return_relaxed(mapped); last = (last < ENTIRELY_MAPPED); } if (last) nr++; } while (page++, --nr_pages > 0); break; case RMAP_LEVEL_PMD: last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pmdmapped = folio_nr_pages(folio); nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } break; } if (nr_pmdmapped) { if (folio_test_anon(folio)) idx = NR_ANON_THPS; else if (folio_test_swapbacked(folio)) idx = NR_SHMEM_PMDMAPPED; else idx = NR_FILE_PMDMAPPED; __lruvec_stat_mod_folio(folio, idx, -nr_pmdmapped); } if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; __lruvec_stat_mod_folio(folio, idx, -nr); /* * Queue anon large folio for deferred split if at least one * page of the folio is unmapped and at least one page * is still mapped. */ if (folio_test_large(folio) && folio_test_anon(folio)) if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped) deferred_split_folio(folio); } /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; if (flags & TTU_SPLIT_HUGE_PMD) split_huge_pmd_address(vma, address, false, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); ret = false; break; } pfn = pte_pfn(ptep_get(pvmw.pte)); subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(&folio->page)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && !folio_test_dirty(folio)) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the folio was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); folio_set_swapbacked(folio); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(&folio->page)); } discard: if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * unmap_page() in mm/huge_memory.c is the only user of migration with * TTU_SPLIT_HUGE_PMD and it wants to freeze. */ if (flags & TTU_SPLIT_HUGE_PMD) split_huge_pmd_address(vma, address, true, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { subpage = folio_page(folio, pmd_pfn(*pvmw.pmd) - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; } #endif /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); if (folio_is_zone_device(folio)) { /* * Our PTE is a non-present device exclusive entry and * calculating the subpage as for the common case would * result in an invalid pointer. * * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); subpage = &folio->page; } else { subpage = folio_page(folio, pfn - folio_pfn(folio)); } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (folio_is_device_private(folio)) { unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; if (anon_exclusive) WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio, subpage)); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); trace_set_migration_pte(pvmw.address, pte_val(swp_pte), compound_order(&folio->page)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(&folio->page)); } else { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), compound_order(&folio->page)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { struct mm_struct *mm; unsigned long address; void *owner; bool valid; }; static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; swp_entry_t entry; pte_t swp_pte; pte_t ptent; mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, address, min(vma->vm_end, address + folio_size(folio)), args->owner); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); ptent = ptep_get(pvmw.pte); if (!pte_present(ptent)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } subpage = folio_page(folio, pte_pfn(ptent) - folio_pfn(folio)); address = pvmw.address; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(ptent)); pteval = ptep_clear_flush(vma, address, pvmw.pte); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* * Check that our target page is still mapped at the expected * address. */ if (args->mm == mm && args->address == address && pte_write(pteval)) args->valid = true; /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_device_exclusive_entry( page_to_pfn(subpage)); else entry = make_readable_device_exclusive_entry( page_to_pfn(subpage)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ folio_remove_rmap_pte(folio, subpage, vma); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * folio_make_device_exclusive - Mark the folio exclusively owned by a device. * @folio: The folio to replace page table entries for. * @mm: The mm_struct where the folio is expected to be mapped. * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * * Tries to remove all the page table entries which are mapping this * folio and replace them with special device exclusive swap entries to * grant a device exclusive access to the folio. * * Context: Caller must hold the folio lock. * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ static bool folio_make_device_exclusive(struct folio *folio, struct mm_struct *mm, unsigned long address, void *owner) { struct make_exclusive_args args = { .mm = mm, .address = address, .owner = owner, .valid = false, }; struct rmap_walk_control rwc = { .rmap_one = page_make_device_exclusive_one, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, .arg = &args, }; /* * Restrict to anonymous folios for now to avoid potential writeback * issues. */ if (!folio_test_anon(folio)) return false; rmap_walk(folio, &rwc); return args.valid && !folio_mapcount(folio); } /** * make_device_exclusive_range() - Mark a range for exclusive use by a device * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * * Returns: number of pages found in the range by GUP. A page is marked for * exclusive access only if the page pointer is non-NULL. * * This function finds ptes mapping page(s) to the given address range, locks * them and replaces mappings with special swap entries preventing userspace CPU * access. On fault these entries are replaced with the original mapping after * calling MMU notifiers. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the page lock and reference after * which point CPU access to the page will revoke the exclusive access. */ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *owner) { long npages = (end - start) >> PAGE_SHIFT; long i; npages = get_user_pages_remote(mm, start, npages, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, pages, NULL); if (npages < 0) return npages; for (i = 0; i < npages; i++, start += PAGE_SIZE) { struct folio *folio = page_folio(pages[i]); if (PageTail(pages[i]) || !folio_trylock(folio)) { folio_put(folio); pages[i] = NULL; continue; } if (!folio_make_device_exclusive(folio, mm, start, owner)) { folio_unlock(folio); folio_put(folio); pages[i] = NULL; } } return npages; } EXPORT_SYMBOL_GPL(make_device_exclusive_range); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(&folio->page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!mapping) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(&folio->page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 377 57 3665 150 3665 3712 631 3670 3667 3790 3779 187 187 187 3713 3794 3763 3770 3709 3712 3716 1081 1834 3200 2789 500 179 3254 2396 422 2688 2692 2686 381 473 3547 3548 433 3546 2 2 3552 45 638 2168 9 9 2520 3541 3543 3545 3541 187 3550 5 438 87 236 2824 82 158 629 115 630 603 13 2 4 585 185 181 4 585 4 580 78 629 629 630 41 630 119 442 12 189 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * * Copyright (c) 2015-2016 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * Code partially derived from nft_hash * Rewritten with rehash code from br_multicast plus single list * pointer as suggested by Josh Triplett * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H #include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/rculist.h> #include <linux/bit_spinlock.h> #include <linux/rhashtable-types.h> /* * Objects in an rhashtable have an embedded struct rhash_head * which is linked into as hash chain from the hash table - or one * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has * the least significant bit set but otherwise stores the address of * the hash bucket. This allows us to be sure we've found the end * of the right list. * The value stored in the hash bucket has BIT(0) used as a lock bit. * This bit must be atomically set before any changes are made to * the chain. To avoid dereferencing this pointer without clearing * the bit first, we use an opaque 'struct rhash_lock_head *' for the * pointer stored in the bucket. This struct needs to be defined so * that rcu_dereference() works on it, but it has no content so a * cast is needed for it to be useful. This ensures it isn't * used by mistake with clearing the lock bit first. */ struct rhash_lock_head {}; /* Maximum chain length before rehash * * The maximum (not average) chain length grows with the size of the hash * table, at a rate of (log N)/(log log N). * * The value of 16 is selected so that even if the hash table grew to * 2^32 you would not expect the maximum chain length to exceed it * unless we are under attack (or extremely unlucky). * * As this limit is only to detect attacks, we don't need to set it to a * lower value as you'd need the chain length to vastly exceed 16 to have * any real effect on the system. */ #define RHT_ELASTICITY 16u /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets * @nest: Number of bits of first-level nested table. * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash * @walkers: List of active walkers * @rcu: RCU structure for freeing the table * @future_tbl: Table under construction during rehashing * @ntbl: Nested table used when out of memory. * @buckets: size * hash buckets */ struct bucket_table { unsigned int size; unsigned int nest; u32 hash_rnd; struct list_head walkers; struct rcu_head rcu; struct bucket_table __rcu *future_tbl; struct lockdep_map dep_map; struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards * the msb. * We give it an address, in which the bottom bit is * always 0, and the msb might be significant. * So we shift the address down one bit to align with * expectations and avoid losing a significant bit. * * We never store the NULLS_MARKER in the hash table * itself as we need the lsb for locking. * Instead we store a NULL */ #define RHT_NULLS_MARKER(ptr) \ ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ ((ptr) = NULL) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { return ((unsigned long) ptr & 1); } static inline void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { return (char *)he - ht->p.head_offset; } static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { return hash & (tbl->size - 1); } static inline unsigned int rht_key_get_hash(struct rhashtable *ht, const void *key, const struct rhashtable_params params, unsigned int hash_rnd) { unsigned int hash; /* params must be equal to ht->p if it isn't constant. */ if (!__builtin_constant_p(params.key_len)) hash = ht->p.hashfn(key, ht->key_len, hash_rnd); else if (params.key_len) { unsigned int key_len = params.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, hash_rnd); else if (key_len & (sizeof(u32) - 1)) hash = jhash(key, key_len, hash_rnd); else hash = jhash2(key, key_len / sizeof(u32), hash_rnd); } else { unsigned int key_len = ht->p.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, hash_rnd); else hash = jhash(key, key_len, hash_rnd); } return hash; } static inline unsigned int rht_key_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const void *key, const struct rhashtable_params params) { unsigned int hash = rht_key_get_hash(ht, key, params, tbl->hash_rnd); return rht_bucket_index(tbl, hash); } static inline unsigned int rht_head_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const struct rhash_head *he, const struct rhashtable_params params) { const char *ptr = rht_obj(ht, he); return likely(params.obj_hashfn) ? rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?: ht->p.key_len, tbl->hash_rnd)) : rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); } /** * rht_grow_above_75 - returns true if nelems > 0.75 * table-size * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_75(const struct rhashtable *ht, const struct bucket_table *tbl) { /* Expand table when exceeding 75% load */ return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) && (!ht->p.max_size || tbl->size < ht->p.max_size); } /** * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size * @ht: hash table * @tbl: current table */ static inline bool rht_shrink_below_30(const struct rhashtable *ht, const struct bucket_table *tbl) { /* Shrink table beneath 30% load */ return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) && tbl->size > ht->p.min_size; } /** * rht_grow_above_100 - returns true if nelems > table-size * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { return atomic_read(&ht->nelems) > tbl->size && (!ht->p.max_size || tbl->size < ht->p.max_size); } /** * rht_grow_above_max - returns true if table is above maximum * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_max(const struct rhashtable *ht, const struct bucket_table *tbl) { return atomic_read(&ht->nelems) >= ht->max_elems; } #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); #else static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht) { return 1; } static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { return 1; } #endif /* CONFIG_PROVE_LOCKING */ void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj); void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU); static inline void rhashtable_walk_start(struct rhashtable_iter *iter) { (void)rhashtable_walk_start_check(iter); } void *rhashtable_walk_next(struct rhashtable_iter *iter); void *rhashtable_walk_peek(struct rhashtable_iter *iter); void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg); void rhashtable_destroy(struct rhashtable *ht); struct rhash_lock_head __rcu **rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash); struct rhash_lock_head __rcu **__rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash); struct rhash_lock_head __rcu **rht_bucket_nested_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) #define rht_dereference_rcu(p, ht) \ rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht)) #define rht_dereference_bucket(p, tbl, hash) \ rcu_dereference_protected(p, lockdep_rht_bucket_is_held(tbl, hash)) #define rht_dereference_bucket_rcu(p, tbl, hash) \ rcu_dereference_check(p, lockdep_rht_bucket_is_held(tbl, hash)) #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : &tbl->buckets[hash]; } /* * We lock a bucket by setting BIT(0) in the pointer - this is always * zero in real pointers. The NULLS mark is never stored in the bucket, * rather we store NULL if the bucket is empty. * bit_spin_locks do not handle contention well, but the whole point * of the hashtable design is to achieve minimum per-bucket contention. * A nested hash table might not have a bucket pointer. In that case * we cannot get a lock. For remove and replace the bucket cannot be * interesting and doesn't need locking. * For insert we allocate the bucket if this is the last bucket_table, * and then take the lock. * Sometimes we unlock a bucket by writing a new pointer there. In that * case we don't need to unlock, but we do need to reset state such as * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() * provides the same release semantics that bit_spin_unlock() provides, * this is safe. * When we write to a bucket without unlocking, we use rht_assign_locked(). */ static inline unsigned long rht_lock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt) { unsigned long flags; local_irq_save(flags); bit_spin_lock(0, (unsigned long *)bkt); lock_map_acquire(&tbl->dep_map); return flags; } static inline unsigned long rht_lock_nested(struct bucket_table *tbl, struct rhash_lock_head __rcu **bucket, unsigned int subclass) { unsigned long flags; local_irq_save(flags); bit_spin_lock(0, (unsigned long *)bucket); lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); return flags; } static inline void rht_unlock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt, unsigned long flags) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); local_irq_restore(flags); } static inline struct rhash_head *__rht_ptr( struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { return (struct rhash_head *) ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } /* * Where 'bkt' is a bucket and might be locked: * rht_ptr_rcu() dereferences that pointer and clears the lock bit. * rht_ptr() dereferences in a context where the bucket is locked. * rht_ptr_exclusive() dereferences in a context where exclusive * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( struct rhash_lock_head __rcu *const *bkt) { return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( struct rhash_lock_head __rcu *const *bkt) { return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { if (rht_is_a_nulls(obj)) obj = NULL; rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt, struct rhash_head *obj, unsigned long flags) { if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_irq_restore(flags); } /** * rht_for_each_from - iterate over hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ #define rht_for_each_from(pos, head, tbl, hash) \ for (pos = head; \ !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** * rht_for_each - iterate over hash chain * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ tbl, hash) /** * rht_for_each_entry_from - iterate over hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ for (pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** * rht_for_each_entry - iterate over hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ rht_for_each_entry_from(tpos, pos, \ rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ tbl, hash, member) /** * rht_for_each_entry_safe - safely iterate over hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @next: the &struct rhash_head to use as next in loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive allows for the looped code to * remove the loop cursor from the list. */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = next, \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** * rht_for_each_rcu_from - iterate over rcu hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ pos = head; \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_rcu - iterate over rcu hash chain * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu(pos, tbl, hash) \ for (({barrier(); }), \ pos = rht_ptr_rcu(rht_bucket(tbl, hash)); \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) /** * rht_for_each_entry_rcu - iterate over rcu hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ rht_for_each_entry_rcu_from(tpos, pos, \ rht_ptr_rcu(rht_bucket(tbl, hash)), \ tbl, hash, member) /** * rhl_for_each_rcu - iterate over rcu hash table list * @pos: the &struct rlist_head to use as a loop cursor. * @list: the head of the list * * This hash chain list-traversal primitive should be used on the * list returned by rhltable_lookup. */ #define rhl_for_each_rcu(pos, list) \ for (pos = list; pos; pos = rcu_dereference_raw(pos->next)) /** * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rlist_head to use as a loop cursor. * @list: the head of the list * @member: name of the &struct rlist_head within the hashable struct. * * This hash chain list-traversal primitive should be used on the * list returned by rhltable_lookup. */ #define rhl_for_each_entry_rcu(tpos, pos, list, member) \ for (pos = list; pos && rht_entry(tpos, pos, member); \ pos = rcu_dereference_raw(pos->next)) static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, const void *obj) { struct rhashtable *ht = arg->ht; const char *ptr = obj; return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); } /* Internal function, do not use. */ static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { rht_for_each_rcu_from(he, rht_ptr_rcu(bkt), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) continue; return he; } /* An object might have been moved to a different hash chain, * while we walk along it - better check and retry. */ } while (he != RHT_NULLS_MARKER(bkt)); /* Ensure we see any new tables. */ smp_rmb(); tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; return NULL; } /** * rhashtable_lookup - search hash table * @ht: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * * Returns the first entry on which the compare function returned true. */ static inline void *rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { struct rhash_head *he = __rhashtable_lookup(ht, key, params); return he ? rht_obj(ht, he) : NULL; } /** * rhashtable_lookup_fast - search hash table, without RCU read lock * @ht: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. * * Returns the first entry on which the compare function returned true. */ static inline void *rhashtable_lookup_fast( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { void *obj; rcu_read_lock(); obj = rhashtable_lookup(ht, key, params); rcu_read_unlock(); return obj; } /** * rhltable_lookup - search hash list table * @hlt: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. * * Returns the list of entries that match the given key. */ static inline struct rhlist_head *rhltable_lookup( struct rhltable *hlt, const void *key, const struct rhashtable_params params) { struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params); return he ? container_of(he, struct rhlist_head, rhead) : NULL; } /* Internal function, please use rhashtable_insert_fast() instead. This * function returns the existing element already in hashes in there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; unsigned long flags; unsigned int hash; int elasticity; void *data; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); hash = rht_head_hashfn(ht, tbl, obj, params); elasticity = RHT_ELASTICITY; bkt = rht_bucket_insert(ht, tbl, hash); data = ERR_PTR(-ENOMEM); if (!bkt) goto out; pprev = NULL; flags = rht_lock(tbl, bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: rht_unlock(tbl, bkt, flags); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; elasticity--; if (!key || (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, head)) : rhashtable_compare(&arg, rht_obj(ht, head)))) { pprev = &head->next; continue; } data = rht_obj(ht, head); if (!rhlist) goto out_unlock; list = container_of(obj, struct rhlist_head, rhead); plist = container_of(head, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); if (pprev) { rcu_assign_pointer(*pprev, obj); rht_unlock(tbl, bkt, flags); } else rht_assign_unlock(tbl, bkt, obj, flags); data = NULL; goto out; } if (elasticity <= 0) goto slow_path; data = ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_max(ht, tbl))) goto out_unlock; if (unlikely(rht_grow_above_100(ht, tbl))) goto slow_path; /* Inserting at head of list makes unlocking free. */ head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (rhlist) { struct rhlist_head *list; list = container_of(obj, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, NULL); } atomic_inc(&ht->nelems); rht_assign_unlock(tbl, bkt, obj, flags); if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); data = NULL; out: rcu_read_unlock(); return data; out_unlock: rht_unlock(tbl, bkt, flags); goto out; } /** * rhashtable_insert_fast - insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhashtable_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { void *ret; ret = __rhashtable_insert_fast(ht, NULL, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhltable_insert_key - insert object into hash list table * @hlt: hash list table * @key: the pointer to the key * @list: pointer to hash list head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhltable_insert_key( struct rhltable *hlt, const void *key, struct rhlist_head *list, const struct rhashtable_params params) { return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead, params, true)); } /** * rhltable_insert - insert object into hash list table * @hlt: hash list table * @list: pointer to hash list head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhltable_insert( struct rhltable *hlt, struct rhlist_head *list, const struct rhashtable_params params) { const char *key = rht_obj(&hlt->ht, &list->rhead); key += params.key_offset; return rhltable_insert_key(hlt, key, list, params); } /** * rhashtable_lookup_insert_fast - lookup and insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * This lookup function may only be used for fixed key hash table (key_len * parameter set). It will BUG() if used inappropriately. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhashtable_lookup_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { const char *key = rht_obj(ht, obj); void *ret; BUG_ON(ht->p.obj_hashfn); ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Just like rhashtable_lookup_insert_fast(), but this function returns the * object if it exists, NULL if it did not and the insertion was successful, * and an ERR_PTR otherwise. */ static inline void *rhashtable_lookup_get_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { const char *key = rht_obj(ht, obj); BUG_ON(ht->p.obj_hashfn); return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, false); } /** * rhashtable_lookup_insert_key - search and insert object to hash table * with explicit key * @ht: hash table * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters * * Lookups may occur in parallel with hashtable mutations and resizing. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. * * Returns zero on success. */ static inline int rhashtable_lookup_insert_key( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params) { void *ret; BUG_ON(!ht->p.obj_hashfn || !key); ret = __rhashtable_insert_fast(ht, key, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhashtable_lookup_get_insert_key - lookup and insert object into hash table * @ht: hash table * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters * * Just like rhashtable_lookup_insert_key(), but this function returns the * object if it exists, NULL if it does not and the insertion was successful, * and an ERR_PTR otherwise. */ static inline void *rhashtable_lookup_get_insert_key( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params) { BUG_ON(!ht->p.obj_hashfn || !key); return __rhashtable_insert_fast(ht, key, obj, params, false); } /* Internal function, please use rhashtable_remove_fast() instead */ static inline int __rhashtable_remove_fast_one( struct rhashtable *ht, struct bucket_table *tbl, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned long flags; unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); bkt = rht_bucket_var(tbl, hash); if (!bkt) return -ENOENT; pprev = NULL; flags = rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); if (he != obj) { struct rhlist_head __rcu **lpprev; pprev = &he->next; if (!rhlist) continue; do { lpprev = &list->next; list = rht_dereference_bucket(list->next, tbl, hash); } while (list && obj != &list->rhead); if (!list) continue; list = rht_dereference_bucket(list->next, tbl, hash); RCU_INIT_POINTER(*lpprev, list); err = 0; break; } obj = rht_dereference_bucket(obj->next, tbl, hash); err = 1; if (rhlist) { list = rht_dereference_bucket(list->next, tbl, hash); if (list) { RCU_INIT_POINTER(list->rhead.next, obj); obj = &list->rhead; err = 0; } } if (pprev) { rcu_assign_pointer(*pprev, obj); rht_unlock(tbl, bkt, flags); } else { rht_assign_unlock(tbl, bkt, obj, flags); } goto unlocked; } rht_unlock(tbl, bkt, flags); unlocked: if (err > 0) { atomic_dec(&ht->nelems); if (unlikely(ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl))) schedule_work(&ht->run_work); err = 0; } return err; } /* Internal function, please use rhashtable_remove_fast() instead */ static inline int __rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct bucket_table *tbl; int err; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); /* Because we have already taken (and released) the bucket * lock in old_tbl, if we find that future_tbl is not yet * visible then that guarantees the entry to still be in * the old tbl if it exists. */ while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params, rhlist)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; rcu_read_unlock(); return err; } /** * rhashtable_remove_fast - remove object from hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30%. * * Returns zero on success, -ENOENT if the entry could not be found. */ static inline int rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { return __rhashtable_remove_fast(ht, obj, params, false); } /** * rhltable_remove - remove object from hash list table * @hlt: hash list table * @list: pointer to hash list head inside object * @params: hash table parameters * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% * * Returns zero on success, -ENOENT if the entry could not be found. */ static inline int rhltable_remove( struct rhltable *hlt, struct rhlist_head *list, const struct rhashtable_params params) { return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true); } /* Internal function, please use rhashtable_replace_fast() instead */ static inline int __rhashtable_replace_fast( struct rhashtable *ht, struct bucket_table *tbl, struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned long flags; unsigned int hash; int err = -ENOENT; /* Minimally, the old and new objects must have same hash * (which should mean identifiers are the same). */ hash = rht_head_hashfn(ht, tbl, obj_old, params); if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) return -EINVAL; bkt = rht_bucket_var(tbl, hash); if (!bkt) return -ENOENT; pprev = NULL; flags = rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; } rcu_assign_pointer(obj_new->next, obj_old->next); if (pprev) { rcu_assign_pointer(*pprev, obj_new); rht_unlock(tbl, bkt, flags); } else { rht_assign_unlock(tbl, bkt, obj_new, flags); } err = 0; goto unlocked; } rht_unlock(tbl, bkt, flags); unlocked: return err; } /** * rhashtable_replace_fast - replace an object in hash table * @ht: hash table * @obj_old: pointer to hash head inside object being replaced * @obj_new: pointer to hash head inside object which is new * @params: hash table parameters * * Replacing an object doesn't affect the number of elements in the hash table * or bucket, so we don't need to worry about shrinking or expanding the * table here. * * Returns zero on success, -ENOENT if the entry could not be found, * -EINVAL if hash is not the same for the old and new objects. */ static inline int rhashtable_replace_fast( struct rhashtable *ht, struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { struct bucket_table *tbl; int err; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); /* Because we have already taken (and released) the bucket * lock in old_tbl, if we find that future_tbl is not yet * visible then that guarantees the entry to still be in * the old tbl if it exists. */ while ((err = __rhashtable_replace_fast(ht, tbl, obj_old, obj_new, params)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; rcu_read_unlock(); return err; } /** * rhltable_walk_enter - Initialise an iterator * @hlt: Table to walk over * @iter: Hash table Iterator * * This function prepares a hash table walk. * * Note that if you restart a walk after rhashtable_walk_stop you * may see the same object twice. Also, you may miss objects if * there are removals in between rhashtable_walk_stop and the next * call to rhashtable_walk_start. * * For a completely stable walk you should construct your own data * structure outside the hash table. * * This function may be called from any process context, including * non-preemptable context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ static inline void rhltable_walk_enter(struct rhltable *hlt, struct rhashtable_iter *iter) { return rhashtable_walk_enter(&hlt->ht, iter); } /** * rhltable_free_and_destroy - free elements and destroy hash list table * @hlt: the hash list table to destroy * @free_fn: callback to release resources of element * @arg: pointer passed to free_fn * * See documentation for rhashtable_free_and_destroy. */ static inline void rhltable_free_and_destroy(struct rhltable *hlt, void (*free_fn)(void *ptr, void *arg), void *arg) { return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); } static inline void rhltable_destroy(struct rhltable *hlt) { return rhltable_free_and_destroy(hlt, NULL, NULL); } #endif /* _LINUX_RHASHTABLE_H */ |
| 32 21 59 1647 940 183 1188 1722 3717 1793 365 197 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 /** * struct ext4_journal_cb_entry - Base structure for callback information. * * This struct is a 'seed' structure for a using with your own callback * structs. If you are using callbacks you must allocate one of these * or another struct of your own definition which has this struct * as it's first element and pass it to ext4_journal_callback_add(). */ struct ext4_journal_cb_entry { /* list information for other callbacks attached to the same handle */ struct list_head jce_list; /* Function to call with this callback structure */ void (*jce_func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int error); /* user data goes here */ }; /** * ext4_journal_callback_add: add a function to call after transaction commit * @handle: active journal transaction handle to register callback on * @func: callback function to call after the transaction has committed: * @sb: superblock of current filesystem for transaction * @jce: returned journal callback data * @rc: journal state at commit (0 = transaction committed properly) * @jce: journal callback data (internal and function private data struct) * * The registered function will be called in the context of the journal thread * after the transaction for which the handle was created has completed. * * No locks are held when the callback function is called, so it is safe to * call blocking functions from within the callback, but the callback should * not block or run for too long, or the filesystem will be blocked waiting for * the next transaction to commit. No journaling functions can be used, or * there is a risk of deadlock. * * There is no guaranteed calling order of multiple registered callbacks on * the same transaction. */ static inline void _ext4_journal_callback_add(handle_t *handle, struct ext4_journal_cb_entry *jce) { /* Add the jce to transaction's private list */ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list); } static inline void ext4_journal_callback_add(handle_t *handle, void (*func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int rc), struct ext4_journal_cb_entry *jce) { struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); /* Add the jce to transaction's private list */ jce->jce_func = func; spin_lock(&sbi->s_md_lock); _ext4_journal_callback_add(handle, jce); spin_unlock(&sbi->s_md_lock); } /** * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister * Return true if object was successfully removed */ static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); return deleted; } int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_page(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_page(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } #endif /* _EXT4_JBD2_H */ |
| 25 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* incoming call handling * * Copyright (C) 2007 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/errqueue.h> #include <linux/udp.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/icmp.h> #include <linux/gfp.h> #include <linux/circ_buf.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> #include "ar-internal.h" static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call, unsigned long user_call_ID) { } /* * Preallocate a single service call, connection and peer and, if possible, * give them a user ID and attach the user's side of the ID to them. */ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, struct rxrpc_backlog *b, rxrpc_notify_rx_t notify_rx, rxrpc_user_attach_call_t user_attach_call, unsigned long user_call_ID, gfp_t gfp, unsigned int debug_id) { struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); struct rb_node *parent, **pp; int max, tmp; unsigned int size = RXRPC_BACKLOG_MAX; unsigned int head, tail, call_head, call_tail; max = rx->sk.sk_max_ack_backlog; tmp = rx->sk.sk_ack_backlog; if (tmp >= max) { _leave(" = -ENOBUFS [full %u]", max); return -ENOBUFS; } max -= tmp; /* We don't need more conns and peers than we have calls, but on the * other hand, we shouldn't ever use more peers than conns or conns * than calls. */ call_head = b->call_backlog_head; call_tail = READ_ONCE(b->call_backlog_tail); tmp = CIRC_CNT(call_head, call_tail, size); if (tmp >= max) { _leave(" = -ENOBUFS [enough %u]", tmp); return -ENOBUFS; } max = tmp + 1; head = b->peer_backlog_head; tail = READ_ONCE(b->peer_backlog_tail); if (CIRC_CNT(head, tail, size) < max) { struct rxrpc_peer *peer; peer = rxrpc_alloc_peer(rx->local, gfp, rxrpc_peer_new_prealloc); if (!peer) return -ENOMEM; b->peer_backlog[head] = peer; smp_store_release(&b->peer_backlog_head, (head + 1) & (size - 1)); } head = b->conn_backlog_head; tail = READ_ONCE(b->conn_backlog_tail); if (CIRC_CNT(head, tail, size) < max) { struct rxrpc_connection *conn; conn = rxrpc_prealloc_service_connection(rxnet, gfp); if (!conn) return -ENOMEM; b->conn_backlog[head] = conn; smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); } /* Now it gets complicated, because calls get registered with the * socket here, with a user ID preassigned by the user. */ call = rxrpc_alloc_call(rx, gfp, debug_id); if (!call) return -ENOMEM; call->flags |= (1 << RXRPC_CALL_IS_SERVICE); rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC); __set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), user_call_ID, rxrpc_call_new_prealloc_service); write_lock(&rx->call_lock); /* Check the user ID isn't already in use */ pp = &rx->calls.rb_node; parent = NULL; while (*pp) { parent = *pp; xcall = rb_entry(parent, struct rxrpc_call, sock_node); if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else goto id_in_use; } call->user_call_ID = user_call_ID; call->notify_rx = notify_rx; if (user_attach_call) { rxrpc_get_call(call, rxrpc_call_get_kernel_service); user_attach_call(call, user_call_ID); } rxrpc_get_call(call, rxrpc_call_get_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); set_bit(RXRPC_CALL_HAS_USERID, &call->flags); list_add(&call->sock_link, &rx->sock_calls); write_unlock(&rx->call_lock); rxnet = call->rxnet; spin_lock(&rxnet->call_lock); list_add_tail_rcu(&call->link, &rxnet->calls); spin_unlock(&rxnet->call_lock); b->call_backlog[call_head] = call; smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1)); _leave(" = 0 [%d -> %lx]", call->debug_id, user_call_ID); return 0; id_in_use: write_unlock(&rx->call_lock); rxrpc_cleanup_call(call); _leave(" = -EBADSLT"); return -EBADSLT; } /* * Allocate the preallocation buffers for incoming service calls. These must * be charged manually. */ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) { struct rxrpc_backlog *b = rx->backlog; if (!b) { b = kzalloc(sizeof(struct rxrpc_backlog), gfp); if (!b) return -ENOMEM; rx->backlog = b; } return 0; } /* * Discard the preallocation on a service. */ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) { struct rxrpc_backlog *b = rx->backlog; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); unsigned int size = RXRPC_BACKLOG_MAX, head, tail; if (!b) return; rx->backlog = NULL; /* Make sure that there aren't any incoming calls in progress before we * clear the preallocation buffers. */ spin_lock(&rx->incoming_lock); spin_unlock(&rx->incoming_lock); head = b->peer_backlog_head; tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; rxrpc_put_local(peer->local, rxrpc_local_put_prealloc_peer); kfree(peer); tail = (tail + 1) & (size - 1); } head = b->conn_backlog_head; tail = b->conn_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_connection *conn = b->conn_backlog[tail]; write_lock(&rxnet->conn_lock); list_del(&conn->link); list_del(&conn->proc_link); write_unlock(&rxnet->conn_lock); kfree(conn); if (atomic_dec_and_test(&rxnet->nr_conns)) wake_up_var(&rxnet->nr_conns); tail = (tail + 1) & (size - 1); } head = b->call_backlog_head; tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; rcu_assign_pointer(call->socket, rx); if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); if (call->notify_rx) call->notify_rx = rxrpc_dummy_notify; rxrpc_put_call(call, rxrpc_call_put_kernel); } rxrpc_call_completed(call); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put_discard_prealloc); tail = (tail + 1) & (size - 1); } kfree(b); } /* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. */ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, const struct rxrpc_security *sec, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; struct rxrpc_call *call; unsigned short call_head, conn_head, peer_head; unsigned short call_tail, conn_tail, peer_tail; unsigned short call_count, conn_count; /* #calls >= #conns >= #peers must hold true. */ call_head = smp_load_acquire(&b->call_backlog_head); call_tail = b->call_backlog_tail; call_count = CIRC_CNT(call_head, call_tail, RXRPC_BACKLOG_MAX); conn_head = smp_load_acquire(&b->conn_backlog_head); conn_tail = b->conn_backlog_tail; conn_count = CIRC_CNT(conn_head, conn_tail, RXRPC_BACKLOG_MAX); ASSERTCMP(conn_count, >=, call_count); peer_head = smp_load_acquire(&b->peer_backlog_head); peer_tail = b->peer_backlog_tail; ASSERTCMP(CIRC_CNT(peer_head, peer_tail, RXRPC_BACKLOG_MAX), >=, conn_count); if (call_count == 0) return NULL; if (!conn) { if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_service_conn)) peer = NULL; if (!peer) { peer = b->peer_backlog[peer_tail]; peer->srx = *peer_srx; b->peer_backlog[peer_tail] = NULL; smp_store_release(&b->peer_backlog_tail, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); rxrpc_new_incoming_peer(local, peer); } /* Now allocate and set up the connection */ conn = b->conn_backlog[conn_tail]; b->conn_backlog[conn_tail] = NULL; smp_store_release(&b->conn_backlog_tail, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); conn->local = rxrpc_get_local(local, rxrpc_local_get_prealloc_conn); conn->peer = peer; rxrpc_see_connection(conn, rxrpc_conn_see_new_service_conn); rxrpc_new_incoming_connection(rx, conn, sec, skb); } else { rxrpc_get_connection(conn, rxrpc_conn_get_service_conn); atomic_inc(&conn->active); } /* And now we can allocate and set up a new call */ call = b->call_backlog[call_tail]; b->call_backlog[call_tail] = NULL; smp_store_release(&b->call_backlog_tail, (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); rxrpc_see_call(call, rxrpc_call_see_accept); call->local = rxrpc_get_local(conn->local, rxrpc_local_get_call); call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_accept); call->dest_srx = peer->srx; call->cong_ssthresh = call->peer->cong_ssthresh; call->tx_last_sent = ktime_get_real(); return call; } /* * Set up a new incoming call. Called from the I/O thread. * * If this is for a kernel service, when we allocate the call, it will have * three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the * retainer ref obtained from the backlog buffer. Prealloc calls for userspace * services only have the ref from the backlog buffer. * * If we want to report an error, we mark the skb with the packet type and * abort code and return false. */ bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb) { const struct rxrpc_security *sec = NULL; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_call *call = NULL; struct rxrpc_sock *rx; _enter(""); /* Don't set up a call for anything other than a DATA packet. */ if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA) return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call); read_lock(&local->services_lock); /* Weed out packets to services we're not offering. Packets that would * begin a call are explicitly rejected and the rest are just * discarded. */ rx = local->service; if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && sp->hdr.serviceId != rx->second_service) ) { if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.seq == 1) goto unsupported_service; goto discard; } if (!conn) { sec = rxrpc_get_incoming_security(rx, skb); if (!sec) goto unsupported_security; } spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { rxrpc_direct_abort(skb, rxrpc_abort_shut_down, RX_INVALID_OPERATION, -ESHUTDOWN); goto no_call; } call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, peer_srx, skb); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; goto no_call; } trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; if (rx->notify_new_call) rx->notify_new_call(&rx->sk, call, call->user_call_ID); spin_lock(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_UNSECURED) { conn->state = RXRPC_CONN_SERVICE_CHALLENGING; set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); rxrpc_queue_conn(call->conn, rxrpc_conn_queue_challenge); } spin_unlock(&conn->state_lock); spin_unlock(&rx->incoming_lock); read_unlock(&local->services_lock); if (hlist_unhashed(&call->error_link)) { spin_lock(&call->peer->lock); hlist_add_head(&call->error_link, &call->peer->error_targets); spin_unlock(&call->peer->lock); } _leave(" = %p{%d}", call, call->debug_id); rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); return true; unsupported_service: read_unlock(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EOPNOTSUPP); unsupported_security: read_unlock(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); read_unlock(&local->services_lock); _leave(" = f [%u]", skb->mark); return false; discard: read_unlock(&local->services_lock); return true; } /* * Charge up socket with preallocated calls, attaching user call IDs. */ int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID) { struct rxrpc_backlog *b = rx->backlog; if (rx->sk.sk_state == RXRPC_CLOSE) return -ESHUTDOWN; return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID, GFP_KERNEL, atomic_inc_return(&rxrpc_debug_id)); } /* * rxrpc_kernel_charge_accept - Charge up socket with preallocated calls * @sock: The socket on which to preallocate * @notify_rx: Event notification function for the call * @user_attach_call: Func to attach call to user_call_ID * @user_call_ID: The tag to attach to the preallocated call * @gfp: The allocation conditions. * @debug_id: The tracing debug ID. * * Charge up the socket with preallocated calls, each with a user ID. A * function should be provided to effect the attachment from the user's side. * The user is given a ref to hold on the call. * * Note that the call may be come connected before this function returns. */ int rxrpc_kernel_charge_accept(struct socket *sock, rxrpc_notify_rx_t notify_rx, rxrpc_user_attach_call_t user_attach_call, unsigned long user_call_ID, gfp_t gfp, unsigned int debug_id) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); struct rxrpc_backlog *b = rx->backlog; if (sock->sk->sk_state == RXRPC_CLOSE) return -ESHUTDOWN; return rxrpc_service_prealloc_one(rx, b, notify_rx, user_attach_call, user_call_ID, gfp, debug_id); } EXPORT_SYMBOL(rxrpc_kernel_charge_accept); |
| 117 109 1 1 6 4 1 1 1 4 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <linux/sysfs.h> #include <linux/nospec.h> #include <asm/intel-family.h> #include "probe.h" enum perf_msr_id { PERF_MSR_TSC = 0, PERF_MSR_APERF = 1, PERF_MSR_MPERF = 2, PERF_MSR_PPERF = 3, PERF_MSR_SMI = 4, PERF_MSR_PTSC = 5, PERF_MSR_IRPERF = 6, PERF_MSR_THERM = 7, PERF_MSR_EVENT_MAX, }; static bool test_aperfmperf(int idx, void *data) { return boot_cpu_has(X86_FEATURE_APERFMPERF); } static bool test_ptsc(int idx, void *data) { return boot_cpu_has(X86_FEATURE_PTSC); } static bool test_irperf(int idx, void *data) { return boot_cpu_has(X86_FEATURE_IRPERF); } static bool test_therm_status(int idx, void *data) { return boot_cpu_has(X86_FEATURE_DTHERM); } static bool test_intel(int idx, void *data) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 != 6) return false; switch (boot_cpu_data.x86_model) { case INTEL_FAM6_NEHALEM: case INTEL_FAM6_NEHALEM_G: case INTEL_FAM6_NEHALEM_EP: case INTEL_FAM6_NEHALEM_EX: case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_SANDYBRIDGE_X: case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_IVYBRIDGE_X: case INTEL_FAM6_HASWELL: case INTEL_FAM6_HASWELL_X: case INTEL_FAM6_HASWELL_L: case INTEL_FAM6_HASWELL_G: case INTEL_FAM6_BROADWELL: case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_GRANITERAPIDS_X: case INTEL_FAM6_GRANITERAPIDS_D: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: case INTEL_FAM6_ATOM_AIRMONT: case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_TREMONT_D: case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_ATOM_TREMONT_L: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; case INTEL_FAM6_SKYLAKE_L: case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_L: case INTEL_FAM6_KABYLAKE: case INTEL_FAM6_COMETLAKE_L: case INTEL_FAM6_COMETLAKE: case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_D: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: case INTEL_FAM6_ATOM_GRACEMONT: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: case INTEL_FAM6_METEORLAKE: case INTEL_FAM6_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; } return false; } PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" ); PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" ); PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" ); PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" ); PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" ); PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" ); PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" ); static unsigned long msr_mask; PMU_EVENT_GROUP(events, aperf); PMU_EVENT_GROUP(events, mperf); PMU_EVENT_GROUP(events, pperf); PMU_EVENT_GROUP(events, smi); PMU_EVENT_GROUP(events, ptsc); PMU_EVENT_GROUP(events, irperf); static struct attribute *attrs_therm[] = { &attr_therm.attr.attr, &attr_therm_snap.attr.attr, &attr_therm_unit.attr.attr, NULL, }; static struct attribute_group group_therm = { .name = "events", .attrs = attrs_therm, }; static struct perf_msr msr[] = { [PERF_MSR_TSC] = { .no_check = true, }, [PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, }, [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, }, [PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, }, [PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, }, [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, }, [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, }, [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, }, }; static struct attribute *events_attrs[] = { &attr_tsc.attr.attr, NULL, }; static struct attribute_group events_attr_group = { .name = "events", .attrs = events_attrs, }; PMU_FORMAT_ATTR(event, "config:0-63"); static struct attribute *format_attrs[] = { &format_attr_event.attr, NULL, }; static struct attribute_group format_attr_group = { .name = "format", .attrs = format_attrs, }; static const struct attribute_group *attr_groups[] = { &events_attr_group, &format_attr_group, NULL, }; static const struct attribute_group *attr_update[] = { &group_aperf, &group_mperf, &group_pperf, &group_smi, &group_ptsc, &group_irperf, &group_therm, NULL, }; static int msr_event_init(struct perf_event *event) { u64 cfg = event->attr.config; if (event->attr.type != event->pmu->type) return -ENOENT; /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; if (cfg >= PERF_MSR_EVENT_MAX) return -EINVAL; cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX); if (!(msr_mask & (1 << cfg))) return -EINVAL; event->hw.idx = -1; event->hw.event_base = msr[cfg].msr; event->hw.config = cfg; return 0; } static inline u64 msr_read_counter(struct perf_event *event) { u64 now; if (event->hw.event_base) rdmsrl(event->hw.event_base, now); else now = rdtsc_ordered(); return now; } static void msr_event_update(struct perf_event *event) { u64 prev, now; s64 delta; /* Careful, an NMI might modify the previous event value: */ prev = local64_read(&event->hw.prev_count); do { now = msr_read_counter(event); } while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, now)); delta = now - prev; if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) { delta = sign_extend64(delta, 31); local64_add(delta, &event->count); } else if (unlikely(event->hw.event_base == MSR_IA32_THERM_STATUS)) { /* If valid, extract digital readout, otherwise set to -1: */ now = now & (1ULL << 31) ? (now >> 16) & 0x3f : -1; local64_set(&event->count, now); } else { local64_add(delta, &event->count); } } static void msr_event_start(struct perf_event *event, int flags) { u64 now = msr_read_counter(event); local64_set(&event->hw.prev_count, now); } static void msr_event_stop(struct perf_event *event, int flags) { msr_event_update(event); } static void msr_event_del(struct perf_event *event, int flags) { msr_event_stop(event, PERF_EF_UPDATE); } static int msr_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) msr_event_start(event, flags); return 0; } static struct pmu pmu_msr = { .task_ctx_nr = perf_sw_context, .attr_groups = attr_groups, .event_init = msr_event_init, .add = msr_event_add, .del = msr_event_del, .start = msr_event_start, .stop = msr_event_stop, .read = msr_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, .attr_update = attr_update, }; static int __init msr_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) { pr_cont("no MSR PMU driver.\n"); return 0; } msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL); perf_pmu_register(&pmu_msr, "msr", -1); return 0; } device_initcall(msr_init); |
| 225 5 222 | 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 | /* * 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 <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)); } |
| 6761 11388 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2021, Google LLC. * Pasha Tatashin <pasha.tatashin@soleen.com> */ #ifndef __LINUX_PAGE_TABLE_CHECK_H #define __LINUX_PAGE_TABLE_CHECK_H #ifdef CONFIG_PAGE_TABLE_CHECK #include <linux/jump_label.h> extern struct static_key_true page_table_check_disabled; extern struct page_ext_operations page_table_check_ops; void __page_table_check_zero(struct page *page, unsigned int order); void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte); void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd); void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud); void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr); void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_free(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear(mm, pte); } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_clear(mm, pmd); } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_clear(mm, pud); } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_ptes_set(mm, ptep, pte, nr); } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_set(mm, pmdp, pmd); } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_set(mm, pudp, pud); } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear_range(mm, addr, pmd); } #else static inline void page_table_check_alloc(struct page *page, unsigned int order) { } static inline void page_table_check_free(struct page *page, unsigned int order) { } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { } #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ |
| 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 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 71 17 1162 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_BIT_H #define _LINUX_WAIT_BIT_H /* * Linux wait-bit related types and methods: */ #include <linux/wait.h> struct wait_bit_key { void *flags; int bit_nr; unsigned long timeout; }; struct wait_bit_queue_entry { struct wait_bit_key key; struct wait_queue_entry wq_entry; }; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue_entry name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ .wq_entry = { \ .private = current, \ .func = wake_bit_function, \ .entry = \ LIST_HEAD_INIT((name).wq_entry.entry), \ }, \ } extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit. * For instance, if one were to have waiters on a bitflag, one would * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, mode); } /** * wait_on_bit_io - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), but calls * io_schedule() instead of schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, mode); } /** * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), except also takes a * timeout parameter. * * Returned value will be zero if the bit was cleared before the * @timeout elapsed, or non-zero if the @timeout elapsed or process * received a signal and the mode permitted wakeup on that signal. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, mode, timeout); } /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared, and allow the waiting action to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } /** * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit * when one intends to set it, for instance, trying to lock bitflags. * For instance, if one were to have waiters trying to set bitflag * and waiting for it to clear before setting it, one would call * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); } /** * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to atomically set it. This is similar * to wait_on_bit(), but calls io_schedule() instead of schedule() * for the actual waiting. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); } /** * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to set it, and allow the waiting action * to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, action, mode); } extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); #define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_head *__wq_head = __var_waitqueue(var); \ struct wait_bit_queue_entry __wbq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_var_entry(&__wbq_entry, var, \ exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(__wq_head, \ &__wbq_entry.wq_entry, \ state); \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(__wq_head, &__wbq_entry.wq_entry); \ __out: __ret; \ }) #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_killable(var, condition); \ __ret; \ }) #define __wait_var_event_timeout(var, condition, timeout) \ ___wait_var_event(var, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_var_event_timeout(var, condition, timeout); \ __ret; \ }) #define __wait_var_event_interruptible(var, condition) \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * * @bit: the bit of the word being waited on * @word: the word being waited on, a kernel virtual address * * You can use this helper if bitflags are manipulated atomically rather than * non-atomically under a lock. */ static inline void clear_and_wake_up_bit(int bit, void *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ smp_mb__after_atomic(); wake_up_bit(word, bit); } #endif /* _LINUX_WAIT_BIT_H */ |
| 7 147 160 7 153 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/ip.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/types.h> #include <net/checksum.h> #include <net/dst_cache.h> #include <net/ip.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/lwtunnel.h> #include <net/protocol.h> #include <uapi/linux/ila.h> #include "ila.h" struct ila_lwt { struct ila_params p; struct dst_cache dst_cache; u32 connected : 1; u32 lwt_output : 1; }; static inline struct ila_lwt *ila_lwt_lwtunnel( struct lwtunnel_state *lwt) { return (struct ila_lwt *)lwt->data; } static inline struct ila_params *ila_params_lwtunnel( struct lwtunnel_state *lwt) { return &ila_lwt_lwtunnel(lwt)->p; } static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct rt6_info *rt = (struct rt6_info *)orig_dst; struct ila_lwt *ilwt = ila_lwt_lwtunnel(orig_dst->lwtstate); struct dst_entry *dst; int err = -EINVAL; if (skb->protocol != htons(ETH_P_IPV6)) goto drop; if (ilwt->lwt_output) ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate), true); if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) { /* Already have a next hop address in route, no need for * dest cache route. */ return orig_dst->lwtstate->orig_output(net, sk, skb); } dst = dst_cache_get(&ilwt->dst_cache); if (unlikely(!dst)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct flowi6 fl6; /* Lookup a route for the new destination. Take into * account that the base route may already have a gateway. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = orig_dst->dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = *rt6_nexthop((struct rt6_info *)orig_dst, &ip6h->daddr); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { err = -EHOSTUNREACH; dst_release(dst); goto drop; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto drop; } if (ilwt->connected) dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr); } skb_dst_set(skb, dst); return dst_output(net, sk, skb); drop: kfree_skb(skb); return err; } static int ila_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ila_lwt *ilwt = ila_lwt_lwtunnel(dst->lwtstate); if (skb->protocol != htons(ETH_P_IPV6)) goto drop; if (!ilwt->lwt_output) ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false); return dst->lwtstate->orig_input(skb); drop: kfree_skb(skb); return -EINVAL; } static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, [ILA_ATTR_HOOK_TYPE] = { .type = NLA_U8, }, }; static int ila_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct ila_lwt *ilwt; struct ila_params *p; struct nlattr *tb[ILA_ATTR_MAX + 1]; struct lwtunnel_state *newts; const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; u8 ident_type = ILA_ATYPE_USE_FORMAT; u8 hook_type = ILA_HOOK_ROUTE_OUTPUT; u8 csum_mode = ILA_CSUM_NO_ACTION; bool lwt_output = true; u8 eff_ident_type; int ret; if (family != AF_INET6) return -EINVAL; ret = nla_parse_nested_deprecated(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; if (!tb[ILA_ATTR_LOCATOR]) return -EINVAL; iaddr = (struct ila_addr *)&cfg6->fc_dst; if (tb[ILA_ATTR_IDENT_TYPE]) ident_type = nla_get_u8(tb[ILA_ATTR_IDENT_TYPE]); if (ident_type == ILA_ATYPE_USE_FORMAT) { /* Infer identifier type from type field in formatted * identifier. */ if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { /* Need to have full locator and at least type field * included in destination */ return -EINVAL; } eff_ident_type = iaddr->ident.type; } else { eff_ident_type = ident_type; } switch (eff_ident_type) { case ILA_ATYPE_IID: /* Don't allow ILA for IID type */ return -EINVAL; case ILA_ATYPE_LUID: break; case ILA_ATYPE_VIRT_V4: case ILA_ATYPE_VIRT_UNI_V6: case ILA_ATYPE_VIRT_MULTI_V6: case ILA_ATYPE_NONLOCAL_ADDR: /* These ILA formats are not supported yet. */ default: return -EINVAL; } if (tb[ILA_ATTR_HOOK_TYPE]) hook_type = nla_get_u8(tb[ILA_ATTR_HOOK_TYPE]); switch (hook_type) { case ILA_HOOK_ROUTE_OUTPUT: lwt_output = true; break; case ILA_HOOK_ROUTE_INPUT: lwt_output = false; break; default: return -EINVAL; } if (tb[ILA_ATTR_CSUM_MODE]) csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); if (csum_mode == ILA_CSUM_NEUTRAL_MAP && ila_csum_neutral_set(iaddr->ident)) { /* Don't allow translation if checksum neutral bit is * configured and it's set in the SIR address. */ return -EINVAL; } newts = lwtunnel_state_alloc(sizeof(*ilwt)); if (!newts) return -ENOMEM; ilwt = ila_lwt_lwtunnel(newts); ret = dst_cache_init(&ilwt->dst_cache, GFP_ATOMIC); if (ret) { kfree(newts); return ret; } ilwt->lwt_output = !!lwt_output; p = ila_params_lwtunnel(newts); p->csum_mode = csum_mode; p->ident_type = ident_type; p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); /* Precompute checksum difference for translation since we * know both the old locator and the new one. */ p->locator_match = iaddr->loc; ila_init_saved_csum(p); newts->type = LWTUNNEL_ENCAP_ILA; newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT | LWTUNNEL_STATE_INPUT_REDIRECT; if (cfg6->fc_dst_len == 8 * sizeof(struct in6_addr)) ilwt->connected = 1; *ts = newts; return 0; } static void ila_destroy_state(struct lwtunnel_state *lwt) { dst_cache_destroy(&ila_lwt_lwtunnel(lwt)->dst_cache); } static int ila_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ila_params *p = ila_params_lwtunnel(lwtstate); struct ila_lwt *ilwt = ila_lwt_lwtunnel(lwtstate); if (nla_put_u64_64bit(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator.v64, ILA_ATTR_PAD)) goto nla_put_failure; if (nla_put_u8(skb, ILA_ATTR_CSUM_MODE, (__force u8)p->csum_mode)) goto nla_put_failure; if (nla_put_u8(skb, ILA_ATTR_IDENT_TYPE, (__force u8)p->ident_type)) goto nla_put_failure; if (nla_put_u8(skb, ILA_ATTR_HOOK_TYPE, ilwt->lwt_output ? ILA_HOOK_ROUTE_OUTPUT : ILA_HOOK_ROUTE_INPUT)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(sizeof(u64)) + /* ILA_ATTR_LOCATOR */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_CSUM_MODE */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_IDENT_TYPE */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_HOOK_TYPE */ 0; } static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { struct ila_params *a_p = ila_params_lwtunnel(a); struct ila_params *b_p = ila_params_lwtunnel(b); return (a_p->locator.v64 != b_p->locator.v64); } static const struct lwtunnel_encap_ops ila_encap_ops = { .build_state = ila_build_state, .destroy_state = ila_destroy_state, .output = ila_output, .input = ila_input, .fill_encap = ila_fill_encap_info, .get_encap_size = ila_encap_nlsize, .cmp_encap = ila_encap_cmp, .owner = THIS_MODULE, }; int ila_lwt_init(void) { return lwtunnel_encap_add_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } void ila_lwt_fini(void) { lwtunnel_encap_del_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } |
| 1557 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * Flags to use when allocating a user page table page. */ extern gfp_t __userpte_alloc_gfp; #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 * in a pointer to swap between the two 4k halves. */ #define PGD_ALLOCATION_ORDER 1 #else #define PGD_ALLOCATION_ORDER 0 #endif /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; return (p4d_t *)get_zeroed_page(gfp); } static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); free_page((unsigned long)p4d); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SOCK_REUSEPORT_H #define _SOCK_REUSEPORT_H #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/spinlock.h> #include <net/sock.h> extern spinlock_t reuseport_lock; struct sock_reuseport { struct rcu_head rcu; u16 max_socks; /* length of socks */ u16 num_socks; /* elements in socks */ u16 num_closed_socks; /* closed elements in socks */ u16 incoming_cpu; /* The last synq overflow event timestamp of this * reuse->socks[] group. */ unsigned int synq_overflow_ts; /* ID stays the same even after the size of socks[] grows. */ unsigned int reuseport_id; unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[]; /* array of sock pointers */ }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); void reuseport_stop_listen_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (reuse && reuse->has_conns) ret = true; rcu_read_unlock(); return ret; } void reuseport_has_conns_set(struct sock *sk); void reuseport_update_incoming_cpu(struct sock *sk, int val); #endif /* _SOCK_REUSEPORT_H */ |
| 5 2 2 5 5 2 2 2 2 2 2 12 1 10 1 1 7 6 6 6 6 6 5 5 1 2 1 1 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 | // SPDX-License-Identifier: GPL-2.0-or-later /* L2TPv3 IP encapsulation support * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/ioctls.h> #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/socket.h> #include <linux/l2tp.h> #include <linux/in.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> #include "l2tp_core.h" struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; u32 conn_id; u32 peer_conn_id; }; static DEFINE_RWLOCK(l2tp_ip_lock); static struct hlist_head l2tp_ip_table; static struct hlist_head l2tp_ip_bind_table; static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { struct sock *sk; sk_for_each_bound(sk, &l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); int bound_dev_if; if (!net_eq(sock_net(sk), net)) continue; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && dif && bound_dev_if != dif) continue; if (inet->inet_rcv_saddr && laddr && inet->inet_rcv_saddr != laddr) continue; if (inet->inet_daddr && raddr && inet->inet_daddr != raddr) continue; if (l2tp->conn_id != tunnel_id) continue; goto found; } sk = NULL; found: return sk; } /* When processing receive frames, there are two cases to * consider. Data frames consist of a non-zero session-id and an * optional cookie. Control frames consist of a regular L2TP header * preceded by 32-bits of zeros. * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Control Message Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | (32 bits of zeros) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Control Connection ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns | Nr | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * All control frames are passed to userspace. */ static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; if (!pskb_may_pull(skb, 4)) goto discard; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; session_id = ntohl(*((__be32 *)ptr)); ptr += 4; /* RFC3931: L2TP/IP packets have the first 4 bytes containing * the session_id. If it is 0, the packet is a L2TP control * frame and the session_id value can be discarded. */ if (session_id == 0) { __skb_pull(skb, 4); goto pass_up; } /* Ok, this is a data packet. Lookup the session. */ session = l2tp_session_get(net, session_id); if (!session) goto discard; tunnel = session->tunnel; if (!tunnel) goto discard_sess; if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; pass_up: /* Get the tunnel_id from the L2TP header */ if (!pskb_may_pull(skb, 12)) goto discard; if ((skb->data[0] & 0xc0) != 0xc0) goto discard; tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { read_unlock_bh(&l2tp_ip_lock); goto discard; } sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); discard_sess: l2tp_session_dec_refcount(session); goto discard; discard_put: sock_put(sk); discard: kfree_skb(skb); return 0; } static int l2tp_ip_hash(struct sock *sk) { if (sk_unhashed(sk)) { write_lock_bh(&l2tp_ip_lock); sk_add_node(sk, &l2tp_ip_table); write_unlock_bh(&l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { if (sk_unhashed(sk)) return; write_lock_bh(&l2tp_ip_lock); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) { /* Prevent autobind. We don't have ports. */ inet_sk(sk)->inet_num = IPPROTO_L2TP; l2tp_ip_hash(sk); return 0; } static void l2tp_ip_close(struct sock *sk, long timeout) { write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); if (tunnel) l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); int ret; int chk_addr_ret; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) return -EINVAL; lock_sock(sk); ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (sk->sk_state != TCP_CLOSE) goto out; chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; if (addr->l2tp_addr.s_addr) { inet->inet_rcv_saddr = addr->l2tp_addr.s_addr; inet->inet_saddr = addr->l2tp_addr.s_addr; } if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ write_lock_bh(&l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { write_unlock_bh(&l2tp_ip_lock); ret = -EADDRINUSE; goto out; } sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; int rc; if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; lock_sock(sk); /* Must bind first - autobinding does not work */ if (sock_flag(sk, SOCK_ZAPPED)) { rc = -EINVAL; goto out_sk; } rc = __ip4_datagram_connect(sk, uaddr, addr_len); if (rc < 0) goto out_sk; l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); out_sk: release_sock(sk); return rc; } static int l2tp_ip_disconnect(struct sock *sk, int flags) { if (sock_flag(sk, SOCK_ZAPPED)) return 0; return __udp_disconnect(sk, flags); } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk); struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; memset(lsa, 0, sizeof(*lsa)); lsa->l2tp_family = AF_INET; if (peer) { if (!inet->inet_dport) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; lsa->l2tp_addr.s_addr = inet->inet_daddr; } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) goto drop; return 0; drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct sk_buff *skb; int rc; struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; struct flowi4 *fl4; int connected = 0; __be32 daddr; lock_sock(sk); rc = -ENOTCONN; if (sock_flag(sk, SOCK_DEAD)) goto out; /* Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name); rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) goto out; if (lip->l2tp_family != AF_INET) { rc = -EAFNOSUPPORT; if (lip->l2tp_family != AF_UNSPEC) goto out; } daddr = lip->l2tp_addr.s_addr; } else { rc = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; daddr = inet->inet_daddr; connected = 1; } /* Allocate a socket buffer */ rc = -ENOMEM; skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) + 4 + len, 0, GFP_KERNEL); if (!skb) goto error; /* Reserve space for headers, putting IP header on 4-byte boundary. */ skb_reserve(skb, 2 + NET_SKB_PAD); skb_reset_network_header(skb); skb_reserve(skb, sizeof(struct iphdr)); skb_reset_transport_header(skb); /* Insert 0 session_id */ *((__be32 *)skb_put(skb, 4)) = 0; /* Copy user data into skb */ rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc < 0) { kfree_skb(skb); goto error; } fl4 = &inet->cork.fl.u.ip4; if (connected) rt = (struct rtable *)__sk_dst_check(sk, 0); rcu_read_lock(); if (!rt) { const struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference(inet->inet_opt); /* Use correct destination address if we have options. */ if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; if (connected) { sk_setup_caps(sk, &rt->dst); } else { skb_dst_set(skb, &rt->dst); goto xmit; } } /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(sk, skb, &inet->cork.fl); rcu_read_unlock(); error: if (rc >= 0) rc = len; out: release_sock(sk); return rc; no_route: rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); rc = -EHOSTUNREACH; goto out; } static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) goto out; skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: return err ? err : copied; } int l2tp_ioctl(struct sock *sk, int cmd, int *karg) { struct sk_buff *skb; switch (cmd) { case SIOCOUTQ: *karg = sk_wmem_alloc_get(sk); break; case SIOCINQ: spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); *karg = skb ? skb->len : 0; spin_unlock_bh(&sk->sk_receive_queue.lock); break; default: return -ENOIOCTLCMD; } return 0; } EXPORT_SYMBOL_GPL(l2tp_ioctl); static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, .init = l2tp_ip_open, .close = l2tp_ip_close, .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, .hash = l2tp_ip_hash, .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), }; static const struct proto_ops l2tp_ip_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = l2tp_ip_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, }; static struct inet_protosw l2tp_ip_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_L2TP, .prot = &l2tp_ip_prot, .ops = &l2tp_ip_ops, }; static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); err = proto_register(&l2tp_ip_prot, 1); if (err != 0) goto out; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) goto out1; inet_register_protosw(&l2tp_ip_protosw); return 0; out1: proto_unregister(&l2tp_ip_prot); out: return err; } static void __exit l2tp_ip_exit(void) { inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); } module_init(l2tp_ip_init); module_exit(l2tp_ip_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); /* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, * because __stringify doesn't like enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 115, 2); MODULE_ALIAS_NET_PF_PROTO(PF_INET, 115); |
| 22341 15262 10126 893 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> #define JUMP_TABLE_ENTRY \ ".pushsection __jump_table, \"aw\" \n\t" \ _ASM_ALIGN "\n\t" \ ".long 1b - . \n\t" \ ".long %l[l_yes] - . \n\t" \ _ASM_PTR "%c0 + %c1 - .\n\t" \ ".popsection \n\t" #ifdef CONFIG_HAVE_JUMP_LABEL_HACK static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); return false; l_yes: return true; } #else /* !CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm_volatile_goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #endif /* CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { asm_volatile_goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } extern int arch_jump_entry_size(struct jump_entry *entry); #endif /* __ASSEMBLY__ */ #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock LSM - Ruleset management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #ifndef _SECURITY_LANDLOCK_RULESET_H #define _SECURITY_LANDLOCK_RULESET_H #include <linux/bitops.h> #include <linux/build_bug.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <uapi/linux/landlock.h> #include "limits.h" #include "object.h" /* * All access rights that are denied by default whether they are handled or not * by a ruleset/layer. This must be ORed with all ruleset->access_masks[] * entries when we need to get the absolute handled access masks. */ /* clang-format off */ #define LANDLOCK_ACCESS_FS_INITIALLY_DENIED ( \ LANDLOCK_ACCESS_FS_REFER) /* clang-format on */ typedef u16 access_mask_t; /* Makes sure all filesystem access rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); /* Makes sure all network access rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET); /* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); /* Ruleset access masks. */ typedef u32 access_masks_t; /* Makes sure all ruleset access rights can be stored. */ static_assert(BITS_PER_TYPE(access_masks_t) >= LANDLOCK_NUM_ACCESS_FS + LANDLOCK_NUM_ACCESS_NET); typedef u16 layer_mask_t; /* Makes sure all layers can be checked. */ static_assert(BITS_PER_TYPE(layer_mask_t) >= LANDLOCK_MAX_NUM_LAYERS); /** * struct landlock_layer - Access rights for a given layer */ struct landlock_layer { /** * @level: Position of this layer in the layer stack. */ u16 level; /** * @access: Bitfield of allowed actions on the kernel object. They are * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ). */ access_mask_t access; }; /** * union landlock_key - Key of a ruleset's red-black tree */ union landlock_key { /** * @object: Pointer to identify a kernel object (e.g. an inode). */ struct landlock_object *object; /** * @data: Raw data to identify an arbitrary 32-bit value * (e.g. a TCP port). */ uintptr_t data; }; /** * enum landlock_key_type - Type of &union landlock_key */ enum landlock_key_type { /** * @LANDLOCK_KEY_INODE: Type of &landlock_ruleset.root_inode's node * keys. */ LANDLOCK_KEY_INODE = 1, /** * @LANDLOCK_KEY_NET_PORT: Type of &landlock_ruleset.root_net_port's * node keys. */ LANDLOCK_KEY_NET_PORT, }; /** * struct landlock_id - Unique rule identifier for a ruleset */ struct landlock_id { /** * @key: Identifies either a kernel object (e.g. an inode) or * a raw value (e.g. a TCP port). */ union landlock_key key; /** * @type: Type of a landlock_ruleset's root tree. */ const enum landlock_key_type type; }; /** * struct landlock_rule - Access rights tied to an object */ struct landlock_rule { /** * @node: Node in the ruleset's red-black tree. */ struct rb_node node; /** * @key: A union to identify either a kernel object (e.g. an inode) or * a raw data value (e.g. a network socket port). This is used as a key * for this ruleset element. The pointer is set once and never * modified. It always points to an allocated object because each rule * increments the refcount of its object. */ union landlock_key key; /** * @num_layers: Number of entries in @layers. */ u32 num_layers; /** * @layers: Stack of layers, from the latest to the newest, implemented * as a flexible array member (FAM). */ struct landlock_layer layers[] __counted_by(num_layers); }; /** * struct landlock_hierarchy - Node in a ruleset hierarchy */ struct landlock_hierarchy { /** * @parent: Pointer to the parent node, or NULL if it is a root * Landlock domain. */ struct landlock_hierarchy *parent; /** * @usage: Number of potential children domains plus their parent * domain. */ refcount_t usage; }; /** * struct landlock_ruleset - Landlock ruleset * * This data structure must contain unique entries, be updatable, and quick to * match an object. */ struct landlock_ruleset { /** * @root_inode: Root of a red-black tree containing &struct * landlock_rule nodes with inode object. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_inode; #if IS_ENABLED(CONFIG_INET) /** * @root_net_port: Root of a red-black tree containing &struct * landlock_rule nodes with network port. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_net_port; #endif /* IS_ENABLED(CONFIG_INET) */ /** * @hierarchy: Enables hierarchy identification even when a parent * domain vanishes. This is needed for the ptrace protection. */ struct landlock_hierarchy *hierarchy; union { /** * @work_free: Enables to free a ruleset within a lockless * section. This is only used by * landlock_put_ruleset_deferred() when @usage reaches zero. * The fields @lock, @usage, @num_rules, @num_layers and * @access_masks are then unused. */ struct work_struct work_free; struct { /** * @lock: Protects against concurrent modifications of * @root, if @usage is greater than zero. */ struct mutex lock; /** * @usage: Number of processes (i.e. domains) or file * descriptors referencing this ruleset. */ refcount_t usage; /** * @num_rules: Number of non-overlapping (i.e. not for * the same object) rules in this ruleset. */ u32 num_rules; /** * @num_layers: Number of layers that are used in this * ruleset. This enables to check that all the layers * allow an access request. A value of 0 identifies a * non-merged ruleset (i.e. not a domain). */ u32 num_layers; /** * @access_masks: Contains the subset of filesystem and * network actions that are restricted by a ruleset. * A domain saves all layers of merged rulesets in a * stack (FAM), starting from the first layer to the * last one. These layers are used when merging * rulesets, for user space backward compatibility * (i.e. future-proof), and to properly handle merged * rulesets without overlapping access rights. These * layers are set once and never changed for the * lifetime of the ruleset. */ access_masks_t access_masks[]; }; }; }; struct landlock_ruleset * landlock_create_ruleset(const access_mask_t access_mask_fs, const access_mask_t access_mask_net); void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access); struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset); const struct landlock_rule * landlock_find_rule(const struct landlock_ruleset *const ruleset, const struct landlock_id id); static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset) { if (ruleset) refcount_inc(&ruleset->usage); } static inline void landlock_add_fs_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t fs_access_mask, const u16 layer_level) { access_mask_t fs_mask = fs_access_mask & LANDLOCK_MASK_ACCESS_FS; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(fs_access_mask != fs_mask); ruleset->access_masks[layer_level] |= (fs_mask << LANDLOCK_SHIFT_ACCESS_FS); } static inline void landlock_add_net_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t net_access_mask, const u16 layer_level) { access_mask_t net_mask = net_access_mask & LANDLOCK_MASK_ACCESS_NET; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(net_access_mask != net_mask); ruleset->access_masks[layer_level] |= (net_mask << LANDLOCK_SHIFT_ACCESS_NET); } static inline access_mask_t landlock_get_raw_fs_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return (ruleset->access_masks[layer_level] >> LANDLOCK_SHIFT_ACCESS_FS) & LANDLOCK_MASK_ACCESS_FS; } static inline access_mask_t landlock_get_fs_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { /* Handles all initially denied by default access rights. */ return landlock_get_raw_fs_access_mask(ruleset, layer_level) | LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } static inline access_mask_t landlock_get_net_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return (ruleset->access_masks[layer_level] >> LANDLOCK_SHIFT_ACCESS_NET) & LANDLOCK_MASK_ACCESS_NET; } bool landlock_unmask_layers(const struct landlock_rule *const rule, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const size_t masks_array_size); access_mask_t landlock_init_layer_masks(const struct landlock_ruleset *const domain, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const enum landlock_key_type key_type); #endif /* _SECURITY_LANDLOCK_RULESET_H */ |
| 4 74 74 66 1 6 71 74 9 73 9 71 35 35 22 22 22 4 4 16 22 120 120 117 120 63 63 63 12 49 7 7 7 7 63 63 63 63 63 63 1 1 22 1 22 22 1 1 8 8 8 114 114 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ #include "translation-table.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/build_bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/crc32c.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> #include <net/genetlink.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "originator.h" #include "soft-interface.h" #include "tvlv.h" static struct kmem_cache *batadv_tl_cache __read_mostly; static struct kmem_cache *batadv_tg_cache __read_mostly; static struct kmem_cache *batadv_tt_orig_cache __read_mostly; static struct kmem_cache *batadv_tt_change_cache __read_mostly; static struct kmem_cache *batadv_tt_req_cache __read_mostly; static struct kmem_cache *batadv_tt_roam_cache __read_mostly; /* hash class keys */ static struct lock_class_key batadv_tt_local_hash_lock_class_key; static struct lock_class_key batadv_tt_global_hash_lock_class_key; static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, unsigned short vid, struct batadv_orig_node *orig_node); static void batadv_tt_purge(struct work_struct *work); static void batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry); static void batadv_tt_global_del(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, unsigned short vid, const char *message, bool roaming); /** * batadv_compare_tt() - check if two TT entries are the same * @node: the list element pointer of the first TT entry * @data2: pointer to the tt_common_entry of the second TT entry * * Compare the MAC address and the VLAN ID of the two TT entries and check if * they are the same TT client. * Return: true if the two TT clients are the same, false otherwise */ static bool batadv_compare_tt(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_tt_common_entry, hash_entry); const struct batadv_tt_common_entry *tt1 = data1; const struct batadv_tt_common_entry *tt2 = data2; return (tt1->vid == tt2->vid) && batadv_compare_eth(data1, data2); } /** * batadv_choose_tt() - return the index of the tt entry in the hash table * @data: pointer to the tt_common_entry object to map * @size: the size of the hash table * * Return: the hash index where the object represented by 'data' should be * stored at. */ static inline u32 batadv_choose_tt(const void *data, u32 size) { const struct batadv_tt_common_entry *tt; u32 hash = 0; tt = data; hash = jhash(&tt->addr, ETH_ALEN, hash); hash = jhash(&tt->vid, sizeof(tt->vid), hash); return hash % size; } /** * batadv_tt_hash_find() - look for a client in the given hash table * @hash: the hash table to search * @addr: the mac address of the client to look for * @vid: VLAN identifier * * Return: a pointer to the tt_common struct belonging to the searched client if * found, NULL otherwise. */ static struct batadv_tt_common_entry * batadv_tt_hash_find(struct batadv_hashtable *hash, const u8 *addr, unsigned short vid) { struct hlist_head *head; struct batadv_tt_common_entry to_search, *tt, *tt_tmp = NULL; u32 index; if (!hash) return NULL; ether_addr_copy(to_search.addr, addr); to_search.vid = vid; index = batadv_choose_tt(&to_search, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(tt, head, hash_entry) { if (!batadv_compare_eth(tt, addr)) continue; if (tt->vid != vid) continue; if (!kref_get_unless_zero(&tt->refcount)) continue; tt_tmp = tt; break; } rcu_read_unlock(); return tt_tmp; } /** * batadv_tt_local_hash_find() - search the local table for a given client * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to look for * @vid: VLAN identifier * * Return: a pointer to the corresponding tt_local_entry struct if the client is * found, NULL otherwise. */ static struct batadv_tt_local_entry * batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local_entry = NULL; tt_common_entry = batadv_tt_hash_find(bat_priv->tt.local_hash, addr, vid); if (tt_common_entry) tt_local_entry = container_of(tt_common_entry, struct batadv_tt_local_entry, common); return tt_local_entry; } /** * batadv_tt_global_hash_find() - search the global table for a given client * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to look for * @vid: VLAN identifier * * Return: a pointer to the corresponding tt_global_entry struct if the client * is found, NULL otherwise. */ struct batadv_tt_global_entry * batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global_entry = NULL; tt_common_entry = batadv_tt_hash_find(bat_priv->tt.global_hash, addr, vid); if (tt_common_entry) tt_global_entry = container_of(tt_common_entry, struct batadv_tt_global_entry, common); return tt_global_entry; } /** * batadv_tt_local_entry_free_rcu() - free the tt_local_entry * @rcu: rcu pointer of the tt_local_entry */ static void batadv_tt_local_entry_free_rcu(struct rcu_head *rcu) { struct batadv_tt_local_entry *tt_local_entry; tt_local_entry = container_of(rcu, struct batadv_tt_local_entry, common.rcu); kmem_cache_free(batadv_tl_cache, tt_local_entry); } /** * batadv_tt_local_entry_release() - release tt_local_entry from lists and queue * for free after rcu grace period * @ref: kref pointer of the nc_node */ static void batadv_tt_local_entry_release(struct kref *ref) { struct batadv_tt_local_entry *tt_local_entry; tt_local_entry = container_of(ref, struct batadv_tt_local_entry, common.refcount); batadv_softif_vlan_put(tt_local_entry->vlan); call_rcu(&tt_local_entry->common.rcu, batadv_tt_local_entry_free_rcu); } /** * batadv_tt_local_entry_put() - decrement the tt_local_entry refcounter and * possibly release it * @tt_local_entry: tt_local_entry to be free'd */ static void batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry) { if (!tt_local_entry) return; kref_put(&tt_local_entry->common.refcount, batadv_tt_local_entry_release); } /** * batadv_tt_global_entry_free_rcu() - free the tt_global_entry * @rcu: rcu pointer of the tt_global_entry */ static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) { struct batadv_tt_global_entry *tt_global_entry; tt_global_entry = container_of(rcu, struct batadv_tt_global_entry, common.rcu); kmem_cache_free(batadv_tg_cache, tt_global_entry); } /** * batadv_tt_global_entry_release() - release tt_global_entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the nc_node */ void batadv_tt_global_entry_release(struct kref *ref) { struct batadv_tt_global_entry *tt_global_entry; tt_global_entry = container_of(ref, struct batadv_tt_global_entry, common.refcount); batadv_tt_global_del_orig_list(tt_global_entry); call_rcu(&tt_global_entry->common.rcu, batadv_tt_global_entry_free_rcu); } /** * batadv_tt_global_hash_count() - count the number of orig entries * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to count entries for * @vid: VLAN identifier * * Return: the number of originators advertising the given address/data * (excluding our self). */ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt_global_entry; int count; tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global_entry) return 0; count = atomic_read(&tt_global_entry->orig_list_count); batadv_tt_global_entry_put(tt_global_entry); return count; } /** * batadv_tt_local_size_mod() - change the size by v of the local table * identified by vid * @bat_priv: the bat priv with all the soft interface information * @vid: the VLAN identifier of the sub-table to change * @v: the amount to sum to the local table size */ static void batadv_tt_local_size_mod(struct batadv_priv *bat_priv, unsigned short vid, int v) { struct batadv_softif_vlan *vlan; vlan = batadv_softif_vlan_get(bat_priv, vid); if (!vlan) return; atomic_add(v, &vlan->tt.num_entries); batadv_softif_vlan_put(vlan); } /** * batadv_tt_local_size_inc() - increase by one the local table size for the * given vid * @bat_priv: the bat priv with all the soft interface information * @vid: the VLAN identifier */ static void batadv_tt_local_size_inc(struct batadv_priv *bat_priv, unsigned short vid) { batadv_tt_local_size_mod(bat_priv, vid, 1); } /** * batadv_tt_local_size_dec() - decrease by one the local table size for the * given vid * @bat_priv: the bat priv with all the soft interface information * @vid: the VLAN identifier */ static void batadv_tt_local_size_dec(struct batadv_priv *bat_priv, unsigned short vid) { batadv_tt_local_size_mod(bat_priv, vid, -1); } /** * batadv_tt_global_size_mod() - change the size by v of the global table * for orig_node identified by vid * @orig_node: the originator for which the table has to be modified * @vid: the VLAN identifier * @v: the amount to sum to the global table size */ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, unsigned short vid, int v) { struct batadv_orig_node_vlan *vlan; vlan = batadv_orig_node_vlan_new(orig_node, vid); if (!vlan) return; if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); if (!hlist_unhashed(&vlan->list)) { hlist_del_init_rcu(&vlan->list); batadv_orig_node_vlan_put(vlan); } spin_unlock_bh(&orig_node->vlan_list_lock); } batadv_orig_node_vlan_put(vlan); } /** * batadv_tt_global_size_inc() - increase by one the global table size for the * given vid * @orig_node: the originator which global table size has to be decreased * @vid: the vlan identifier */ static void batadv_tt_global_size_inc(struct batadv_orig_node *orig_node, unsigned short vid) { batadv_tt_global_size_mod(orig_node, vid, 1); } /** * batadv_tt_global_size_dec() - decrease by one the global table size for the * given vid * @orig_node: the originator which global table size has to be decreased * @vid: the vlan identifier */ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, unsigned short vid) { batadv_tt_global_size_mod(orig_node, vid, -1); } /** * batadv_tt_orig_list_entry_free_rcu() - free the orig_entry * @rcu: rcu pointer of the orig_entry */ static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) { struct batadv_tt_orig_list_entry *orig_entry; orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); kmem_cache_free(batadv_tt_orig_cache, orig_entry); } /** * batadv_tt_orig_list_entry_release() - release tt orig entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the tt orig entry */ static void batadv_tt_orig_list_entry_release(struct kref *ref) { struct batadv_tt_orig_list_entry *orig_entry; orig_entry = container_of(ref, struct batadv_tt_orig_list_entry, refcount); batadv_orig_node_put(orig_entry->orig_node); call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } /** * batadv_tt_orig_list_entry_put() - decrement the tt orig entry refcounter and * possibly release it * @orig_entry: tt orig entry to be free'd */ static void batadv_tt_orig_list_entry_put(struct batadv_tt_orig_list_entry *orig_entry) { if (!orig_entry) return; kref_put(&orig_entry->refcount, batadv_tt_orig_list_entry_release); } /** * batadv_tt_local_event() - store a local TT event (ADD/DEL) * @bat_priv: the bat priv with all the soft interface information * @tt_local_entry: the TT entry involved in the event * @event_flags: flags to store in the event structure */ static void batadv_tt_local_event(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, u8 event_flags) { struct batadv_tt_change_node *tt_change_node, *entry, *safe; struct batadv_tt_common_entry *common = &tt_local_entry->common; u8 flags = common->flags | event_flags; bool event_removed = false; bool del_op_requested, del_op_entry; tt_change_node = kmem_cache_alloc(batadv_tt_change_cache, GFP_ATOMIC); if (!tt_change_node) return; tt_change_node->change.flags = flags; memset(tt_change_node->change.reserved, 0, sizeof(tt_change_node->change.reserved)); ether_addr_copy(tt_change_node->change.addr, common->addr); tt_change_node->change.vid = htons(common->vid); del_op_requested = flags & BATADV_TT_CLIENT_DEL; /* check for ADD+DEL or DEL+ADD events */ spin_lock_bh(&bat_priv->tt.changes_list_lock); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { if (!batadv_compare_eth(entry->change.addr, common->addr)) continue; /* DEL+ADD in the same orig interval have no effect and can be * removed to avoid silly behaviour on the receiver side. The * other way around (ADD+DEL) can happen in case of roaming of * a client still in the NEW state. Roaming of NEW clients is * now possible due to automatically recognition of "temporary" * clients */ del_op_entry = entry->change.flags & BATADV_TT_CLIENT_DEL; if (!del_op_requested && del_op_entry) goto del; if (del_op_requested && !del_op_entry) goto del; /* this is a second add in the same originator interval. It * means that flags have been changed: update them! */ if (!del_op_requested && !del_op_entry) entry->change.flags = flags; continue; del: list_del(&entry->list); kmem_cache_free(batadv_tt_change_cache, entry); kmem_cache_free(batadv_tt_change_cache, tt_change_node); event_removed = true; goto unlock; } /* track the change in the OGMinterval list */ list_add_tail(&tt_change_node->list, &bat_priv->tt.changes_list); unlock: spin_unlock_bh(&bat_priv->tt.changes_list_lock); if (event_removed) atomic_dec(&bat_priv->tt.local_changes); else atomic_inc(&bat_priv->tt.local_changes); } /** * batadv_tt_len() - compute length in bytes of given number of tt changes * @changes_num: number of tt changes * * Return: computed length in bytes. */ static int batadv_tt_len(int changes_num) { return changes_num * sizeof(struct batadv_tvlv_tt_change); } /** * batadv_tt_entries() - compute the number of entries fitting in tt_len bytes * @tt_len: available space * * Return: the number of entries. */ static u16 batadv_tt_entries(u16 tt_len) { return tt_len / batadv_tt_len(1); } /** * batadv_tt_local_table_transmit_size() - calculates the local translation * table size when transmitted over the air * @bat_priv: the bat priv with all the soft interface information * * Return: local translation table size in bytes. */ static int batadv_tt_local_table_transmit_size(struct batadv_priv *bat_priv) { u16 num_vlan = 0; u16 tt_local_entries = 0; struct batadv_softif_vlan *vlan; int hdr_size; rcu_read_lock(); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { num_vlan++; tt_local_entries += atomic_read(&vlan->tt.num_entries); } rcu_read_unlock(); /* header size of tvlv encapsulated tt response payload */ hdr_size = sizeof(struct batadv_unicast_tvlv_packet); hdr_size += sizeof(struct batadv_tvlv_hdr); hdr_size += sizeof(struct batadv_tvlv_tt_data); hdr_size += num_vlan * sizeof(struct batadv_tvlv_tt_vlan_data); return hdr_size + batadv_tt_len(tt_local_entries); } static int batadv_tt_local_init(struct batadv_priv *bat_priv) { if (bat_priv->tt.local_hash) return 0; bat_priv->tt.local_hash = batadv_hash_new(1024); if (!bat_priv->tt.local_hash) return -ENOMEM; batadv_hash_set_lock_class(bat_priv->tt.local_hash, &batadv_tt_local_hash_lock_class_key); return 0; } static void batadv_tt_global_free(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global, const char *message) { struct batadv_tt_global_entry *tt_removed_entry; struct hlist_node *tt_removed_node; batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, batadv_print_vid(tt_global->common.vid), message); tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, batadv_choose_tt, &tt_global->common); if (!tt_removed_node) return; /* drop reference of remove hash entry */ tt_removed_entry = hlist_entry(tt_removed_node, struct batadv_tt_global_entry, common.hash_entry); batadv_tt_global_entry_put(tt_removed_entry); } /** * batadv_tt_local_add() - add a new client to the local table or update an * existing client * @soft_iface: netdev struct of the mesh interface * @addr: the mac address of the client to add * @vid: VLAN identifier * @ifindex: index of the interface where the client is connected to (useful to * identify wireless clients) * @mark: the value contained in the skb->mark field of the received packet (if * any) * * Return: true if the client was successfully added, false otherwise. */ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, unsigned short vid, int ifindex, u32 mark) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; struct batadv_tt_global_entry *tt_global = NULL; struct net *net = dev_net(soft_iface); struct batadv_softif_vlan *vlan; struct net_device *in_dev = NULL; struct batadv_hard_iface *in_hardif = NULL; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; int hash_added, table_size, packet_size_max; bool ret = false; bool roamed_back = false; u8 remote_flags; u32 match_mark; if (ifindex != BATADV_NULL_IFINDEX) in_dev = dev_get_by_index(net, ifindex); if (in_dev) in_hardif = batadv_hardif_get_by_netdev(in_dev); tt_local = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!is_multicast_ether_addr(addr)) tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); if (tt_local) { tt_local->last_seen = jiffies; if (tt_local->common.flags & BATADV_TT_CLIENT_PENDING) { batadv_dbg(BATADV_DBG_TT, bat_priv, "Re-adding pending client %pM (vid: %d)\n", addr, batadv_print_vid(vid)); /* whatever the reason why the PENDING flag was set, * this is a client which was enqueued to be removed in * this orig_interval. Since it popped up again, the * flag can be reset like it was never enqueued */ tt_local->common.flags &= ~BATADV_TT_CLIENT_PENDING; goto add_event; } if (tt_local->common.flags & BATADV_TT_CLIENT_ROAM) { batadv_dbg(BATADV_DBG_TT, bat_priv, "Roaming client %pM (vid: %d) came back to its original location\n", addr, batadv_print_vid(vid)); /* the ROAM flag is set because this client roamed away * and the node got a roaming_advertisement message. Now * that the client popped up again at its original * location such flag can be unset */ tt_local->common.flags &= ~BATADV_TT_CLIENT_ROAM; roamed_back = true; } goto check_roaming; } /* Ignore the client if we cannot send it in a full table response. */ table_size = batadv_tt_local_table_transmit_size(bat_priv); table_size += batadv_tt_len(1); packet_size_max = atomic_read(&bat_priv->packet_size_max); if (table_size > packet_size_max) { net_ratelimited_function(batadv_info, soft_iface, "Local translation table size (%i) exceeds maximum packet size (%i); Ignoring new local tt entry: %pM\n", table_size, packet_size_max, addr); goto out; } tt_local = kmem_cache_alloc(batadv_tl_cache, GFP_ATOMIC); if (!tt_local) goto out; /* increase the refcounter of the related vlan */ vlan = batadv_softif_vlan_get(bat_priv, vid); if (!vlan) { net_ratelimited_function(batadv_info, soft_iface, "adding TT local entry %pM to non-existent VLAN %d\n", addr, batadv_print_vid(vid)); kmem_cache_free(batadv_tl_cache, tt_local); tt_local = NULL; goto out; } batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n", addr, batadv_print_vid(vid), (u8)atomic_read(&bat_priv->tt.vn)); ether_addr_copy(tt_local->common.addr, addr); /* The local entry has to be marked as NEW to avoid to send it in * a full table response going out before the next ttvn increment * (consistency check) */ tt_local->common.flags = BATADV_TT_CLIENT_NEW; tt_local->common.vid = vid; if (batadv_is_wifi_hardif(in_hardif)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; kref_init(&tt_local->common.refcount); tt_local->last_seen = jiffies; tt_local->common.added_at = tt_local->last_seen; tt_local->vlan = vlan; /* the batman interface mac and multicast addresses should never be * purged */ if (batadv_compare_eth(addr, soft_iface->dev_addr) || is_multicast_ether_addr(addr)) tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; kref_get(&tt_local->common.refcount); hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local->common, &tt_local->common.hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_tt_local_entry_put(tt_local); goto out; } add_event: batadv_tt_local_event(bat_priv, tt_local, BATADV_NO_FLAGS); check_roaming: /* Check whether it is a roaming, but don't do anything if the roaming * process has already been handled */ if (tt_global && !(tt_global->common.flags & BATADV_TT_CLIENT_ROAM)) { /* These node are probably going to update their tt table */ head = &tt_global->orig_list; rcu_read_lock(); hlist_for_each_entry_rcu(orig_entry, head, list) { batadv_send_roam_adv(bat_priv, tt_global->common.addr, tt_global->common.vid, orig_entry->orig_node); } rcu_read_unlock(); if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose */ tt_global->common.flags |= BATADV_TT_CLIENT_ROAM; tt_global->roam_at = jiffies; } } /* store the current remote flags before altering them. This helps * understanding is flags are changing or not */ remote_flags = tt_local->common.flags & BATADV_TT_REMOTE_MASK; if (batadv_is_wifi_hardif(in_hardif)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; else tt_local->common.flags &= ~BATADV_TT_CLIENT_WIFI; /* check the mark in the skb: if it's equal to the configured * isolation_mark, it means the packet is coming from an isolated * non-mesh client */ match_mark = (mark & bat_priv->isolation_mark_mask); if (bat_priv->isolation_mark_mask && match_mark == bat_priv->isolation_mark) tt_local->common.flags |= BATADV_TT_CLIENT_ISOLA; else tt_local->common.flags &= ~BATADV_TT_CLIENT_ISOLA; /* if any "dynamic" flag has been modified, resend an ADD event for this * entry so that all the nodes can get the new flags */ if (remote_flags ^ (tt_local->common.flags & BATADV_TT_REMOTE_MASK)) batadv_tt_local_event(bat_priv, tt_local, BATADV_NO_FLAGS); ret = true; out: batadv_hardif_put(in_hardif); dev_put(in_dev); batadv_tt_local_entry_put(tt_local); batadv_tt_global_entry_put(tt_global); return ret; } /** * batadv_tt_prepare_tvlv_global_data() - prepare the TVLV TT header to send * within a TT Response directed to another node * @orig_node: originator for which the TT data has to be prepared * @tt_data: uninitialised pointer to the address of the TVLV buffer * @tt_change: uninitialised pointer to the address of the area where the TT * changed can be stored * @tt_len: pointer to the length to reserve to the tt_change. if -1 this * function reserves the amount of space needed to send the entire global TT * table. In case of success the value is updated with the real amount of * reserved bytes * Allocate the needed amount of memory for the entire TT TVLV and write its * header made up of one tvlv_tt_data object and a series of tvlv_tt_vlan_data * objects, one per active VLAN served by the originator node. * * Return: the size of the allocated buffer or 0 in case of failure. */ static u16 batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_data **tt_data, struct batadv_tvlv_tt_change **tt_change, s32 *tt_len) { u16 num_vlan = 0; u16 num_entries = 0; u16 change_offset; u16 tvlv_len; struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_orig_node_vlan *vlan; u8 *tt_change_ptr; spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); } change_offset = sizeof(**tt_data); change_offset += num_vlan * sizeof(*tt_vlan); /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) *tt_len = batadv_tt_len(num_entries); tvlv_len = *tt_len; tvlv_len += change_offset; *tt_data = kmalloc(tvlv_len, GFP_ATOMIC); if (!*tt_data) { *tt_len = 0; goto out; } (*tt_data)->flags = BATADV_NO_FLAGS; (*tt_data)->ttvn = atomic_read(&orig_node->last_ttvn); (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); tt_vlan->reserved = 0; tt_vlan++; } tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: spin_unlock_bh(&orig_node->vlan_list_lock); return tvlv_len; } /** * batadv_tt_prepare_tvlv_local_data() - allocate and prepare the TT TVLV for * this node * @bat_priv: the bat priv with all the soft interface information * @tt_data: uninitialised pointer to the address of the TVLV buffer * @tt_change: uninitialised pointer to the address of the area where the TT * changes can be stored * @tt_len: pointer to the length to reserve to the tt_change. if -1 this * function reserves the amount of space needed to send the entire local TT * table. In case of success the value is updated with the real amount of * reserved bytes * * Allocate the needed amount of memory for the entire TT TVLV and write its * header made up by one tvlv_tt_data object and a series of tvlv_tt_vlan_data * objects, one per active VLAN. * * Return: the size of the allocated buffer or 0 in case of failure. */ static u16 batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data **tt_data, struct batadv_tvlv_tt_change **tt_change, s32 *tt_len) { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_softif_vlan *vlan; u16 num_vlan = 0; u16 vlan_entries = 0; u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; int change_offset; spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) continue; num_vlan++; total_entries += vlan_entries; } change_offset = sizeof(**tt_data); change_offset += num_vlan * sizeof(*tt_vlan); /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) *tt_len = batadv_tt_len(total_entries); tvlv_len = *tt_len; tvlv_len += change_offset; *tt_data = kmalloc(tvlv_len, GFP_ATOMIC); if (!*tt_data) { tvlv_len = 0; goto out; } (*tt_data)->flags = BATADV_NO_FLAGS; (*tt_data)->ttvn = atomic_read(&bat_priv->tt.vn); (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) continue; tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); tt_vlan->reserved = 0; tt_vlan++; } tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return tvlv_len; } /** * batadv_tt_tvlv_container_update() - update the translation table tvlv * container after local tt changes have been committed * @bat_priv: the bat priv with all the soft interface information */ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) { struct batadv_tt_change_node *entry, *safe; struct batadv_tvlv_tt_data *tt_data; struct batadv_tvlv_tt_change *tt_change; int tt_diff_len, tt_change_len = 0; int tt_diff_entries_num = 0; int tt_diff_entries_count = 0; u16 tvlv_len; tt_diff_entries_num = atomic_read(&bat_priv->tt.local_changes); tt_diff_len = batadv_tt_len(tt_diff_entries_num); /* if we have too many changes for one packet don't send any * and wait for the tt table request which will be fragmented */ if (tt_diff_len > bat_priv->soft_iface->mtu) tt_diff_len = 0; tvlv_len = batadv_tt_prepare_tvlv_local_data(bat_priv, &tt_data, &tt_change, &tt_diff_len); if (!tvlv_len) return; tt_data->flags = BATADV_TT_OGM_DIFF; if (tt_diff_len == 0) goto container_register; spin_lock_bh(&bat_priv->tt.changes_list_lock); atomic_set(&bat_priv->tt.local_changes, 0); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { if (tt_diff_entries_count < tt_diff_entries_num) { memcpy(tt_change + tt_diff_entries_count, &entry->change, sizeof(struct batadv_tvlv_tt_change)); tt_diff_entries_count++; } list_del(&entry->list); kmem_cache_free(batadv_tt_change_cache, entry); } spin_unlock_bh(&bat_priv->tt.changes_list_lock); /* Keep the buffer for possible tt_request */ spin_lock_bh(&bat_priv->tt.last_changeset_lock); kfree(bat_priv->tt.last_changeset); bat_priv->tt.last_changeset_len = 0; bat_priv->tt.last_changeset = NULL; tt_change_len = batadv_tt_len(tt_diff_entries_count); /* check whether this new OGM has no changes due to size problems */ if (tt_diff_entries_count > 0) { /* if kmalloc() fails we will reply with the full table * instead of providing the diff */ bat_priv->tt.last_changeset = kzalloc(tt_diff_len, GFP_ATOMIC); if (bat_priv->tt.last_changeset) { memcpy(bat_priv->tt.last_changeset, tt_change, tt_change_len); bat_priv->tt.last_changeset_len = tt_diff_len; } } spin_unlock_bh(&bat_priv->tt.last_changeset_lock); container_register: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_TT, 1, tt_data, tvlv_len); kfree(tt_data); } /** * batadv_tt_local_dump_entry() - Dump one TT local entry into a message * @msg :Netlink message to dump into * @portid: Port making netlink request * @cb: Control block containing additional options * @bat_priv: The bat priv with all the soft interface information * @common: tt local & tt global common data * * Return: Error code, or 0 on success */ static int batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_priv *bat_priv, struct batadv_tt_common_entry *common) { void *hdr; struct batadv_softif_vlan *vlan; struct batadv_tt_local_entry *local; unsigned int last_seen_msecs; u32 crc; local = container_of(common, struct batadv_tt_local_entry, common); last_seen_msecs = jiffies_to_msecs(jiffies - local->last_seen); vlan = batadv_softif_vlan_get(bat_priv, common->vid); if (!vlan) return 0; crc = vlan->tt.crc; batadv_softif_vlan_put(vlan); hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_TRANSTABLE_LOCAL); if (!hdr) return -ENOBUFS; genl_dump_check_consistent(cb, hdr); if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) goto nla_put_failure; if (!(common->flags & BATADV_TT_CLIENT_NOPURGE) && nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, last_seen_msecs)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_tt_local_dump_bucket() - Dump one TT local bucket into a message * @msg: Netlink message to dump into * @portid: Port making netlink request * @cb: Control block containing additional options * @bat_priv: The bat priv with all the soft interface information * @hash: hash to dump * @bucket: bucket index to dump * @idx_s: Number of entries to skip * * Return: Error code, or 0 on success */ static int batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_priv *bat_priv, struct batadv_hashtable *hash, unsigned int bucket, int *idx_s) { struct batadv_tt_common_entry *common; int idx = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(common, &hash->table[bucket], hash_entry) { if (idx++ < *idx_s) continue; if (batadv_tt_local_dump_entry(msg, portid, cb, bat_priv, common)) { spin_unlock_bh(&hash->list_locks[bucket]); *idx_s = idx - 1; return -EMSGSIZE; } } spin_unlock_bh(&hash->list_locks[bucket]); *idx_s = 0; return 0; } /** * batadv_tt_local_dump() - Dump TT local entries into a message * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: Error code, or 0 on success */ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_hashtable *hash; int ret; int ifindex; int bucket = cb->args[0]; int idx = cb->args[1]; int portid = NETLINK_CB(cb->skb).portid; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } hash = bat_priv->tt.local_hash; while (bucket < hash->size) { if (batadv_tt_local_dump_bucket(msg, portid, cb, bat_priv, hash, bucket, &idx)) break; bucket++; } ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); cb->args[0] = bucket; cb->args[1] = idx; return ret; } static void batadv_tt_local_set_pending(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, u16 flags, const char *message) { batadv_tt_local_event(bat_priv, tt_local_entry, flags); /* The local client has to be marked as "pending to be removed" but has * to be kept in the table in order to send it in a full table * response issued before the net ttvn increment (consistency check) */ tt_local_entry->common.flags |= BATADV_TT_CLIENT_PENDING; batadv_dbg(BATADV_DBG_TT, bat_priv, "Local tt entry (%pM, vid: %d) pending to be removed: %s\n", tt_local_entry->common.addr, batadv_print_vid(tt_local_entry->common.vid), message); } /** * batadv_tt_local_remove() - logically remove an entry from the local table * @bat_priv: the bat priv with all the soft interface information * @addr: the MAC address of the client to remove * @vid: VLAN identifier * @message: message to append to the log on deletion * @roaming: true if the deletion is due to a roaming event * * Return: the flags assigned to the local entry before being deleted */ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid, const char *message, bool roaming) { struct batadv_tt_local_entry *tt_removed_entry; struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; struct hlist_node *tt_removed_node; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) goto out; curr_flags = tt_local_entry->common.flags; flags = BATADV_TT_CLIENT_DEL; /* if this global entry addition is due to a roaming, the node has to * mark the local entry as "roamed" in order to correctly reroute * packets later */ if (roaming) { flags |= BATADV_TT_CLIENT_ROAM; /* mark the local client as ROAMed */ tt_local_entry->common.flags |= BATADV_TT_CLIENT_ROAM; } if (!(tt_local_entry->common.flags & BATADV_TT_CLIENT_NEW)) { batadv_tt_local_set_pending(bat_priv, tt_local_entry, flags, message); goto out; } /* if this client has been added right now, it is possible to * immediately purge it */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local_entry->common); if (!tt_removed_node) goto out; /* drop reference of remove hash entry */ tt_removed_entry = hlist_entry(tt_removed_node, struct batadv_tt_local_entry, common.hash_entry); batadv_tt_local_entry_put(tt_removed_entry); out: batadv_tt_local_entry_put(tt_local_entry); return curr_flags; } /** * batadv_tt_local_purge_list() - purge inactive tt local entries * @bat_priv: the bat priv with all the soft interface information * @head: pointer to the list containing the local tt entries * @timeout: parameter deciding whether a given tt local entry is considered * inactive or not */ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, struct hlist_head *head, int timeout) { struct batadv_tt_local_entry *tt_local_entry; struct batadv_tt_common_entry *tt_common_entry; struct hlist_node *node_tmp; hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { tt_local_entry = container_of(tt_common_entry, struct batadv_tt_local_entry, common); if (tt_local_entry->common.flags & BATADV_TT_CLIENT_NOPURGE) continue; /* entry already marked for deletion */ if (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) continue; if (!batadv_has_timed_out(tt_local_entry->last_seen, timeout)) continue; batadv_tt_local_set_pending(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL, "timed out"); } } /** * batadv_tt_local_purge() - purge inactive tt local entries * @bat_priv: the bat priv with all the soft interface information * @timeout: parameter deciding whether a given tt local entry is considered * inactive or not */ static void batadv_tt_local_purge(struct batadv_priv *bat_priv, int timeout) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); batadv_tt_local_purge_list(bat_priv, head, timeout); spin_unlock_bh(list_lock); } } static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; if (!bat_priv->tt.local_hash) return; hash = bat_priv->tt.local_hash; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { hlist_del_rcu(&tt_common_entry->hash_entry); tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, common); batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); } batadv_hash_destroy(hash); bat_priv->tt.local_hash = NULL; } static int batadv_tt_global_init(struct batadv_priv *bat_priv) { if (bat_priv->tt.global_hash) return 0; bat_priv->tt.global_hash = batadv_hash_new(1024); if (!bat_priv->tt.global_hash) return -ENOMEM; batadv_hash_set_lock_class(bat_priv->tt.global_hash, &batadv_tt_global_hash_lock_class_key); return 0; } static void batadv_tt_changes_list_free(struct batadv_priv *bat_priv) { struct batadv_tt_change_node *entry, *safe; spin_lock_bh(&bat_priv->tt.changes_list_lock); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { list_del(&entry->list); kmem_cache_free(batadv_tt_change_cache, entry); } atomic_set(&bat_priv->tt.local_changes, 0); spin_unlock_bh(&bat_priv->tt.changes_list_lock); } /** * batadv_tt_global_orig_entry_find() - find a TT orig_list_entry * @entry: the TT global entry where the orig_list_entry has to be * extracted from * @orig_node: the originator for which the orig_list_entry has to be found * * retrieve the orig_tt_list_entry belonging to orig_node from the * batadv_tt_global_entry list * * Return: it with an increased refcounter, NULL if not found */ static struct batadv_tt_orig_list_entry * batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, const struct batadv_orig_node *orig_node) { struct batadv_tt_orig_list_entry *tmp_orig_entry, *orig_entry = NULL; const struct hlist_head *head; rcu_read_lock(); head = &entry->orig_list; hlist_for_each_entry_rcu(tmp_orig_entry, head, list) { if (tmp_orig_entry->orig_node != orig_node) continue; if (!kref_get_unless_zero(&tmp_orig_entry->refcount)) continue; orig_entry = tmp_orig_entry; break; } rcu_read_unlock(); return orig_entry; } /** * batadv_tt_global_entry_has_orig() - check if a TT global entry is also * handled by a given originator * @entry: the TT global entry to check * @orig_node: the originator to search in the list * @flags: a pointer to store TT flags for the given @entry received * from @orig_node * * find out if an orig_node is already in the list of a tt_global_entry. * * Return: true if found, false otherwise */ static bool batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, const struct batadv_orig_node *orig_node, u8 *flags) { struct batadv_tt_orig_list_entry *orig_entry; bool found = false; orig_entry = batadv_tt_global_orig_entry_find(entry, orig_node); if (orig_entry) { found = true; if (flags) *flags = orig_entry->flags; batadv_tt_orig_list_entry_put(orig_entry); } return found; } /** * batadv_tt_global_sync_flags() - update TT sync flags * @tt_global: the TT global entry to update sync flags in * * Updates the sync flag bits in the tt_global flag attribute with a logical * OR of all sync flags from any of its TT orig entries. */ static void batadv_tt_global_sync_flags(struct batadv_tt_global_entry *tt_global) { struct batadv_tt_orig_list_entry *orig_entry; const struct hlist_head *head; u16 flags = BATADV_NO_FLAGS; rcu_read_lock(); head = &tt_global->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) flags |= orig_entry->flags; rcu_read_unlock(); flags |= tt_global->common.flags & (~BATADV_TT_SYNC_MASK); tt_global->common.flags = flags; } /** * batadv_tt_global_orig_entry_add() - add or update a TT orig entry * @tt_global: the TT global entry to add an orig entry in * @orig_node: the originator to add an orig entry for * @ttvn: translation table version number of this changeset * @flags: TT sync flags */ static void batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, struct batadv_orig_node *orig_node, int ttvn, u8 flags) { struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global->list_lock); orig_entry = batadv_tt_global_orig_entry_find(tt_global, orig_node); if (orig_entry) { /* refresh the ttvn: the current value could be a bogus one that * was added during a "temporary client detection" */ orig_entry->ttvn = ttvn; orig_entry->flags = flags; goto sync_flags; } orig_entry = kmem_cache_zalloc(batadv_tt_orig_cache, GFP_ATOMIC); if (!orig_entry) goto out; INIT_HLIST_NODE(&orig_entry->list); kref_get(&orig_node->refcount); batadv_tt_global_size_inc(orig_node, tt_global->common.vid); orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; orig_entry->flags = flags; kref_init(&orig_entry->refcount); kref_get(&orig_entry->refcount); hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); atomic_inc(&tt_global->orig_list_count); sync_flags: batadv_tt_global_sync_flags(tt_global); out: batadv_tt_orig_list_entry_put(orig_entry); spin_unlock_bh(&tt_global->list_lock); } /** * batadv_tt_global_add() - add a new TT global entry or update an existing one * @bat_priv: the bat priv with all the soft interface information * @orig_node: the originator announcing the client * @tt_addr: the mac address of the non-mesh client * @vid: VLAN identifier * @flags: TT flags that have to be set for this non-mesh client * @ttvn: the tt version number ever announcing this non-mesh client * * Add a new TT global entry for the given originator. If the entry already * exists add a new reference to the given originator (a global entry can have * references to multiple originators) and adjust the flags attribute to reflect * the function argument. * If a TT local entry exists for this non-mesh client remove it. * * The caller must hold the orig_node refcount. * * Return: true if the new entry has been added, false otherwise */ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *tt_addr, unsigned short vid, u16 flags, u8 ttvn) { struct batadv_tt_global_entry *tt_global_entry; struct batadv_tt_local_entry *tt_local_entry; bool ret = false; int hash_added; struct batadv_tt_common_entry *common; u16 local_flags; /* ignore global entries from backbone nodes */ if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) return true; tt_global_entry = batadv_tt_global_hash_find(bat_priv, tt_addr, vid); tt_local_entry = batadv_tt_local_hash_find(bat_priv, tt_addr, vid); /* if the node already has a local client for this entry, it has to wait * for a roaming advertisement instead of manually messing up the global * table */ if ((flags & BATADV_TT_CLIENT_TEMP) && tt_local_entry && !(tt_local_entry->common.flags & BATADV_TT_CLIENT_NEW)) goto out; if (!tt_global_entry) { tt_global_entry = kmem_cache_zalloc(batadv_tg_cache, GFP_ATOMIC); if (!tt_global_entry) goto out; common = &tt_global_entry->common; ether_addr_copy(common->addr, tt_addr); common->vid = vid; if (!is_multicast_ether_addr(common->addr)) common->flags = flags & (~BATADV_TT_SYNC_MASK); tt_global_entry->roam_at = 0; /* node must store current time in case of roaming. This is * needed to purge this entry out on timeout (if nobody claims * it) */ if (flags & BATADV_TT_CLIENT_ROAM) tt_global_entry->roam_at = jiffies; kref_init(&common->refcount); common->added_at = jiffies; INIT_HLIST_HEAD(&tt_global_entry->orig_list); atomic_set(&tt_global_entry->orig_list_count, 0); spin_lock_init(&tt_global_entry->list_lock); kref_get(&common->refcount); hash_added = batadv_hash_add(bat_priv->tt.global_hash, batadv_compare_tt, batadv_choose_tt, common, &common->hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_tt_global_entry_put(tt_global_entry); goto out_remove; } } else { common = &tt_global_entry->common; /* If there is already a global entry, we can use this one for * our processing. * But if we are trying to add a temporary client then here are * two options at this point: * 1) the global client is not a temporary client: the global * client has to be left as it is, temporary information * should never override any already known client state * 2) the global client is a temporary client: purge the * originator list and add the new one orig_entry */ if (flags & BATADV_TT_CLIENT_TEMP) { if (!(common->flags & BATADV_TT_CLIENT_TEMP)) goto out; if (batadv_tt_global_entry_has_orig(tt_global_entry, orig_node, NULL)) goto out_remove; batadv_tt_global_del_orig_list(tt_global_entry); goto add_orig_entry; } /* if the client was temporary added before receiving the first * OGM announcing it, we have to clear the TEMP flag. Also, * remove the previous temporary orig node and re-add it * if required. If the orig entry changed, the new one which * is a non-temporary entry is preferred. */ if (common->flags & BATADV_TT_CLIENT_TEMP) { batadv_tt_global_del_orig_list(tt_global_entry); common->flags &= ~BATADV_TT_CLIENT_TEMP; } /* the change can carry possible "attribute" flags like the * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ if (!is_multicast_ether_addr(common->addr)) common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a * delete + roaming change for this originator. * * We should first delete the old originator before adding the * new one. */ if (common->flags & BATADV_TT_CLIENT_ROAM) { batadv_tt_global_del_orig_list(tt_global_entry); common->flags &= ~BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = 0; } } add_orig_entry: /* add the new orig_entry (if needed) or update it */ batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn, flags & BATADV_TT_SYNC_MASK); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (vid: %d, via %pM)\n", common->addr, batadv_print_vid(common->vid), orig_node->orig); ret = true; out_remove: /* Do not remove multicast addresses from the local hash on * global additions */ if (is_multicast_ether_addr(tt_addr)) goto out; /* remove address from local hash if present */ local_flags = batadv_tt_local_remove(bat_priv, tt_addr, vid, "global tt received", flags & BATADV_TT_CLIENT_ROAM); tt_global_entry->common.flags |= local_flags & BATADV_TT_CLIENT_WIFI; if (!(flags & BATADV_TT_CLIENT_ROAM)) /* this is a normal global add. Therefore the client is not in a * roaming state anymore. */ tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_ROAM; out: batadv_tt_global_entry_put(tt_global_entry); batadv_tt_local_entry_put(tt_local_entry); return ret; } /** * batadv_transtable_best_orig() - Get best originator list entry from tt entry * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: global translation table entry to be analyzed * * This function assumes the caller holds rcu_read_lock(). * Return: best originator list entry or NULL on errors. */ static struct batadv_tt_orig_list_entry * batadv_transtable_best_orig(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global_entry) { struct batadv_neigh_node *router, *best_router = NULL; struct batadv_algo_ops *bao = bat_priv->algo_ops; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL; head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { router = batadv_orig_router_get(orig_entry->orig_node, BATADV_IF_DEFAULT); if (!router) continue; if (best_router && bao->neigh.cmp(router, BATADV_IF_DEFAULT, best_router, BATADV_IF_DEFAULT) <= 0) { batadv_neigh_node_put(router); continue; } /* release the refcount for the "old" best */ batadv_neigh_node_put(best_router); best_entry = orig_entry; best_router = router; } batadv_neigh_node_put(best_router); return best_entry; } /** * batadv_tt_global_dump_subentry() - Dump all TT local entries into a message * @msg: Netlink message to dump into * @portid: Port making netlink request * @seq: Sequence number of netlink message * @common: tt local & tt global common data * @orig: Originator node announcing a non-mesh client * @best: Is the best originator for the TT entry * * Return: Error code, or 0 on success */ static int batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_tt_common_entry *common, struct batadv_tt_orig_list_entry *orig, bool best) { u16 flags = (common->flags & (~BATADV_TT_SYNC_MASK)) | orig->flags; void *hdr; struct batadv_orig_node_vlan *vlan; u8 last_ttvn; u32 crc; vlan = batadv_orig_node_vlan_get(orig->orig_node, common->vid); if (!vlan) return 0; crc = vlan->tt.crc; batadv_orig_node_vlan_put(vlan); hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_TRANSTABLE_GLOBAL); if (!hdr) return -ENOBUFS; last_ttvn = atomic_read(&orig->orig_node->last_ttvn); if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig->orig_node->orig) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, orig->ttvn) || nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, flags)) goto nla_put_failure; if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_tt_global_dump_entry() - Dump one TT global entry into a message * @msg: Netlink message to dump into * @portid: Port making netlink request * @seq: Sequence number of netlink message * @bat_priv: The bat priv with all the soft interface information * @common: tt local & tt global common data * @sub_s: Number of entries to skip * * This function assumes the caller holds rcu_read_lock(). * * Return: Error code, or 0 on success */ static int batadv_tt_global_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_priv *bat_priv, struct batadv_tt_common_entry *common, int *sub_s) { struct batadv_tt_orig_list_entry *orig_entry, *best_entry; struct batadv_tt_global_entry *global; struct hlist_head *head; int sub = 0; bool best; global = container_of(common, struct batadv_tt_global_entry, common); best_entry = batadv_transtable_best_orig(bat_priv, global); head = &global->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { if (sub++ < *sub_s) continue; best = (orig_entry == best_entry); if (batadv_tt_global_dump_subentry(msg, portid, seq, common, orig_entry, best)) { *sub_s = sub - 1; return -EMSGSIZE; } } *sub_s = 0; return 0; } /** * batadv_tt_global_dump_bucket() - Dump one TT local bucket into a message * @msg: Netlink message to dump into * @portid: Port making netlink request * @seq: Sequence number of netlink message * @bat_priv: The bat priv with all the soft interface information * @head: Pointer to the list containing the global tt entries * @idx_s: Number of entries to skip * @sub: Number of entries to skip * * Return: Error code, or 0 on success */ static int batadv_tt_global_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_priv *bat_priv, struct hlist_head *head, int *idx_s, int *sub) { struct batadv_tt_common_entry *common; int idx = 0; rcu_read_lock(); hlist_for_each_entry_rcu(common, head, hash_entry) { if (idx++ < *idx_s) continue; if (batadv_tt_global_dump_entry(msg, portid, seq, bat_priv, common, sub)) { rcu_read_unlock(); *idx_s = idx - 1; return -EMSGSIZE; } } rcu_read_unlock(); *idx_s = 0; *sub = 0; return 0; } /** * batadv_tt_global_dump() - Dump TT global entries into a message * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: Error code, or length of message on success */ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_hashtable *hash; struct hlist_head *head; int ret; int ifindex; int bucket = cb->args[0]; int idx = cb->args[1]; int sub = cb->args[2]; int portid = NETLINK_CB(cb->skb).portid; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } hash = bat_priv->tt.global_hash; while (bucket < hash->size) { head = &hash->table[bucket]; if (batadv_tt_global_dump_bucket(msg, portid, cb->nlh->nlmsg_seq, bat_priv, head, &idx, &sub)) break; bucket++; } ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); cb->args[0] = bucket; cb->args[1] = idx; cb->args[2] = sub; return ret; } /** * _batadv_tt_global_del_orig_entry() - remove and free an orig_entry * @tt_global_entry: the global entry to remove the orig_entry from * @orig_entry: the orig entry to remove and free * * Remove an orig_entry from its list in the given tt_global_entry and * free this orig_entry afterwards. * * Caller must hold tt_global_entry->list_lock and ensure orig_entry->list is * part of a list. */ static void _batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry, struct batadv_tt_orig_list_entry *orig_entry) { lockdep_assert_held(&tt_global_entry->list_lock); batadv_tt_global_size_dec(orig_entry->orig_node, tt_global_entry->common.vid); atomic_dec(&tt_global_entry->orig_list_count); /* requires holding tt_global_entry->list_lock and orig_entry->list * being part of a list */ hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_put(orig_entry); } /* deletes the orig list of a tt_global_entry */ static void batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) { struct hlist_head *head; struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; hlist_for_each_entry_safe(orig_entry, safe, head, list) _batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry); spin_unlock_bh(&tt_global_entry->list_lock); } /** * batadv_tt_global_del_orig_node() - remove orig_node from a global tt entry * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: the global entry to remove the orig_node from * @orig_node: the originator announcing the client * @message: message to append to the log on deletion * * Remove the given orig_node and its according orig_entry from the given * global tt entry. */ static void batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global_entry, struct batadv_orig_node *orig_node, const char *message) { struct hlist_head *head; struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; unsigned short vid; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; hlist_for_each_entry_safe(orig_entry, safe, head, list) { if (orig_entry->orig_node == orig_node) { vid = tt_global_entry->common.vid; batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting %pM from global tt entry %pM (vid: %d): %s\n", orig_node->orig, tt_global_entry->common.addr, batadv_print_vid(vid), message); _batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry); } } spin_unlock_bh(&tt_global_entry->list_lock); } /* If the client is to be deleted, we check if it is the last origantor entry * within tt_global entry. If yes, we set the BATADV_TT_CLIENT_ROAM flag and the * timer, otherwise we simply remove the originator scheduled for deletion. */ static void batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global_entry, struct batadv_orig_node *orig_node, const char *message) { bool last_entry = true; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; /* no local entry exists, case 1: * Check if this is the last one or if other entries exist. */ rcu_read_lock(); head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { if (orig_entry->orig_node != orig_node) { last_entry = false; break; } } rcu_read_unlock(); if (last_entry) { /* its the last one, mark for roaming. */ tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = jiffies; } else { /* there is another entry, we can simply delete this * one and can still use the other one. */ batadv_tt_global_del_orig_node(bat_priv, tt_global_entry, orig_node, message); } } /** * batadv_tt_global_del() - remove a client from the global table * @bat_priv: the bat priv with all the soft interface information * @orig_node: an originator serving this client * @addr: the mac address of the client * @vid: VLAN identifier * @message: a message explaining the reason for deleting the client to print * for debugging purpose * @roaming: true if the deletion has been triggered by a roaming event */ static void batadv_tt_global_del(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, unsigned short vid, const char *message, bool roaming) { struct batadv_tt_global_entry *tt_global_entry; struct batadv_tt_local_entry *local_entry = NULL; tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global_entry) goto out; if (!roaming) { batadv_tt_global_del_orig_node(bat_priv, tt_global_entry, orig_node, message); if (hlist_empty(&tt_global_entry->orig_list)) batadv_tt_global_free(bat_priv, tt_global_entry, message); goto out; } /* if we are deleting a global entry due to a roam * event, there are two possibilities: * 1) the client roamed from node A to node B => if there * is only one originator left for this client, we mark * it with BATADV_TT_CLIENT_ROAM, we start a timer and we * wait for node B to claim it. In case of timeout * the entry is purged. * * If there are other originators left, we directly delete * the originator. * 2) the client roamed to us => we can directly delete * the global entry, since it is useless now. */ local_entry = batadv_tt_local_hash_find(bat_priv, tt_global_entry->common.addr, vid); if (local_entry) { /* local entry exists, case 2: client roamed to us. */ batadv_tt_global_del_orig_list(tt_global_entry); batadv_tt_global_free(bat_priv, tt_global_entry, message); } else { /* no local entry exists, case 1: check for roaming */ batadv_tt_global_del_roaming(bat_priv, tt_global_entry, orig_node, message); } out: batadv_tt_global_entry_put(tt_global_entry); batadv_tt_local_entry_put(local_entry); } /** * batadv_tt_global_del_orig() - remove all the TT global entries belonging to * the given originator matching the provided vid * @bat_priv: the bat priv with all the soft interface information * @orig_node: the originator owning the entries to remove * @match_vid: the VLAN identifier to match. If negative all the entries will be * removed * @message: debug message to print as "reason" */ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, s32 match_vid, const char *message) { struct batadv_tt_global_entry *tt_global; struct batadv_tt_common_entry *tt_common_entry; u32 i; struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct hlist_node *safe; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ unsigned short vid; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common_entry, safe, head, hash_entry) { /* remove only matching entries */ if (match_vid >= 0 && tt_common_entry->vid != match_vid) continue; tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, common); batadv_tt_global_del_orig_node(bat_priv, tt_global, orig_node, message); if (hlist_empty(&tt_global->orig_list)) { vid = tt_global->common.vid; batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, batadv_print_vid(vid), message); hlist_del_rcu(&tt_common_entry->hash_entry); batadv_tt_global_entry_put(tt_global); } } spin_unlock_bh(list_lock); } clear_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized); } static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global, char **msg) { bool purge = false; unsigned long roam_timeout = BATADV_TT_CLIENT_ROAM_TIMEOUT; unsigned long temp_timeout = BATADV_TT_CLIENT_TEMP_TIMEOUT; if ((tt_global->common.flags & BATADV_TT_CLIENT_ROAM) && batadv_has_timed_out(tt_global->roam_at, roam_timeout)) { purge = true; *msg = "Roaming timeout\n"; } if ((tt_global->common.flags & BATADV_TT_CLIENT_TEMP) && batadv_has_timed_out(tt_global->common.added_at, temp_timeout)) { purge = true; *msg = "Temporary client timeout\n"; } return purge; } static void batadv_tt_global_purge(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct hlist_head *head; struct hlist_node *node_tmp; spinlock_t *list_lock; /* protects write access to the hash lists */ u32 i; char *msg = NULL; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, common); if (!batadv_tt_global_to_purge(tt_global, &msg)) continue; batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, batadv_print_vid(tt_global->common.vid), msg); hlist_del_rcu(&tt_common->hash_entry); batadv_tt_global_entry_put(tt_global); } spin_unlock_bh(list_lock); } } static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; if (!bat_priv->tt.global_hash) return; hash = bat_priv->tt.global_hash; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { hlist_del_rcu(&tt_common_entry->hash_entry); tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, common); batadv_tt_global_entry_put(tt_global); } spin_unlock_bh(list_lock); } batadv_hash_destroy(hash); bat_priv->tt.global_hash = NULL; } static bool _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry, struct batadv_tt_global_entry *tt_global_entry) { if (tt_local_entry->common.flags & BATADV_TT_CLIENT_WIFI && tt_global_entry->common.flags & BATADV_TT_CLIENT_WIFI) return true; /* check if the two clients are marked as isolated */ if (tt_local_entry->common.flags & BATADV_TT_CLIENT_ISOLA && tt_global_entry->common.flags & BATADV_TT_CLIENT_ISOLA) return true; return false; } /** * batadv_transtable_search() - get the mesh destination for a given client * @bat_priv: the bat priv with all the soft interface information * @src: mac address of the source client * @addr: mac address of the destination client * @vid: VLAN identifier * * Return: a pointer to the originator that was selected as destination in the * mesh for contacting the client 'addr', NULL otherwise. * In case of multiple originators serving the same client, the function returns * the best one (best in terms of metric towards the destination node). * * If the two clients are AP isolated the function returns NULL. */ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, const u8 *src, const u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry = NULL; struct batadv_tt_global_entry *tt_global_entry = NULL; struct batadv_orig_node *orig_node = NULL; struct batadv_tt_orig_list_entry *best_entry; if (src && batadv_vlan_ap_isola_get(bat_priv, vid)) { tt_local_entry = batadv_tt_local_hash_find(bat_priv, src, vid); if (!tt_local_entry || (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING)) goto out; } tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global_entry) goto out; /* check whether the clients should not communicate due to AP * isolation */ if (tt_local_entry && _batadv_is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; rcu_read_lock(); best_entry = batadv_transtable_best_orig(bat_priv, tt_global_entry); /* found anything? */ if (best_entry) orig_node = best_entry->orig_node; if (orig_node && !kref_get_unless_zero(&orig_node->refcount)) orig_node = NULL; rcu_read_unlock(); out: batadv_tt_global_entry_put(tt_global_entry); batadv_tt_local_entry_put(tt_local_entry); return orig_node; } /** * batadv_tt_global_crc() - calculates the checksum of the local table belonging * to the given orig_node * @bat_priv: the bat priv with all the soft interface information * @orig_node: originator for which the CRC should be computed * @vid: VLAN identifier for which the CRC32 has to be computed * * This function computes the checksum for the global table corresponding to a * specific originator. In particular, the checksum is computed as follows: For * each client connected to the originator the CRC32C of the MAC address and the * VID is computed and then all the CRC32Cs of the various clients are xor'ed * together. * * The idea behind is that CRC32C should be used as much as possible in order to * produce a unique hash of the table, but since the order which is used to feed * the CRC32C function affects the result and since every node in the network * probably sorts the clients differently, the hash function cannot be directly * computed over the entire table. Hence the CRC32C is used only on * the single client entry, while all the results are then xor'ed together * because the XOR operation can combine them all while trying to reduce the * noise as much as possible. * * Return: the checksum of the global table of a given originator. */ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct batadv_tt_orig_list_entry *tt_orig; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; u32 i, crc_tmp, crc = 0; u8 flags; __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_common, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, common); /* compute the CRC only for entries belonging to the * VLAN identified by the vid passed as parameter */ if (tt_common->vid != vid) continue; /* Roaming clients are in the global table for * consistency only. They don't have to be * taken into account while computing the * global crc */ if (tt_common->flags & BATADV_TT_CLIENT_ROAM) continue; /* Temporary clients have not been announced yet, so * they have to be skipped while computing the global * crc */ if (tt_common->flags & BATADV_TT_CLIENT_TEMP) continue; /* find out if this global entry is announced by this * originator */ tt_orig = batadv_tt_global_orig_entry_find(tt_global, orig_node); if (!tt_orig) continue; /* use network order to read the VID: this ensures that * every node reads the bytes in the same order. */ tmp_vid = htons(tt_common->vid); crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes */ flags = tt_orig->flags; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); batadv_tt_orig_list_entry_put(tt_orig); } rcu_read_unlock(); } return crc; } /** * batadv_tt_local_crc() - calculates the checksum of the local table * @bat_priv: the bat priv with all the soft interface information * @vid: VLAN identifier for which the CRC32 has to be computed * * For details about the computation, please refer to the documentation for * batadv_tt_global_crc(). * * Return: the checksum of the local table */ static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct hlist_head *head; u32 i, crc_tmp, crc = 0; u8 flags; __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_common, head, hash_entry) { /* compute the CRC only for entries belonging to the * VLAN identified by vid */ if (tt_common->vid != vid) continue; /* not yet committed clients have not to be taken into * account while computing the CRC */ if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; /* use network order to read the VID: this ensures that * every node reads the bytes in the same order. */ tmp_vid = htons(tt_common->vid); crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes */ flags = tt_common->flags & BATADV_TT_SYNC_MASK; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); } rcu_read_unlock(); } return crc; } /** * batadv_tt_req_node_release() - free tt_req node entry * @ref: kref pointer of the tt req_node entry */ static void batadv_tt_req_node_release(struct kref *ref) { struct batadv_tt_req_node *tt_req_node; tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount); kmem_cache_free(batadv_tt_req_cache, tt_req_node); } /** * batadv_tt_req_node_put() - decrement the tt_req_node refcounter and * possibly release it * @tt_req_node: tt_req_node to be free'd */ static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node) { if (!tt_req_node) return; kref_put(&tt_req_node->refcount, batadv_tt_req_node_release); } static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) { struct batadv_tt_req_node *node; struct hlist_node *safe; spin_lock_bh(&bat_priv->tt.req_list_lock); hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { hlist_del_init(&node->list); batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); } static void batadv_tt_save_orig_buffer(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const void *tt_buff, u16 tt_buff_len) { /* Replace the old buffer only if I received something in the * last OGM (the OGM could carry no changes) */ spin_lock_bh(&orig_node->tt_buff_lock); if (tt_buff_len > 0) { kfree(orig_node->tt_buff); orig_node->tt_buff_len = 0; orig_node->tt_buff = kmalloc(tt_buff_len, GFP_ATOMIC); if (orig_node->tt_buff) { memcpy(orig_node->tt_buff, tt_buff, tt_buff_len); orig_node->tt_buff_len = tt_buff_len; } } spin_unlock_bh(&orig_node->tt_buff_lock); } static void batadv_tt_req_purge(struct batadv_priv *bat_priv) { struct batadv_tt_req_node *node; struct hlist_node *safe; spin_lock_bh(&bat_priv->tt.req_list_lock); hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { if (batadv_has_timed_out(node->issued_at, BATADV_TT_REQUEST_TIMEOUT)) { hlist_del_init(&node->list); batadv_tt_req_node_put(node); } } spin_unlock_bh(&bat_priv->tt.req_list_lock); } /** * batadv_tt_req_node_new() - search and possibly create a tt_req_node object * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node this request is being issued for * * Return: the pointer to the new tt_req_node struct if no request * has already been issued for this orig_node, NULL otherwise. */ static struct batadv_tt_req_node * batadv_tt_req_node_new(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_tt_req_node *tt_req_node_tmp, *tt_req_node = NULL; spin_lock_bh(&bat_priv->tt.req_list_lock); hlist_for_each_entry(tt_req_node_tmp, &bat_priv->tt.req_list, list) { if (batadv_compare_eth(tt_req_node_tmp, orig_node) && !batadv_has_timed_out(tt_req_node_tmp->issued_at, BATADV_TT_REQUEST_TIMEOUT)) goto unlock; } tt_req_node = kmem_cache_alloc(batadv_tt_req_cache, GFP_ATOMIC); if (!tt_req_node) goto unlock; kref_init(&tt_req_node->refcount); ether_addr_copy(tt_req_node->addr, orig_node->orig); tt_req_node->issued_at = jiffies; kref_get(&tt_req_node->refcount); hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list); unlock: spin_unlock_bh(&bat_priv->tt.req_list_lock); return tt_req_node; } /** * batadv_tt_local_valid() - verify local tt entry and get flags * @entry_ptr: to be checked local tt entry * @data_ptr: not used but definition required to satisfy the callback prototype * @flags: a pointer to store TT flags for this client to * * Checks the validity of the given local TT entry. If it is, then the provided * flags pointer is updated. * * Return: true if the entry is a valid, false otherwise. */ static bool batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr, u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW) return false; if (flags) *flags = tt_common_entry->flags; return true; } /** * batadv_tt_global_valid() - verify global tt entry and get flags * @entry_ptr: to be checked global tt entry * @data_ptr: an orig_node object (may be NULL) * @flags: a pointer to store TT flags for this client to * * Checks the validity of the given global TT entry. If it is, then the provided * flags pointer is updated either with the common (summed) TT flags if data_ptr * is NULL or the specific, per originator TT flags otherwise. * * Return: true if the entry is a valid, false otherwise. */ static bool batadv_tt_global_valid(const void *entry_ptr, const void *data_ptr, u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; const struct batadv_tt_global_entry *tt_global_entry; const struct batadv_orig_node *orig_node = data_ptr; if (tt_common_entry->flags & BATADV_TT_CLIENT_ROAM || tt_common_entry->flags & BATADV_TT_CLIENT_TEMP) return false; tt_global_entry = container_of(tt_common_entry, struct batadv_tt_global_entry, common); return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node, flags); } /** * batadv_tt_tvlv_generate() - fill the tvlv buff with the tt entries from the * specified tt hash * @bat_priv: the bat priv with all the soft interface information * @hash: hash table containing the tt entries * @tt_len: expected tvlv tt data buffer length in number of bytes * @tvlv_buff: pointer to the buffer to fill with the TT data * @valid_cb: function to filter tt change entries and to return TT flags * @cb_data: data passed to the filter function as argument * * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb * is not provided then this becomes a no-op. */ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, void *tvlv_buff, u16 tt_len, bool (*valid_cb)(const void *, const void *, u8 *flags), void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; struct hlist_head *head; u16 tt_tot, tt_num_entries = 0; u8 flags; bool ret; u32 i; tt_tot = batadv_tt_entries(tt_len); tt_change = tvlv_buff; if (!valid_cb) return; rcu_read_lock(); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (tt_tot == tt_num_entries) break; ret = valid_cb(tt_common_entry, cb_data, &flags); if (!ret) continue; ether_addr_copy(tt_change->addr, tt_common_entry->addr); tt_change->flags = flags; tt_change->vid = htons(tt_common_entry->vid); memset(tt_change->reserved, 0, sizeof(tt_change->reserved)); tt_num_entries++; tt_change++; } } rcu_read_unlock(); } /** * batadv_tt_global_check_crc() - check if all the CRCs are correct * @orig_node: originator for which the CRCs have to be checked * @tt_vlan: pointer to the first tvlv VLAN entry * @num_vlan: number of tvlv VLAN entries * * Return: true if all the received CRCs match the locally stored ones, false * otherwise */ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_vlan_data *tt_vlan, u16 num_vlan) { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; int i, orig_num_vlan; u32 crc; /* check if each received CRC matches the locally stored one */ for (i = 0; i < num_vlan; i++) { tt_vlan_tmp = tt_vlan + i; /* if orig_node is a backbone node for this VLAN, don't check * the CRC as we ignore all the global entries over it */ if (batadv_bla_is_backbone_gw_orig(orig_node->bat_priv, orig_node->orig, ntohs(tt_vlan_tmp->vid))) continue; vlan = batadv_orig_node_vlan_get(orig_node, ntohs(tt_vlan_tmp->vid)); if (!vlan) return false; crc = vlan->tt.crc; batadv_orig_node_vlan_put(vlan); if (crc != ntohl(tt_vlan_tmp->crc)) return false; } /* check if any excess VLANs exist locally for the originator * which are not mentioned in the TVLV from the originator. */ rcu_read_lock(); orig_num_vlan = 0; hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) orig_num_vlan++; rcu_read_unlock(); if (orig_num_vlan > num_vlan) return false; return true; } /** * batadv_tt_local_update_crc() - update all the local CRCs * @bat_priv: the bat priv with all the soft interface information */ static void batadv_tt_local_update_crc(struct batadv_priv *bat_priv) { struct batadv_softif_vlan *vlan; /* recompute the global CRC for each VLAN */ rcu_read_lock(); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { vlan->tt.crc = batadv_tt_local_crc(bat_priv, vlan->vid); } rcu_read_unlock(); } /** * batadv_tt_global_update_crc() - update all the global CRCs for this orig_node * @bat_priv: the bat priv with all the soft interface information * @orig_node: the orig_node for which the CRCs have to be updated */ static void batadv_tt_global_update_crc(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_orig_node_vlan *vlan; u32 crc; /* recompute the global CRC for each VLAN */ rcu_read_lock(); hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { /* if orig_node is a backbone node for this VLAN, don't compute * the CRC as we ignore all the global entries over it */ if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vlan->vid)) continue; crc = batadv_tt_global_crc(bat_priv, orig_node, vlan->vid); vlan->tt.crc = crc; } rcu_read_unlock(); } /** * batadv_send_tt_request() - send a TT Request message to a given node * @bat_priv: the bat priv with all the soft interface information * @dst_orig_node: the destination of the message * @ttvn: the version number that the source of the message is looking for * @tt_vlan: pointer to the first tvlv VLAN object to request * @num_vlan: number of tvlv VLAN entries * @full_table: ask for the entire translation table if true, while only for the * last TT diff otherwise * * Return: true if the TT Request was sent, false otherwise */ static bool batadv_send_tt_request(struct batadv_priv *bat_priv, struct batadv_orig_node *dst_orig_node, u8 ttvn, struct batadv_tvlv_tt_vlan_data *tt_vlan, u16 num_vlan, bool full_table) { struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_tt_req_node *tt_req_node = NULL; struct batadv_tvlv_tt_vlan_data *tt_vlan_req; struct batadv_hard_iface *primary_if; bool ret = false; int i, size; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* The new tt_req will be issued only if I'm not waiting for a * reply from the same orig_node yet */ tt_req_node = batadv_tt_req_node_new(bat_priv, dst_orig_node); if (!tt_req_node) goto out; size = sizeof(*tvlv_tt_data) + sizeof(*tt_vlan_req) * num_vlan; tvlv_tt_data = kzalloc(size, GFP_ATOMIC); if (!tvlv_tt_data) goto out; tvlv_tt_data->flags = BATADV_TT_REQUEST; tvlv_tt_data->ttvn = ttvn; tvlv_tt_data->num_vlan = htons(num_vlan); /* send all the CRCs within the request. This is needed by intermediate * nodes to ensure they have the correct table before replying */ tt_vlan_req = (struct batadv_tvlv_tt_vlan_data *)(tvlv_tt_data + 1); for (i = 0; i < num_vlan; i++) { tt_vlan_req->vid = tt_vlan->vid; tt_vlan_req->crc = tt_vlan->crc; tt_vlan_req++; tt_vlan++; } if (full_table) tvlv_tt_data->flags |= BATADV_TT_FULL_TABLE; batadv_dbg(BATADV_DBG_TT, bat_priv, "Sending TT_REQUEST to %pM [%c]\n", dst_orig_node->orig, full_table ? 'F' : '.'); batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_TX); batadv_tvlv_unicast_send(bat_priv, primary_if->net_dev->dev_addr, dst_orig_node->orig, BATADV_TVLV_TT, 1, tvlv_tt_data, size); ret = true; out: batadv_hardif_put(primary_if); if (ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); if (!hlist_unhashed(&tt_req_node->list)) { hlist_del_init(&tt_req_node->list); batadv_tt_req_node_put(tt_req_node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); } batadv_tt_req_node_put(tt_req_node); kfree(tvlv_tt_data); return ret; } /** * batadv_send_other_tt_response() - send reply to tt request concerning another * node's translation table * @bat_priv: the bat priv with all the soft interface information * @tt_data: tt data containing the tt request information * @req_src: mac address of tt request sender * @req_dst: mac address of tt request recipient * * Return: true if tt request reply was sent, false otherwise. */ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, u8 *req_src, u8 *req_dst) { struct batadv_orig_node *req_dst_orig_node; struct batadv_orig_node *res_dst_orig_node = NULL; struct batadv_tvlv_tt_change *tt_change; struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_tvlv_tt_vlan_data *tt_vlan; bool ret = false, full_table; u8 orig_ttvn, req_ttvn; u16 tvlv_len; s32 tt_len; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_REQUEST from %pM for ttvn: %u (%pM) [%c]\n", req_src, tt_data->ttvn, req_dst, ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.')); /* Let's get the orig node of the REAL destination */ req_dst_orig_node = batadv_orig_hash_find(bat_priv, req_dst); if (!req_dst_orig_node) goto out; res_dst_orig_node = batadv_orig_hash_find(bat_priv, req_src); if (!res_dst_orig_node) goto out; orig_ttvn = (u8)atomic_read(&req_dst_orig_node->last_ttvn); req_ttvn = tt_data->ttvn; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(tt_data + 1); /* this node doesn't have the requested data */ if (orig_ttvn != req_ttvn || !batadv_tt_global_check_crc(req_dst_orig_node, tt_vlan, ntohs(tt_data->num_vlan))) goto out; /* If the full table has been explicitly requested */ if (tt_data->flags & BATADV_TT_FULL_TABLE || !req_dst_orig_node->tt_buff) full_table = true; else full_table = false; /* TT fragmentation hasn't been implemented yet, so send as many * TT entries fit a single packet as possible only */ if (!full_table) { spin_lock_bh(&req_dst_orig_node->tt_buff_lock); tt_len = req_dst_orig_node->tt_buff_len; tvlv_len = batadv_tt_prepare_tvlv_global_data(req_dst_orig_node, &tvlv_tt_data, &tt_change, &tt_len); if (!tt_len) goto unlock; /* Copy the last orig_node's OGM buffer */ memcpy(tt_change, req_dst_orig_node->tt_buff, req_dst_orig_node->tt_buff_len); spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); } else { /* allocate the tvlv, put the tt_data and all the tt_vlan_data * in the initial part */ tt_len = -1; tvlv_len = batadv_tt_prepare_tvlv_global_data(req_dst_orig_node, &tvlv_tt_data, &tt_change, &tt_len); if (!tt_len) goto out; /* fill the rest of the tvlv with the real TT entries */ batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.global_hash, tt_change, tt_len, batadv_tt_global_valid, req_dst_orig_node); } /* Don't send the response, if larger than fragmented packet. */ tt_len = sizeof(struct batadv_unicast_tvlv_packet) + tvlv_len; if (tt_len > atomic_read(&bat_priv->packet_size_max)) { net_ratelimited_function(batadv_info, bat_priv->soft_iface, "Ignoring TT_REQUEST from %pM; Response size exceeds max packet size.\n", res_dst_orig_node->orig); goto out; } tvlv_tt_data->flags = BATADV_TT_RESPONSE; tvlv_tt_data->ttvn = req_ttvn; if (full_table) tvlv_tt_data->flags |= BATADV_TT_FULL_TABLE; batadv_dbg(BATADV_DBG_TT, bat_priv, "Sending TT_RESPONSE %pM for %pM [%c] (ttvn: %u)\n", res_dst_orig_node->orig, req_dst_orig_node->orig, full_table ? 'F' : '.', req_ttvn); batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); batadv_tvlv_unicast_send(bat_priv, req_dst_orig_node->orig, req_src, BATADV_TVLV_TT, 1, tvlv_tt_data, tvlv_len); ret = true; goto out; unlock: spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); out: batadv_orig_node_put(res_dst_orig_node); batadv_orig_node_put(req_dst_orig_node); kfree(tvlv_tt_data); return ret; } /** * batadv_send_my_tt_response() - send reply to tt request concerning this * node's translation table * @bat_priv: the bat priv with all the soft interface information * @tt_data: tt data containing the tt request information * @req_src: mac address of tt request sender * * Return: true if tt request reply was sent, false otherwise. */ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, u8 *req_src) { struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_hard_iface *primary_if = NULL; struct batadv_tvlv_tt_change *tt_change; struct batadv_orig_node *orig_node; u8 my_ttvn, req_ttvn; u16 tvlv_len; bool full_table; s32 tt_len; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_REQUEST from %pM for ttvn: %u (me) [%c]\n", req_src, tt_data->ttvn, ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.')); spin_lock_bh(&bat_priv->tt.commit_lock); my_ttvn = (u8)atomic_read(&bat_priv->tt.vn); req_ttvn = tt_data->ttvn; orig_node = batadv_orig_hash_find(bat_priv, req_src); if (!orig_node) goto out; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* If the full table has been explicitly requested or the gap * is too big send the whole local translation table */ if (tt_data->flags & BATADV_TT_FULL_TABLE || my_ttvn != req_ttvn || !bat_priv->tt.last_changeset) full_table = true; else full_table = false; /* TT fragmentation hasn't been implemented yet, so send as many * TT entries fit a single packet as possible only */ if (!full_table) { spin_lock_bh(&bat_priv->tt.last_changeset_lock); tt_len = bat_priv->tt.last_changeset_len; tvlv_len = batadv_tt_prepare_tvlv_local_data(bat_priv, &tvlv_tt_data, &tt_change, &tt_len); if (!tt_len || !tvlv_len) goto unlock; /* Copy the last orig_node's OGM buffer */ memcpy(tt_change, bat_priv->tt.last_changeset, bat_priv->tt.last_changeset_len); spin_unlock_bh(&bat_priv->tt.last_changeset_lock); } else { req_ttvn = (u8)atomic_read(&bat_priv->tt.vn); /* allocate the tvlv, put the tt_data and all the tt_vlan_data * in the initial part */ tt_len = -1; tvlv_len = batadv_tt_prepare_tvlv_local_data(bat_priv, &tvlv_tt_data, &tt_change, &tt_len); if (!tt_len || !tvlv_len) goto out; /* fill the rest of the tvlv with the real TT entries */ batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.local_hash, tt_change, tt_len, batadv_tt_local_valid, NULL); } tvlv_tt_data->flags = BATADV_TT_RESPONSE; tvlv_tt_data->ttvn = req_ttvn; if (full_table) tvlv_tt_data->flags |= BATADV_TT_FULL_TABLE; batadv_dbg(BATADV_DBG_TT, bat_priv, "Sending TT_RESPONSE to %pM [%c] (ttvn: %u)\n", orig_node->orig, full_table ? 'F' : '.', req_ttvn); batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); batadv_tvlv_unicast_send(bat_priv, primary_if->net_dev->dev_addr, req_src, BATADV_TVLV_TT, 1, tvlv_tt_data, tvlv_len); goto out; unlock: spin_unlock_bh(&bat_priv->tt.last_changeset_lock); out: spin_unlock_bh(&bat_priv->tt.commit_lock); batadv_orig_node_put(orig_node); batadv_hardif_put(primary_if); kfree(tvlv_tt_data); /* The packet was for this host, so it doesn't need to be re-routed */ return true; } /** * batadv_send_tt_response() - send reply to tt request * @bat_priv: the bat priv with all the soft interface information * @tt_data: tt data containing the tt request information * @req_src: mac address of tt request sender * @req_dst: mac address of tt request recipient * * Return: true if tt request reply was sent, false otherwise. */ static bool batadv_send_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, u8 *req_src, u8 *req_dst) { if (batadv_is_my_mac(bat_priv, req_dst)) return batadv_send_my_tt_response(bat_priv, tt_data, req_src); return batadv_send_other_tt_response(bat_priv, tt_data, req_src, req_dst); } static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_change *tt_change, u16 tt_num_changes, u8 ttvn) { int i; int roams; for (i = 0; i < tt_num_changes; i++) { if ((tt_change + i)->flags & BATADV_TT_CLIENT_DEL) { roams = (tt_change + i)->flags & BATADV_TT_CLIENT_ROAM; batadv_tt_global_del(bat_priv, orig_node, (tt_change + i)->addr, ntohs((tt_change + i)->vid), "tt removed by changes", roams); } else { if (!batadv_tt_global_add(bat_priv, orig_node, (tt_change + i)->addr, ntohs((tt_change + i)->vid), (tt_change + i)->flags, ttvn)) /* In case of problem while storing a * global_entry, we stop the updating * procedure without committing the * ttvn change. This will avoid to send * corrupted data on tt_request */ return; } } set_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized); } static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_change *tt_change, u8 ttvn, u8 *resp_src, u16 num_entries) { struct batadv_orig_node *orig_node; orig_node = batadv_orig_hash_find(bat_priv, resp_src); if (!orig_node) goto out; /* Purge the old table first.. */ batadv_tt_global_del_orig(bat_priv, orig_node, -1, "Received full table"); _batadv_tt_update_changes(bat_priv, orig_node, tt_change, num_entries, ttvn); spin_lock_bh(&orig_node->tt_buff_lock); kfree(orig_node->tt_buff); orig_node->tt_buff_len = 0; orig_node->tt_buff = NULL; spin_unlock_bh(&orig_node->tt_buff_lock); atomic_set(&orig_node->last_ttvn, ttvn); out: batadv_orig_node_put(orig_node); } static void batadv_tt_update_changes(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, u16 tt_num_changes, u8 ttvn, struct batadv_tvlv_tt_change *tt_change) { _batadv_tt_update_changes(bat_priv, orig_node, tt_change, tt_num_changes, ttvn); batadv_tt_save_orig_buffer(bat_priv, orig_node, tt_change, batadv_tt_len(tt_num_changes)); atomic_set(&orig_node->last_ttvn, ttvn); } /** * batadv_is_my_client() - check if a client is served by the local node * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to check * @vid: VLAN identifier * * Return: true if the client is served by this node, false otherwise. */ bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry; bool ret = false; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) goto out; /* Check if the client has been logically deleted (but is kept for * consistency purpose) */ if ((tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) || (tt_local_entry->common.flags & BATADV_TT_CLIENT_ROAM)) goto out; ret = true; out: batadv_tt_local_entry_put(tt_local_entry); return ret; } /** * batadv_handle_tt_response() - process incoming tt reply * @bat_priv: the bat priv with all the soft interface information * @tt_data: tt data containing the tt request information * @resp_src: mac address of tt reply sender * @num_entries: number of tt change entries appended to the tt data */ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, u8 *resp_src, u16 num_entries) { struct batadv_tt_req_node *node; struct hlist_node *safe; struct batadv_orig_node *orig_node = NULL; struct batadv_tvlv_tt_change *tt_change; u8 *tvlv_ptr = (u8 *)tt_data; u16 change_offset; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n", resp_src, tt_data->ttvn, num_entries, ((tt_data->flags & BATADV_TT_FULL_TABLE) ? 'F' : '.')); orig_node = batadv_orig_hash_find(bat_priv, resp_src); if (!orig_node) goto out; spin_lock_bh(&orig_node->tt_lock); change_offset = sizeof(struct batadv_tvlv_tt_vlan_data); change_offset *= ntohs(tt_data->num_vlan); change_offset += sizeof(*tt_data); tvlv_ptr += change_offset; tt_change = (struct batadv_tvlv_tt_change *)tvlv_ptr; if (tt_data->flags & BATADV_TT_FULL_TABLE) { batadv_tt_fill_gtable(bat_priv, tt_change, tt_data->ttvn, resp_src, num_entries); } else { batadv_tt_update_changes(bat_priv, orig_node, num_entries, tt_data->ttvn, tt_change); } /* Recalculate the CRC for this orig_node and store it */ batadv_tt_global_update_crc(bat_priv, orig_node); spin_unlock_bh(&orig_node->tt_lock); /* Delete the tt_req_node from pending tt_requests list */ spin_lock_bh(&bat_priv->tt.req_list_lock); hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { if (!batadv_compare_eth(node->addr, resp_src)) continue; hlist_del_init(&node->list); batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); out: batadv_orig_node_put(orig_node); } static void batadv_tt_roam_list_free(struct batadv_priv *bat_priv) { struct batadv_tt_roam_node *node, *safe; spin_lock_bh(&bat_priv->tt.roam_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt.roam_list, list) { list_del(&node->list); kmem_cache_free(batadv_tt_roam_cache, node); } spin_unlock_bh(&bat_priv->tt.roam_list_lock); } static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) { struct batadv_tt_roam_node *node, *safe; spin_lock_bh(&bat_priv->tt.roam_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt.roam_list, list) { if (!batadv_has_timed_out(node->first_time, BATADV_ROAMING_MAX_TIME)) continue; list_del(&node->list); kmem_cache_free(batadv_tt_roam_cache, node); } spin_unlock_bh(&bat_priv->tt.roam_list_lock); } /** * batadv_tt_check_roam_count() - check if a client has roamed too frequently * @bat_priv: the bat priv with all the soft interface information * @client: mac address of the roaming client * * This function checks whether the client already reached the * maximum number of possible roaming phases. In this case the ROAMING_ADV * will not be sent. * * Return: true if the ROAMING_ADV can be sent, false otherwise */ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) { struct batadv_tt_roam_node *tt_roam_node; bool ret = false; spin_lock_bh(&bat_priv->tt.roam_list_lock); /* The new tt_req will be issued only if I'm not waiting for a * reply from the same orig_node yet */ list_for_each_entry(tt_roam_node, &bat_priv->tt.roam_list, list) { if (!batadv_compare_eth(tt_roam_node->addr, client)) continue; if (batadv_has_timed_out(tt_roam_node->first_time, BATADV_ROAMING_MAX_TIME)) continue; if (!batadv_atomic_dec_not_zero(&tt_roam_node->counter)) /* Sorry, you roamed too many times! */ goto unlock; ret = true; break; } if (!ret) { tt_roam_node = kmem_cache_alloc(batadv_tt_roam_cache, GFP_ATOMIC); if (!tt_roam_node) goto unlock; tt_roam_node->first_time = jiffies; atomic_set(&tt_roam_node->counter, BATADV_ROAMING_MAX_COUNT - 1); ether_addr_copy(tt_roam_node->addr, client); list_add(&tt_roam_node->list, &bat_priv->tt.roam_list); ret = true; } unlock: spin_unlock_bh(&bat_priv->tt.roam_list_lock); return ret; } /** * batadv_send_roam_adv() - send a roaming advertisement message * @bat_priv: the bat priv with all the soft interface information * @client: mac address of the roaming client * @vid: VLAN identifier * @orig_node: message destination * * Send a ROAMING_ADV message to the node which was previously serving this * client. This is done to inform the node that from now on all traffic destined * for this particular roamed client has to be forwarded to the sender of the * roaming message. */ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, unsigned short vid, struct batadv_orig_node *orig_node) { struct batadv_hard_iface *primary_if; struct batadv_tvlv_roam_adv tvlv_roam; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* before going on we have to check whether the client has * already roamed to us too many times */ if (!batadv_tt_check_roam_count(bat_priv, client)) goto out; batadv_dbg(BATADV_DBG_TT, bat_priv, "Sending ROAMING_ADV to %pM (client %pM, vid: %d)\n", orig_node->orig, client, batadv_print_vid(vid)); batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX); memcpy(tvlv_roam.client, client, sizeof(tvlv_roam.client)); tvlv_roam.vid = htons(vid); batadv_tvlv_unicast_send(bat_priv, primary_if->net_dev->dev_addr, orig_node->orig, BATADV_TVLV_ROAM, 1, &tvlv_roam, sizeof(tvlv_roam)); out: batadv_hardif_put(primary_if); } static void batadv_tt_purge(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_tt *priv_tt; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); priv_tt = container_of(delayed_work, struct batadv_priv_tt, work); bat_priv = container_of(priv_tt, struct batadv_priv, tt); batadv_tt_local_purge(bat_priv, BATADV_TT_LOCAL_TIMEOUT); batadv_tt_global_purge(bat_priv); batadv_tt_req_purge(bat_priv); batadv_tt_roam_purge(bat_priv); queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); } /** * batadv_tt_free() - Free translation table of soft interface * @bat_priv: the bat priv with all the soft interface information */ void batadv_tt_free(struct batadv_priv *bat_priv) { batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_ROAM, 1); batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_TT, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_TT, 1); cancel_delayed_work_sync(&bat_priv->tt.work); batadv_tt_local_table_free(bat_priv); batadv_tt_global_table_free(bat_priv); batadv_tt_req_list_free(bat_priv); batadv_tt_changes_list_free(bat_priv); batadv_tt_roam_list_free(bat_priv); kfree(bat_priv->tt.last_changeset); } /** * batadv_tt_local_set_flags() - set or unset the specified flags on the local * table and possibly count them in the TT size * @bat_priv: the bat priv with all the soft interface information * @flags: the flag to switch * @enable: whether to set or unset the flag * @count: whether to increase the TT size by the number of changed entries */ static void batadv_tt_local_set_flags(struct batadv_priv *bat_priv, u16 flags, bool enable, bool count) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common_entry; struct hlist_head *head; u32 i; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (enable) { if ((tt_common_entry->flags & flags) == flags) continue; tt_common_entry->flags |= flags; } else { if (!(tt_common_entry->flags & flags)) continue; tt_common_entry->flags &= ~flags; } if (!count) continue; batadv_tt_local_size_inc(bat_priv, tt_common_entry->vid); } rcu_read_unlock(); } } /* Purge out all the tt local entries marked with BATADV_TT_CLIENT_PENDING */ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ u32 i; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { if (!(tt_common->flags & BATADV_TT_CLIENT_PENDING)) continue; batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting local tt entry (%pM, vid: %d): pending\n", tt_common->addr, batadv_print_vid(tt_common->vid)); batadv_tt_local_size_dec(bat_priv, tt_common->vid); hlist_del_rcu(&tt_common->hash_entry); tt_local = container_of(tt_common, struct batadv_tt_local_entry, common); batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); } } /** * batadv_tt_local_commit_changes_nolock() - commit all pending local tt changes * which have been queued in the time since the last commit * @bat_priv: the bat priv with all the soft interface information * * Caller must hold tt->commit_lock. */ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) { lockdep_assert_held(&bat_priv->tt.commit_lock); if (atomic_read(&bat_priv->tt.local_changes) < 1) { if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt)) batadv_tt_tvlv_container_update(bat_priv); return; } batadv_tt_local_set_flags(bat_priv, BATADV_TT_CLIENT_NEW, false, true); batadv_tt_local_purge_pending_clients(bat_priv); batadv_tt_local_update_crc(bat_priv); /* Increment the TTVN only once per OGM interval */ atomic_inc(&bat_priv->tt.vn); batadv_dbg(BATADV_DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n", (u8)atomic_read(&bat_priv->tt.vn)); /* reset the sending counter */ atomic_set(&bat_priv->tt.ogm_append_cnt, BATADV_TT_OGM_APPEND_MAX); batadv_tt_tvlv_container_update(bat_priv); } /** * batadv_tt_local_commit_changes() - commit all pending local tt changes which * have been queued in the time since the last commit * @bat_priv: the bat priv with all the soft interface information */ void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv) { spin_lock_bh(&bat_priv->tt.commit_lock); batadv_tt_local_commit_changes_nolock(bat_priv); spin_unlock_bh(&bat_priv->tt.commit_lock); } /** * batadv_is_ap_isolated() - Check if packet from upper layer should be dropped * @bat_priv: the bat priv with all the soft interface information * @src: source mac address of packet * @dst: destination mac address of packet * @vid: vlan id of packet * * Return: true when src+dst(+vid) pair should be isolated, false otherwise */ bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, u8 *src, u8 *dst, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry; struct batadv_tt_global_entry *tt_global_entry; struct batadv_softif_vlan *vlan; bool ret = false; vlan = batadv_softif_vlan_get(bat_priv, vid); if (!vlan) return false; if (!atomic_read(&vlan->ap_isolation)) goto vlan_put; tt_local_entry = batadv_tt_local_hash_find(bat_priv, dst, vid); if (!tt_local_entry) goto vlan_put; tt_global_entry = batadv_tt_global_hash_find(bat_priv, src, vid); if (!tt_global_entry) goto local_entry_put; if (_batadv_is_ap_isolated(tt_local_entry, tt_global_entry)) ret = true; batadv_tt_global_entry_put(tt_global_entry); local_entry_put: batadv_tt_local_entry_put(tt_local_entry); vlan_put: batadv_softif_vlan_put(vlan); return ret; } /** * batadv_tt_update_orig() - update global translation table with new tt * information received via ogms * @bat_priv: the bat priv with all the soft interface information * @orig_node: the orig_node of the ogm * @tt_buff: pointer to the first tvlv VLAN entry * @tt_num_vlan: number of tvlv VLAN entries * @tt_change: pointer to the first entry in the TT buffer * @tt_num_changes: number of tt changes inside the tt buffer * @ttvn: translation table version number of this changeset */ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const void *tt_buff, u16 tt_num_vlan, struct batadv_tvlv_tt_change *tt_change, u16 tt_num_changes, u8 ttvn) { u8 orig_ttvn = (u8)atomic_read(&orig_node->last_ttvn); struct batadv_tvlv_tt_vlan_data *tt_vlan; bool full_table = true; bool has_tt_init; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff; has_tt_init = test_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized); /* orig table not initialised AND first diff is in the OGM OR the ttvn * increased by one -> we can apply the attached changes */ if ((!has_tt_init && ttvn == 1) || ttvn - orig_ttvn == 1) { /* the OGM could not contain the changes due to their size or * because they have already been sent BATADV_TT_OGM_APPEND_MAX * times. * In this case send a tt request */ if (!tt_num_changes) { full_table = false; goto request_table; } spin_lock_bh(&orig_node->tt_lock); batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, tt_change); /* Even if we received the precomputed crc with the OGM, we * prefer to recompute it to spot any possible inconsistency * in the global table */ batadv_tt_global_update_crc(bat_priv, orig_node); spin_unlock_bh(&orig_node->tt_lock); /* The ttvn alone is not enough to guarantee consistency * because a single value could represent different states * (due to the wrap around). Thus a node has to check whether * the resulting table (after applying the changes) is still * consistent or not. E.g. a node could disconnect while its * ttvn is X and reconnect on ttvn = X + TTVN_MAX: in this case * checking the CRC value is mandatory to detect the * inconsistency */ if (!batadv_tt_global_check_crc(orig_node, tt_vlan, tt_num_vlan)) goto request_table; } else { /* if we missed more than one change or our tables are not * in sync anymore -> request fresh tt data */ if (!has_tt_init || ttvn != orig_ttvn || !batadv_tt_global_check_crc(orig_node, tt_vlan, tt_num_vlan)) { request_table: batadv_dbg(BATADV_DBG_TT, bat_priv, "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u num_changes: %u)\n", orig_node->orig, ttvn, orig_ttvn, tt_num_changes); batadv_send_tt_request(bat_priv, orig_node, ttvn, tt_vlan, tt_num_vlan, full_table); return; } } } /** * batadv_tt_global_client_is_roaming() - check if a client is marked as roaming * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to check * @vid: VLAN identifier * * Return: true if we know that the client has moved from its old originator * to another one. This entry is still kept for consistency purposes and will be * deleted later by a DEL or because of timeout */ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt_global_entry; bool ret = false; tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global_entry) goto out; ret = tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM; batadv_tt_global_entry_put(tt_global_entry); out: return ret; } /** * batadv_tt_local_client_is_roaming() - tells whether the client is roaming * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the local client to query * @vid: VLAN identifier * * Return: true if the local client is known to be roaming (it is not served by * this node anymore) or not. If yes, the client is still present in the table * to keep the latter consistent with the node TTVN */ bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry; bool ret = false; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) goto out; ret = tt_local_entry->common.flags & BATADV_TT_CLIENT_ROAM; batadv_tt_local_entry_put(tt_local_entry); out: return ret; } /** * batadv_tt_add_temporary_global_entry() - Add temporary entry to global TT * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which the temporary entry should be associated with * @addr: mac address of the client * @vid: VLAN id of the new temporary global translation table * * Return: true when temporary tt entry could be added, false otherwise */ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, unsigned short vid) { /* ignore loop detect macs, they are not supposed to be in the tt local * data as well. */ if (batadv_bla_is_loopdetect_mac(addr)) return false; if (!batadv_tt_global_add(bat_priv, orig_node, addr, vid, BATADV_TT_CLIENT_TEMP, atomic_read(&orig_node->last_ttvn))) return false; batadv_dbg(BATADV_DBG_TT, bat_priv, "Added temporary global client (addr: %pM, vid: %d, orig: %pM)\n", addr, batadv_print_vid(vid), orig_node->orig); return true; } /** * batadv_tt_local_resize_to_mtu() - resize the local translation table fit the * maximum packet size that can be transported through the mesh * @soft_iface: netdev struct of the mesh interface * * Remove entries older than 'timeout' and half timeout if more entries need * to be removed. */ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); int packet_size_max = atomic_read(&bat_priv->packet_size_max); int table_size, timeout = BATADV_TT_LOCAL_TIMEOUT / 2; bool reduced = false; spin_lock_bh(&bat_priv->tt.commit_lock); while (true) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; batadv_tt_local_purge(bat_priv, timeout); batadv_tt_local_purge_pending_clients(bat_priv); timeout /= 2; reduced = true; net_ratelimited_function(batadv_info, soft_iface, "Forced to purge local tt entries to fit new maximum fragment MTU (%i)\n", packet_size_max); } /* commit these changes immediately, to avoid synchronization problem * with the TTVN */ if (reduced) batadv_tt_local_commit_changes_nolock(bat_priv); spin_unlock_bh(&bat_priv->tt.commit_lock); } /** * batadv_tt_tvlv_ogm_handler_v1() - process incoming tt tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the gateway data * @tvlv_value_len: tvlv buffer length */ static void batadv_tt_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_tvlv_tt_change *tt_change; struct batadv_tvlv_tt_data *tt_data; u16 num_entries, num_vlan; if (tvlv_value_len < sizeof(*tt_data)) return; tt_data = tvlv_value; tvlv_value_len -= sizeof(*tt_data); num_vlan = ntohs(tt_data->num_vlan); if (tvlv_value_len < sizeof(*tt_vlan) * num_vlan) return; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(tt_data + 1); tt_change = (struct batadv_tvlv_tt_change *)(tt_vlan + num_vlan); tvlv_value_len -= sizeof(*tt_vlan) * num_vlan; num_entries = batadv_tt_entries(tvlv_value_len); batadv_tt_update_orig(bat_priv, orig, tt_vlan, num_vlan, tt_change, num_entries, tt_data->ttvn); } /** * batadv_tt_tvlv_unicast_handler_v1() - process incoming (unicast) tt tvlv * container * @bat_priv: the bat priv with all the soft interface information * @src: mac address of tt tvlv sender * @dst: mac address of tt tvlv recipient * @tvlv_value: tvlv buffer containing the tt data * @tvlv_value_len: tvlv buffer length * * Return: NET_RX_DROP if the tt tvlv is to be re-routed, NET_RX_SUCCESS * otherwise. */ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_tt_data *tt_data; u16 tt_vlan_len, tt_num_entries; char tt_flag; bool ret; if (tvlv_value_len < sizeof(*tt_data)) return NET_RX_SUCCESS; tt_data = tvlv_value; tvlv_value_len -= sizeof(*tt_data); tt_vlan_len = sizeof(struct batadv_tvlv_tt_vlan_data); tt_vlan_len *= ntohs(tt_data->num_vlan); if (tvlv_value_len < tt_vlan_len) return NET_RX_SUCCESS; tvlv_value_len -= tt_vlan_len; tt_num_entries = batadv_tt_entries(tvlv_value_len); switch (tt_data->flags & BATADV_TT_DATA_TYPE_MASK) { case BATADV_TT_REQUEST: batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_RX); /* If this node cannot provide a TT response the tt_request is * forwarded */ ret = batadv_send_tt_response(bat_priv, tt_data, src, dst); if (!ret) { if (tt_data->flags & BATADV_TT_FULL_TABLE) tt_flag = 'F'; else tt_flag = '.'; batadv_dbg(BATADV_DBG_TT, bat_priv, "Routing TT_REQUEST to %pM [%c]\n", dst, tt_flag); /* tvlv API will re-route the packet */ return NET_RX_DROP; } break; case BATADV_TT_RESPONSE: batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_RX); if (batadv_is_my_mac(bat_priv, dst)) { batadv_handle_tt_response(bat_priv, tt_data, src, tt_num_entries); return NET_RX_SUCCESS; } if (tt_data->flags & BATADV_TT_FULL_TABLE) tt_flag = 'F'; else tt_flag = '.'; batadv_dbg(BATADV_DBG_TT, bat_priv, "Routing TT_RESPONSE to %pM [%c]\n", dst, tt_flag); /* tvlv API will re-route the packet */ return NET_RX_DROP; } return NET_RX_SUCCESS; } /** * batadv_roam_tvlv_unicast_handler_v1() - process incoming tt roam tvlv * container * @bat_priv: the bat priv with all the soft interface information * @src: mac address of tt tvlv sender * @dst: mac address of tt tvlv recipient * @tvlv_value: tvlv buffer containing the tt data * @tvlv_value_len: tvlv buffer length * * Return: NET_RX_DROP if the tt roam tvlv is to be re-routed, NET_RX_SUCCESS * otherwise. */ static int batadv_roam_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_roam_adv *roaming_adv; struct batadv_orig_node *orig_node = NULL; /* If this node is not the intended recipient of the * roaming advertisement the packet is forwarded * (the tvlv API will re-route the packet). */ if (!batadv_is_my_mac(bat_priv, dst)) return NET_RX_DROP; if (tvlv_value_len < sizeof(*roaming_adv)) goto out; orig_node = batadv_orig_hash_find(bat_priv, src); if (!orig_node) goto out; batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX); roaming_adv = tvlv_value; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received ROAMING_ADV from %pM (client %pM)\n", src, roaming_adv->client); batadv_tt_global_add(bat_priv, orig_node, roaming_adv->client, ntohs(roaming_adv->vid), BATADV_TT_CLIENT_ROAM, atomic_read(&orig_node->last_ttvn) + 1); out: batadv_orig_node_put(orig_node); return NET_RX_SUCCESS; } /** * batadv_tt_init() - initialise the translation table internals * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure. */ int batadv_tt_init(struct batadv_priv *bat_priv) { int ret; /* synchronized flags must be remote */ BUILD_BUG_ON(!(BATADV_TT_SYNC_MASK & BATADV_TT_REMOTE_MASK)); ret = batadv_tt_local_init(bat_priv); if (ret < 0) return ret; ret = batadv_tt_global_init(bat_priv); if (ret < 0) { batadv_tt_local_table_free(bat_priv); return ret; } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, batadv_tt_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_TT, 1, BATADV_NO_FLAGS); batadv_tvlv_handler_register(bat_priv, NULL, batadv_roam_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_ROAM, 1, BATADV_NO_FLAGS); INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); return 1; } /** * batadv_tt_global_is_isolated() - check if a client is marked as isolated * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client * @vid: the identifier of the VLAN where this client is connected * * Return: true if the client is marked with the TT_CLIENT_ISOLA flag, false * otherwise */ bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt; bool ret; tt = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt) return false; ret = tt->common.flags & BATADV_TT_CLIENT_ISOLA; batadv_tt_global_entry_put(tt); return ret; } /** * batadv_tt_cache_init() - Initialize tt memory object cache * * Return: 0 on success or negative error number in case of failure. */ int __init batadv_tt_cache_init(void) { size_t tl_size = sizeof(struct batadv_tt_local_entry); size_t tg_size = sizeof(struct batadv_tt_global_entry); size_t tt_orig_size = sizeof(struct batadv_tt_orig_list_entry); size_t tt_change_size = sizeof(struct batadv_tt_change_node); size_t tt_req_size = sizeof(struct batadv_tt_req_node); size_t tt_roam_size = sizeof(struct batadv_tt_roam_node); batadv_tl_cache = kmem_cache_create("batadv_tl_cache", tl_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tl_cache) return -ENOMEM; batadv_tg_cache = kmem_cache_create("batadv_tg_cache", tg_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tg_cache) goto err_tt_tl_destroy; batadv_tt_orig_cache = kmem_cache_create("batadv_tt_orig_cache", tt_orig_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tt_orig_cache) goto err_tt_tg_destroy; batadv_tt_change_cache = kmem_cache_create("batadv_tt_change_cache", tt_change_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tt_change_cache) goto err_tt_orig_destroy; batadv_tt_req_cache = kmem_cache_create("batadv_tt_req_cache", tt_req_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tt_req_cache) goto err_tt_change_destroy; batadv_tt_roam_cache = kmem_cache_create("batadv_tt_roam_cache", tt_roam_size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!batadv_tt_roam_cache) goto err_tt_req_destroy; return 0; err_tt_req_destroy: kmem_cache_destroy(batadv_tt_req_cache); batadv_tt_req_cache = NULL; err_tt_change_destroy: kmem_cache_destroy(batadv_tt_change_cache); batadv_tt_change_cache = NULL; err_tt_orig_destroy: kmem_cache_destroy(batadv_tt_orig_cache); batadv_tt_orig_cache = NULL; err_tt_tg_destroy: kmem_cache_destroy(batadv_tg_cache); batadv_tg_cache = NULL; err_tt_tl_destroy: kmem_cache_destroy(batadv_tl_cache); batadv_tl_cache = NULL; return -ENOMEM; } /** * batadv_tt_cache_destroy() - Destroy tt memory object cache */ void batadv_tt_cache_destroy(void) { kmem_cache_destroy(batadv_tl_cache); kmem_cache_destroy(batadv_tg_cache); kmem_cache_destroy(batadv_tt_orig_cache); kmem_cache_destroy(batadv_tt_change_cache); kmem_cache_destroy(batadv_tt_req_cache); kmem_cache_destroy(batadv_tt_roam_cache); } |
| 7153 7160 277 277 7159 712 6811 6822 7150 7155 6814 712 2546 2545 2546 2544 2546 2545 2546 2546 2546 2516 2545 2546 2546 2546 2544 3838 3839 1536 1536 3966 3965 522 3964 214 3964 244 3965 3966 3837 3839 3833 3836 1463 2664 3839 3839 3839 2672 2672 2671 28 28 28 28 28 28 28 28 2 2 28 28 1536 1536 1289 1505 1536 1536 1535 28 1536 1535 1536 31 31 31 31 31 1537 1537 1536 2567 2553 2567 2567 2562 745 745 745 745 744 744 744 2552 744 2568 1343 993 1343 305 305 305 305 | 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 | // 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? As a power of 2 */ int page_cluster; const int page_cluster_max = 31; /* Protecting only lru_rotate.fbatch which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct cpu_fbatches { local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch activate; #endif }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void __page_cache_release(struct folio *folio) { if (folio_test_lru(folio)) { struct lruvec *lruvec; unsigned long flags; lruvec = folio_lruvec_lock_irqsave(folio, &flags); lruvec_del_folio(lruvec, folio); __folio_clear_lru_flags(folio); unlock_page_lruvec_irqrestore(lruvec, flags); } /* See comment on folio_test_mlocked in release_pages() */ if (unlikely(folio_test_mlocked(folio))) { long nr_pages = folio_nr_pages(folio); __folio_clear_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); } } static void __folio_put_small(struct folio *folio) { __page_cache_release(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, 0); } static void __folio_put_large(struct folio *folio) { /* * __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 (!folio_test_hugetlb(folio)) __page_cache_release(folio); destroy_large_folio(folio); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) free_zone_device_page(&folio->page); else if (unlikely(folio_test_large(folio))) __folio_put_large(folio); else __folio_put_small(folio); } EXPORT_SYMBOL(__folio_put); /** * 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. */ void put_pages_list(struct list_head *pages) { struct folio *folio, *next; list_for_each_entry_safe(folio, next, pages, lru) { if (!folio_put_testzero(folio)) { list_del(&folio->lru); continue; } if (folio_test_large(folio)) { list_del(&folio->lru); __folio_put_large(folio); continue; } /* LRU flag must be clear because it's passed using the lru */ } free_unref_page_list(pages); INIT_LIST_HEAD(pages); } EXPORT_SYMBOL(put_pages_list); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add_fn(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of release_pages(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; /* block memcg migration while the folio moves between lru */ if (move_fn != lru_add_fn && !folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch->folios, folio_batch_count(fbatch)); folio_batch_reinit(fbatch); } static void folio_batch_add_and_move(struct folio_batch *fbatch, struct folio *folio, move_fn_t move_fn) { if (folio_batch_add(fbatch, folio) && !folio_test_large(folio) && !lru_cache_disabled()) return; folio_batch_move_lru(fbatch, move_fn); } static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio) { if (!folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (!folio_test_locked(folio) && !folio_test_dirty(folio) && !folio_test_unevictable(folio) && folio_test_lru(folio)) { struct folio_batch *fbatch; unsigned long flags; folio_get(folio); local_lock_irqsave(&lru_rotate.lock, flags); fbatch = this_cpu_ptr(&lru_rotate.fbatch); folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; 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 += cost; else lruvec->anon_cost += cost; /* * 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_refault(struct folio *folio) { lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void folio_activate_fn(struct lruvec *lruvec, struct folio *folio) { if (!folio_test_active(folio) && !folio_test_unevictable(folio)) { long nr_pages = folio_nr_pages(folio); lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, folio_activate_fn); } void folio_activate(struct folio *folio) { if (folio_test_lru(folio) && !folio_test_active(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.activate); folio_batch_add_and_move(fbatch, folio, folio_activate_fn); local_unlock(&cpu_fbatches.lock); } } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (folio_test_clear_lru(folio)) { lruvec = folio_lruvec_lock_irq(folio); folio_activate_fn(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void folio_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); if (folio_test_unevictable(folio)) return; if (!folio_test_referenced(folio)) { folio_set_referenced(folio); return; } if (!folio_test_workingset(folio)) { folio_set_workingset(folio); return; } /* see the comment on MAX_NR_TIERS */ do { new_flags = old_flags & LRU_REFS_MASK; if (new_flags == LRU_REFS_MASK) break; new_flags += BIT(LRU_REFS_PGOFF); new_flags |= old_flags & ~LRU_REFS_MASK; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); } #else static void folio_inc_refs(struct folio *folio) { } #endif /* CONFIG_LRU_GEN */ /* * 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 folio_mark_accessed(struct folio *folio) { if (lru_gen_enabled()) { folio_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { struct folio_batch *fbatch; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_add_folio() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_get(folio); local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); folio_batch_add_and_move(fbatch, folio, lru_add_fn); local_unlock(&cpu_fbatches.lock); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot 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 folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __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 lruvec *lruvec, struct folio *folio) { if (!folio_test_unevictable(folio) && (folio_test_active(folio) || lru_gen_enabled())) { long nr_pages = folio_nr_pages(folio); lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct lruvec *lruvec, struct folio *folio) { if (folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { long nr_pages = folio_nr_pages(folio); lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's folio_batch. * 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 cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add_fn); fbatch = &per_cpu(lru_rotate.fbatch, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); folio_batch_move_lru(fbatch, lru_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file_fn); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_fn); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree_fn); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { struct folio_batch *fbatch; /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio)) return; folio_get(folio); local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file); folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn); local_unlock(&cpu_fbatches.lock); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_lru(folio) && !folio_test_unevictable(folio) && (folio_test_active(folio) || lru_gen_enabled())) { struct folio_batch *fbatch; folio_get(folio); local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate); folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn); local_unlock(&cpu_fbatches.lock); } } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (folio_test_lru(folio) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree); folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn); local_unlock(&cpu_fbatches.lock); } } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * 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(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #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(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || data_race(folio_batch_count(&per_cpu(lru_rotate.fbatch, cpu))) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * 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. */ static 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 folio_batch 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 * folio_batch 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 (cpu_needs_drain(cpu)) { 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); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { int i; struct encoded_page **encoded = arg.encoded_pages; LIST_HEAD(pages_to_free); struct lruvec *lruvec = NULL; unsigned long flags = 0; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct folio *folio; /* Turn any of the argument types into a folio */ folio = page_folio(encoded_page_ptr(encoded[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; } if (is_huge_zero_page(&folio->page)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (put_devmap_managed_page(&folio->page)) continue; if (folio_put_testzero(folio)) free_zone_device_page(&folio->page); continue; } if (!folio_put_testzero(folio)) continue; if (folio_test_large(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } __folio_put_large(folio); continue; } if (folio_test_lru(folio)) { struct lruvec *prev_lruvec = lruvec; lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); if (prev_lruvec != lruvec) lock_batch = 0; lruvec_del_folio(lruvec, folio); __folio_clear_lru_flags(folio); } /* * In rare cases, when truncation or holepunching raced with * munlock after VM_LOCKED was cleared, Mlocked may still be * found set here. This does not indicate a problem, unless * "unevictable_pgs_cleared" appears worryingly large. */ if (unlikely(folio_test_mlocked(folio))) { __folio_clear_mlocked(folio); zone_stat_sub_folio(folio, NR_MLOCK); count_vm_event(UNEVICTABLE_PGCLEARED); } list_add(&folio->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 folios 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 folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } release_pages(fbatch->folios, folio_batch_count(fbatch)); folio_batch_reinit(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } /* * 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 */ } |
| 1952 2 1953 1950 1954 1954 759 758 759 758 759 759 759 758 741 741 741 741 741 740 741 759 759 758 759 759 759 758 759 759 759 759 759 759 759 759 759 741 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/filelock.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/ima.h> #include "internal.h" /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. * We retain backwards compatibility and require setgid bit to be removed * unconditionally if S_IXGRP is set. Otherwise we have the exact same * requirements as setattr_prepare() and setattr_copy(). * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode) { umode_t mode = inode->i_mode; if (!(mode & S_ISGID)) return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) return ATTR_KILL_SGID; return 0; } EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both * set{g,u}id bits need to be removed the corresponding mask of both flags is * returned. * * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ int setattr_should_drop_suidgid(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(idmap, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(setattr_should_drop_suidgid); /** * chown_ok - verify permissions to chown inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsuid: uid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chown_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsuid_t ia_vfsuid) { vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid()) && vfsuid_eq(ia_vfsuid, vfsuid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsuid_valid(vfsuid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * chgrp_ok - verify permissions to chgrp inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsgid: gid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chgrp_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t ia_vfsgid) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid)) return true; if (vfsgid_in_group_p(ia_vfsgid)) return true; } if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsgid_valid(vfsgid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @idmap: idmap of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(idmap, inode, attr->ia_vfsuid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(idmap, inode, attr->ia_vfsgid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { vfsgid_t vfsgid; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ia_valid & ATTR_GID) vfsgid = attr->ia_vfsgid; else vfsgid = i_gid_into_vfsgid(idmap, inode); /* Also check the setgid bit! */ if (!in_group_or_capable(idmap, inode, vfsgid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(idmap, inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(idmap, dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode * @idmap: idmap of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr on idmapped mounts. Necessary permission checks to determine * whether or not the S_ISGID property needs to be removed are performed with * the correct idmapped mount permission helpers. * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; inode->i_mode = mode; } } EXPORT_SYMBOL(setattr_copy); int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid) { int error; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(idmap, inode)) { error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; } } return 0; } EXPORT_SYMBOL(may_setattr); /** * notify_change - modify attributes of a filesytem object * @idmap: idmap of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); error = may_setattr(idmap, inode, ia_valid); if (error) return error; if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsuid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsgid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !vfsuid_valid(i_uid_into_vfsuid(idmap, inode))) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; error = security_inode_setattr(idmap, dentry, attr); if (error) return error; error = try_break_deleg(inode, delegated_inode); if (error) return error; if (inode->i_op->setattr) error = inode->i_op->setattr(idmap, dentry, attr); else error = simple_setattr(idmap, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); ima_inode_post_setattr(idmap, dentry); evm_inode_post_setattr(dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 10 10 10 10 10 10 10 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | // SPDX-License-Identifier: GPL-2.0-only /* * 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. * * Generic TIME_WAIT sockets functions * * From code orinally in TCP */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> /** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash * @tw: timewait socket * @hashinfo: hashinfo pointer * * unhash a timewait socket from bind hash, if hashed. * bind hash lock must be held by caller. * Returns 1 if caller should call inet_twsk_put() after lock release. */ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind2_bucket *tb2 = tw->tw_tb2; struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) return; __sk_del_bind_node((struct sock *)tw); tw->tw_tb = NULL; tw->tw_tb2 = NULL; inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); __sock_put((struct sock *)tw); } /* Must be called with locally disabled BHs. */ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); struct inet_bind_hashbucket *bhead, *bhead2; spin_lock(lock); sk_nulls_del_node_init_rcu((struct sock *)tw); spin_unlock(lock); /* Disassociate with bind bucket. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, hashinfo->bhash_size)]; bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw, twsk_net(tw), tw->tw_num); spin_lock(&bhead->lock); spin_lock(&bhead2->lock); inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead2->lock); spin_unlock(&bhead->lock); refcount_dec(&tw->tw_dr->tw_refcount); inet_twsk_put(tw); } void inet_twsk_free(struct inet_timewait_sock *tw) { struct module *owner = tw->tw_prot->owner; twsk_destructor((struct sock *)tw); kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); module_put(owner); } void inet_twsk_put(struct inet_timewait_sock *tw) { if (refcount_dec_and_test(&tw->tw_refcnt)) inet_twsk_free(tw); } EXPORT_SYMBOL_GPL(inet_twsk_put); static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&tw->tw_node, list); } /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it * from the SK, and mess with hash chains and list linkage. */ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo) { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead, *bhead2; /* Step 1: Put TW into bind hash. Original socket stays there too. Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num); spin_lock(&bhead->lock); spin_lock(&bhead2->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); tw->tw_tb2 = icsk->icsk_bind2_hash; WARN_ON(!icsk->icsk_bind2_hash); sk_add_bind_node((struct sock *)tw, &tw->tw_tb2->owners); spin_unlock(&bhead2->lock); spin_unlock(&bhead->lock); spin_lock(lock); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(lock); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. * - one reference for timer. * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. * Also note that after this point, we lost our implicit reference * so we are not allowed to use tw anymore. */ refcount_set(&tw->tw_refcnt, 3); } EXPORT_SYMBOL_GPL(inet_twsk_hashdance); static void tw_timer_handler(struct timer_list *t) { struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); inet_twsk_kill(tw); } struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, struct inet_timewait_death_row *dr, const int state) { struct inet_timewait_sock *tw; if (refcount_read(&dr->tw_refcount) - 1 >= READ_ONCE(dr->sysctl_max_tw_buckets)) return NULL; tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, GFP_ATOMIC); if (tw) { const struct inet_sock *inet = inet_sk(sk); tw->tw_dr = dr; /* Give us an identity. */ tw->tw_daddr = inet->inet_daddr; tw->tw_rcv_saddr = inet->inet_rcv_saddr; tw->tw_bound_dev_if = sk->sk_bound_dev_if; tw->tw_tos = inet->tos; tw->tw_num = inet->inet_num; tw->tw_state = TCP_TIME_WAIT; tw->tw_substate = state; tw->tw_sport = inet->inet_sport; tw->tw_dport = inet->inet_dport; tw->tw_family = sk->sk_family; tw->tw_reuse = sk->sk_reuse; tw->tw_reuseport = sk->sk_reuseport; tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this * timewait socket. */ refcount_set(&tw->tw_refcnt, 0); __module_get(tw->tw_prot->owner); } return tw; } EXPORT_SYMBOL_GPL(inet_twsk_alloc); /* These are always called from BH context. See callers in * tcp_input.c to verify this. */ /* This is for handling early-kills of TIME_WAIT sockets. * Warning : consume reference. * Caller should not access tw anymore. */ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { if (del_timer_sync(&tw->tw_timer)) inet_twsk_kill(tw); inet_twsk_put(tw); } EXPORT_SYMBOL(inet_twsk_deschedule_put); void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) { /* timeout := RTO * 3.5 * * 3.5 = 1+2+0.5 to wait for two retransmits. * * RATIONALE: if FIN arrived and we entered TIME-WAIT state, * our ACK acking that FIN can be lost. If N subsequent retransmitted * FINs (or previous seqments) are lost (probability of such event * is p^(N+1), where p is probability to lose single packet and * time to detect the loss is about RTO*(2^N - 1) with exponential * backoff). Normal timewait length is calculated so, that we * waited at least for one retransmitted FIN (maximal RTO is 120sec). * [ BTW Linux. following BSD, violates this requirement waiting * only for 60sec, we should wait at least for 240 secs. * Well, 240 consumes too much of resources 8) * ] * This interval is not reduced to catch old duplicate and * responces to our wandering segments living for two MSLs. * However, if we use PAWS to detect * old duplicates, we can reduce the interval to bounds required * by RTO, rather than MSL. So, if peer understands PAWS, we * kill tw bucket after 3.5*RTO (it is important that this number * is greater than TS tick!) and detect old duplicates with help * of PAWS. */ if (!rearm) { bool kill = timeo <= 4*HZ; __NET_INC_STATS(twsk_net(tw), kill ? LINUX_MIB_TIMEWAITKILLED : LINUX_MIB_TIMEWAITED); BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo)); refcount_inc(&tw->tw_dr->tw_refcount); } else { mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { struct inet_timewait_sock *tw; struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; restart_rcu: cond_resched(); rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_state != TCP_TIME_WAIT) { /* A kernel listener socket might not hold refcnt for net, * so reqsk_timer_handler() could be fired after net is * freed. Userspace listener and reqsk never exist here. */ if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV && hashinfo->pernet)) { struct request_sock *req = inet_reqsk(sk); inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); } continue; } tw = inet_twsk(sk); if ((tw->tw_family != family) || refcount_read(&twsk_net(tw)->ns.count)) continue; if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) continue; if (unlikely((tw->tw_family != family) || refcount_read(&twsk_net(tw)->ns.count))) { inet_twsk_put(tw); goto restart; } rcu_read_unlock(); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); goto restart_rcu; } /* If the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != slot) goto restart; rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(inet_twsk_purge); |
| 3 2 3 3 3 3 3 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 | /* * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin * cleaned up code to current version of sparse and added the slicing-by-8 * algorithm to the closely similar existing slicing-by-4 algorithm. * * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com> * Nicer crc32 functions/docs submitted by linux@horizon.com. Thanks! * Code was from the public domain, copyright abandoned. Code was * subsequently included in the kernel, thus was re-licensed under the * GNU GPL v2. * * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com> * Same crc32 function was used in 5 other places in the kernel. * I made one version, and deleted the others. * There are various incantations of crc32(). Some use a seed of 0 or ~0. * Some xor at the end with ~0. The generic crc32() function takes * seed as an argument, and doesn't xor at the end. Then individual * users can do whatever they need. * drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0. * fs/jffs2 uses seed 0, doesn't xor with ~0. * fs/partitions/efi.c uses seed ~0, xor's with ~0. * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. */ /* see: Documentation/staging/crc32.rst for a description of algorithms */ #include <linux/crc32.h> #include <linux/crc32poly.h> #include <linux/module.h> #include <linux/types.h> #include <linux/sched.h> #include "crc32defs.h" #if CRC_LE_BITS > 8 # define tole(x) ((__force u32) cpu_to_le32(x)) #else # define tole(x) (x) #endif #if CRC_BE_BITS > 8 # define tobe(x) ((__force u32) cpu_to_be32(x)) #else # define tobe(x) (x) #endif #include "crc32table.h" MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); #if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 /* implements slicing-by-4 or slicing-by-8 algorithm */ static inline u32 __pure crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) { # ifdef __LITTLE_ENDIAN # define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8) # define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \ t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255]) # define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \ t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255]) # else # define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8) # define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \ t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255]) # define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \ t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255]) # endif const u32 *b; size_t rem_len; # ifdef CONFIG_X86 size_t i; # endif const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3]; # if CRC_LE_BITS != 32 const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7]; # endif u32 q; /* Align it */ if (unlikely((long)buf & 3 && len)) { do { DO_CRC(*buf++); } while ((--len) && ((long)buf)&3); } # if CRC_LE_BITS == 32 rem_len = len & 3; len = len >> 2; # else rem_len = len & 7; len = len >> 3; # endif b = (const u32 *)buf; # ifdef CONFIG_X86 --b; for (i = 0; i < len; i++) { # else for (--b; len; --len) { # endif q = crc ^ *++b; /* use pre increment for speed */ # if CRC_LE_BITS == 32 crc = DO_CRC4; # else crc = DO_CRC8; q = *++b; crc ^= DO_CRC4; # endif } len = rem_len; /* And the last few bytes */ if (len) { u8 *p = (u8 *)(b + 1) - 1; # ifdef CONFIG_X86 for (i = 0; i < len; i++) DO_CRC(*++p); /* use pre increment for speed */ # else do { DO_CRC(*++p); /* use pre increment for speed */ } while (--len); # endif } return crc; #undef DO_CRC #undef DO_CRC4 #undef DO_CRC8 } #endif /** * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II * CRC32/CRC32C * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for other * uses, or the previous crc32/crc32c value if computing incrementally. * @p: pointer to buffer over which CRC32/CRC32C is run * @len: length of buffer @p * @tab: little-endian Ethernet table * @polynomial: CRC32/CRC32c LE polynomial */ static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, size_t len, const u32 (*tab)[256], u32 polynomial) { #if CRC_LE_BITS == 1 int i; while (len--) { crc ^= *p++; for (i = 0; i < 8; i++) crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); } # elif CRC_LE_BITS == 2 while (len--) { crc ^= *p++; crc = (crc >> 2) ^ tab[0][crc & 3]; crc = (crc >> 2) ^ tab[0][crc & 3]; crc = (crc >> 2) ^ tab[0][crc & 3]; crc = (crc >> 2) ^ tab[0][crc & 3]; } # elif CRC_LE_BITS == 4 while (len--) { crc ^= *p++; crc = (crc >> 4) ^ tab[0][crc & 15]; crc = (crc >> 4) ^ tab[0][crc & 15]; } # elif CRC_LE_BITS == 8 /* aka Sarwate algorithm */ while (len--) { crc ^= *p++; crc = (crc >> 8) ^ tab[0][crc & 255]; } # else crc = (__force u32) __cpu_to_le32(crc); crc = crc32_body(crc, p, len, tab); crc = __le32_to_cpu((__force __le32)crc); #endif return crc; } #if CRC_LE_BITS == 1 u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) { return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE); } u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) { return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE); } #else u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) { return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE); } u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) { return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE); } #endif EXPORT_SYMBOL(crc32_le); EXPORT_SYMBOL(__crc32c_le); u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be); /* * This multiplies the polynomials x and y modulo the given modulus. * This follows the "little-endian" CRC convention that the lsbit * represents the highest power of x, and the msbit represents x^0. */ static u32 __attribute_const__ gf2_multiply(u32 x, u32 y, u32 modulus) { u32 product = x & 1 ? y : 0; int i; for (i = 0; i < 31; i++) { product = (product >> 1) ^ (product & 1 ? modulus : 0); x >>= 1; product ^= x & 1 ? y : 0; } return product; } /** * crc32_generic_shift - Append @len 0 bytes to crc, in logarithmic time * @crc: The original little-endian CRC (i.e. lsbit is x^31 coefficient) * @len: The number of bytes. @crc is multiplied by x^(8*@len) * @polynomial: The modulus used to reduce the result to 32 bits. * * It's possible to parallelize CRC computations by computing a CRC * over separate ranges of a buffer, then summing them. * This shifts the given CRC by 8*len bits (i.e. produces the same effect * as appending len bytes of zero to the data), in time proportional * to log(len). */ static u32 __attribute_const__ crc32_generic_shift(u32 crc, size_t len, u32 polynomial) { u32 power = polynomial; /* CRC of x^32 */ int i; /* Shift up to 32 bits in the simple linear way */ for (i = 0; i < 8 * (int)(len & 3); i++) crc = (crc >> 1) ^ (crc & 1 ? polynomial : 0); len >>= 2; if (!len) return crc; for (;;) { /* "power" is x^(2^i), modulo the polynomial */ if (len & 1) crc = gf2_multiply(crc, power, polynomial); len >>= 1; if (!len) break; /* Square power, advancing to x^(2^(i+1)) */ power = gf2_multiply(power, power, polynomial); } return crc; } u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len) { return crc32_generic_shift(crc, len, CRC32_POLY_LE); } u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) { return crc32_generic_shift(crc, len, CRC32C_POLY_LE); } EXPORT_SYMBOL(crc32_le_shift); EXPORT_SYMBOL(__crc32c_le_shift); /** * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for * other uses, or the previous crc32 value if computing incrementally. * @p: pointer to buffer over which CRC32 is run * @len: length of buffer @p * @tab: big-endian Ethernet table * @polynomial: CRC32 BE polynomial */ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, size_t len, const u32 (*tab)[256], u32 polynomial) { #if CRC_BE_BITS == 1 int i; while (len--) { crc ^= *p++ << 24; for (i = 0; i < 8; i++) crc = (crc << 1) ^ ((crc & 0x80000000) ? polynomial : 0); } # elif CRC_BE_BITS == 2 while (len--) { crc ^= *p++ << 24; crc = (crc << 2) ^ tab[0][crc >> 30]; crc = (crc << 2) ^ tab[0][crc >> 30]; crc = (crc << 2) ^ tab[0][crc >> 30]; crc = (crc << 2) ^ tab[0][crc >> 30]; } # elif CRC_BE_BITS == 4 while (len--) { crc ^= *p++ << 24; crc = (crc << 4) ^ tab[0][crc >> 28]; crc = (crc << 4) ^ tab[0][crc >> 28]; } # elif CRC_BE_BITS == 8 while (len--) { crc ^= *p++ << 24; crc = (crc << 8) ^ tab[0][crc >> 24]; } # else crc = (__force u32) __cpu_to_be32(crc); crc = crc32_body(crc, p, len, tab); crc = __be32_to_cpu((__force __be32)crc); # endif return crc; } #if CRC_BE_BITS == 1 u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) { return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); } #else u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) { return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE); } #endif EXPORT_SYMBOL(crc32_be); |
| 1 3 1 1 1 1 1 1 4 1 3 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */ #include <linux/skmsg.h> #include <net/sock.h> #include <net/udp.h> #include <net/inet_common.h> #include "udp_impl.h" static struct proto *udpv6_prot_saved __read_mostly; static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return udpv6_prot_saved->recvmsg(sk, msg, len, flags, addr_len); #endif return udp_prot.recvmsg(sk, msg, len, flags, addr_len); } static bool udp_sk_has_data(struct sock *sk) { return !skb_queue_empty(&udp_sk(sk)->reader_queue) || !skb_queue_empty(&sk->sk_receive_queue); } static bool psock_has_data(struct sk_psock *psock) { return !skb_queue_empty(&psock->ingress_skb) || !sk_psock_queue_empty(psock); } #define udp_msg_has_data(__sk, __psock) \ ({ udp_sk_has_data(__sk) || psock_has_data(__psock); }) static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) return 1; if (!timeo) return ret; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = udp_msg_has_data(sk, psock); if (!ret) { wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); ret = udp_msg_has_data(sk, psock); } sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; } static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sk_psock *psock; int copied, ret; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (!len) return 0; psock = sk_psock_get(sk); if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, flags, addr_len); if (!psock_has_data(psock)) { ret = sk_udp_recvmsg(sk, msg, len, flags, addr_len); goto out; } msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { long timeo; int data; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = udp_msg_wait_data(sk, psock, timeo); if (data) { if (psock_has_data(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, flags, addr_len); goto out; } copied = -EAGAIN; } ret = copied; out: sk_psock_put(sk, psock); return ret; } enum { UDP_BPF_IPV4, UDP_BPF_IPV6, UDP_BPF_NUM_PROTS, }; static DEFINE_SPINLOCK(udpv6_prot_lock); static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS]; static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = udp_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; } static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { spin_lock_bh(&udpv6_prot_lock); if (likely(ops != udpv6_prot_saved)) { udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops); smp_store_release(&udpv6_prot_saved, ops); } spin_unlock_bh(&udpv6_prot_lock); } } static int __init udp_bpf_v4_build_proto(void) { udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot); return 0; } late_initcall(udp_bpf_v4_build_proto); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } if (sk->sk_family == AF_INET6) udp_bpf_check_v6_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &udp_bpf_prots[family]); return 0; } EXPORT_SYMBOL_GPL(udp_bpf_update_proto); |
| 3561 3561 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOPRIO_H #define IOPRIO_H #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/iocontext.h> #include <uapi/linux/ioprio.h> /* * Default IO priority. */ #define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0) /* * Check that a priority value has a valid class. */ static inline bool ioprio_valid(unsigned short ioprio) { unsigned short class = IOPRIO_PRIO_CLASS(ioprio); return class > IOPRIO_CLASS_NONE && class <= IOPRIO_CLASS_IDLE; } /* * if process has set io priority explicitly, use that. if not, convert * the cpu scheduler nice value to an io priority */ static inline int task_nice_ioprio(struct task_struct *task) { return (task_nice(task) + 20) / 5; } /* * This is for the case where the task hasn't asked for a specific IO class. * Check for idle and rt task process, and return appropriate IO class. */ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; else if (task_is_realtime(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; } #ifdef CONFIG_BLOCK /* * If the task has set an I/O priority, use that. Otherwise, return * the default I/O priority. * * Expected to be called for current task or with task_lock() held to keep * io_context stable. */ static inline int __get_task_ioprio(struct task_struct *p) { struct io_context *ioc = p->io_context; int prio; if (!ioc) return IOPRIO_DEFAULT; if (p != current) lockdep_assert_held(&p->alloc_lock); prio = ioc->ioprio; if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), task_nice_ioprio(p)); return prio; } #else static inline int __get_task_ioprio(struct task_struct *p) { return IOPRIO_DEFAULT; } #endif /* CONFIG_BLOCK */ static inline int get_current_ioprio(void) { return __get_task_ioprio(current); } extern int set_task_ioprio(struct task_struct *task, int ioprio); #ifdef CONFIG_BLOCK extern int ioprio_check_cap(int ioprio); #else static inline int ioprio_check_cap(int ioprio) { return -ENOTBLK; } #endif /* CONFIG_BLOCK */ #endif |
| 27 27 27 27 9 9 9 1 1 7 44 8 27 9 27 8 32 2 1 44 44 35 35 9 26 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 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ #include "multicast.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/icmpv6.h> #include <linux/if_bridge.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jiffies.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/addrconf.h> #include <net/genetlink.h> #include <net/if_inet6.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "send.h" #include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" static void batadv_mcast_mla_update(struct work_struct *work); /** * batadv_mcast_start_timer() - schedule the multicast periodic worker * @bat_priv: the bat priv with all the soft interface information */ static void batadv_mcast_start_timer(struct batadv_priv *bat_priv) { queue_delayed_work(batadv_event_workqueue, &bat_priv->mcast.work, msecs_to_jiffies(BATADV_MCAST_WORK_PERIOD)); } /** * batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists * @soft_iface: netdev struct of the mesh interface * * If the given soft interface has a bridge on top then the refcount * of the according net device is increased. * * Return: NULL if no such bridge exists. Otherwise the net device of the * bridge. */ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface) { struct net_device *upper = soft_iface; rcu_read_lock(); do { upper = netdev_master_upper_dev_get_rcu(upper); } while (upper && !netif_is_bridge_master(upper)); dev_hold(upper); rcu_read_unlock(); return upper; } /** * batadv_mcast_mla_rtr_flags_softif_get_ipv4() - get mcast router flags from * node for IPv4 * @dev: the interface to check * * Checks the presence of an IPv4 multicast router on this node. * * Caller needs to hold rcu read lock. * * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR4 otherwise. */ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); if (in_dev && IN_DEV_MFORWARD(in_dev)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR4; } /** * batadv_mcast_mla_rtr_flags_softif_get_ipv6() - get mcast router flags from * node for IPv6 * @dev: the interface to check * * Checks the presence of an IPv6 multicast router on this node. * * Caller needs to hold rcu read lock. * * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR6 otherwise. */ #if IS_ENABLED(CONFIG_IPV6_MROUTE) static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { struct inet6_dev *in6_dev = __in6_dev_get(dev); if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR6; } #else static inline u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { return BATADV_MCAST_WANT_NO_RTR6; } #endif /** * batadv_mcast_mla_rtr_flags_softif_get() - get mcast router flags from node * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers on this * node. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv, struct net_device *bridge) { struct net_device *dev = bridge ? bridge : bat_priv->soft_iface; u8 flags = BATADV_NO_FLAGS; rcu_read_lock(); flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv4(dev); flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv6(dev); rcu_read_unlock(); return flags; } /** * batadv_mcast_mla_rtr_flags_bridge_get() - get mcast router flags from bridge * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers behind a bridge. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, struct net_device *bridge) { struct net_device *dev = bat_priv->soft_iface; u8 flags = BATADV_NO_FLAGS; if (!bridge) return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; if (!br_multicast_has_router_adjacent(dev, ETH_P_IP)) flags |= BATADV_MCAST_WANT_NO_RTR4; if (!br_multicast_has_router_adjacent(dev, ETH_P_IPV6)) flags |= BATADV_MCAST_WANT_NO_RTR6; return flags; } /** * batadv_mcast_mla_rtr_flags_get() - get multicast router flags * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers on this * node or behind its bridge. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv, struct net_device *bridge) { u8 flags = BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; flags &= batadv_mcast_mla_rtr_flags_softif_get(bat_priv, bridge); flags &= batadv_mcast_mla_rtr_flags_bridge_get(bat_priv, bridge); return flags; } /** * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags * @bat_priv: the bat priv with all the soft interface information * * Checks if all active hard interfaces have an MTU larger or equal to 1280 * bytes (IPv6 minimum MTU). * * Return: BATADV_MCAST_HAVE_MC_PTYPE_CAPA if yes, BATADV_NO_FLAGS otherwise. */ static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv) { const struct batadv_hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) { rcu_read_unlock(); return BATADV_NO_FLAGS; } } rcu_read_unlock(); return BATADV_MCAST_HAVE_MC_PTYPE_CAPA; } /** * batadv_mcast_mla_flags_get() - get the new multicast flags * @bat_priv: the bat priv with all the soft interface information * * Return: A set of flags for the current/next TVLV, querier and * bridge state. */ static struct batadv_mcast_mla_flags batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv) { struct net_device *dev = bat_priv->soft_iface; struct batadv_mcast_querier_state *qr4, *qr6; struct batadv_mcast_mla_flags mla_flags; struct net_device *bridge; bridge = batadv_mcast_get_bridge(dev); memset(&mla_flags, 0, sizeof(mla_flags)); mla_flags.enabled = 1; mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv, bridge); mla_flags.tvlv_flags |= batadv_mcast_mla_forw_flags_get(bat_priv); if (!bridge) return mla_flags; dev_put(bridge); mla_flags.bridged = 1; qr4 = &mla_flags.querier_ipv4; qr6 = &mla_flags.querier_ipv6; if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)) pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n"); qr4->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP); qr4->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP); qr6->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6); qr6->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6); mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES; /* 1) If no querier exists at all, then multicast listeners on * our local TT clients behind the bridge will keep silent. * 2) If the selected querier is on one of our local TT clients, * behind the bridge, then this querier might shadow multicast * listeners on our local TT clients, behind this bridge. * * In both cases, we will signalize other batman nodes that * we need all multicast traffic of the according protocol. */ if (!qr4->exists || qr4->shadowing) { mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV4; mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR4; } if (!qr6->exists || qr6->shadowing) { mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV6; mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR6; } return mla_flags; } /** * batadv_mcast_mla_is_duplicate() - check whether an address is in a list * @mcast_addr: the multicast address to check * @mcast_list: the list with multicast addresses to search in * * Return: true if the given address is already in the given list. * Otherwise returns false. */ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; hlist_for_each_entry(mcast_entry, mcast_list, list) if (batadv_compare_eth(mcast_entry->addr, mcast_addr)) return true; return false; } /** * batadv_mcast_mla_softif_get_ipv4() - get softif IPv4 multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of IPv4 multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_softif_get_ipv4(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct batadv_hw_addr *new; struct in_device *in_dev; u8 mcast_addr[ETH_ALEN]; struct ip_mc_list *pmc; int ret = 0; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4) return 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return 0; } for (pmc = rcu_dereference(in_dev->mc_list); pmc; pmc = rcu_dereference(pmc->next_rcu)) { if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv4_is_local_multicast(pmc->multiaddr)) continue; if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) && !ipv4_is_local_multicast(pmc->multiaddr)) continue; ip_eth_mc_map(pmc->multiaddr, mcast_addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); ret++; } rcu_read_unlock(); return ret; } /** * batadv_mcast_mla_softif_get_ipv6() - get softif IPv6 multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of IPv6 multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ #if IS_ENABLED(CONFIG_IPV6) static int batadv_mcast_mla_softif_get_ipv6(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct batadv_hw_addr *new; struct inet6_dev *in6_dev; u8 mcast_addr[ETH_ALEN]; struct ifmcaddr6 *pmc6; int ret = 0; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6) return 0; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) { rcu_read_unlock(); return 0; } for (pmc6 = rcu_dereference(in6_dev->mc_list); pmc6; pmc6 = rcu_dereference(pmc6->next)) { if (IPV6_ADDR_MC_SCOPE(&pmc6->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) continue; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv6_addr_is_ll_all_nodes(&pmc6->mca_addr)) continue; if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) && IPV6_ADDR_MC_SCOPE(&pmc6->mca_addr) > IPV6_ADDR_SCOPE_LINKLOCAL) continue; ipv6_eth_mc_map(&pmc6->mca_addr, mcast_addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); ret++; } rcu_read_unlock(); return ret; } #else static inline int batadv_mcast_mla_softif_get_ipv6(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { return 0; } #endif /** * batadv_mcast_mla_softif_get() - get softif multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * If there is a bridge interface on top of dev, collect from that one * instead. Just like with IP addresses and routes, multicast listeners * will(/should) register to the bridge interface instead of an * enslaved bat0. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_softif_get(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct net_device *bridge = batadv_mcast_get_bridge(dev); int ret4, ret6 = 0; if (bridge) dev = bridge; ret4 = batadv_mcast_mla_softif_get_ipv4(dev, mcast_list, flags); if (ret4 < 0) goto out; ret6 = batadv_mcast_mla_softif_get_ipv6(dev, mcast_list, flags); if (ret6 < 0) { ret4 = 0; goto out; } out: dev_put(bridge); return ret4 + ret6; } /** * batadv_mcast_mla_br_addr_cpy() - copy a bridge multicast address * @dst: destination to write to - a multicast MAC address * @src: source to read from - a multicast IP address * * Converts a given multicast IPv4/IPv6 address from a bridge * to its matching multicast MAC address and copies it into the given * destination buffer. * * Caller needs to make sure the destination buffer can hold * at least ETH_ALEN bytes. */ static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src) { if (src->proto == htons(ETH_P_IP)) ip_eth_mc_map(src->dst.ip4, dst); #if IS_ENABLED(CONFIG_IPV6) else if (src->proto == htons(ETH_P_IPV6)) ipv6_eth_mc_map(&src->dst.ip6, dst); #endif else eth_zero_addr(dst); } /** * batadv_mcast_mla_bridge_get() - get bridged-in multicast listeners * @dev: a bridge slave whose bridge to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of multicast listeners residing * on foreign, non-mesh devices which we gave access to our mesh via * a bridge on top of the given soft interface, dev, in the given * mcast_list. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_bridge_get(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list); struct br_ip_list *br_ip_entry, *tmp; u8 tvlv_flags = flags->tvlv_flags; struct batadv_hw_addr *new; u8 mcast_addr[ETH_ALEN]; int ret; /* we don't need to detect these devices/listeners, the IGMP/MLD * snooping code of the Linux bridge already does that for us */ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); if (ret < 0) goto out; list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) { if (br_ip_entry->addr.proto == htons(ETH_P_IP)) { if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4) continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) && !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; } #if IS_ENABLED(CONFIG_IPV6) if (br_ip_entry->addr.proto == htons(ETH_P_IPV6)) { if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6) continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) && IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) > IPV6_ADDR_SCOPE_LINKLOCAL) continue; } #endif batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); } out: list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) { list_del(&br_ip_entry->list); kfree(br_ip_entry); } return ret; } /** * batadv_mcast_mla_list_free() - free a list of multicast addresses * @mcast_list: the list to free * * Removes and frees all items in the given mcast_list. */ static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { hlist_del(&mcast_entry->list); kfree(mcast_entry); } } /** * batadv_mcast_mla_tt_retract() - clean up multicast listener announcements * @bat_priv: the bat priv with all the soft interface information * @mcast_list: a list of addresses which should _not_ be removed * * Retracts the announcement of any multicast listener from the * translation table except the ones listed in the given mcast_list. * * If mcast_list is NULL then all are retracted. */ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, list) { if (mcast_list && batadv_mcast_mla_is_duplicate(mcast_entry->addr, mcast_list)) continue; batadv_tt_local_remove(bat_priv, mcast_entry->addr, BATADV_NO_FLAGS, "mcast TT outdated", false); hlist_del(&mcast_entry->list); kfree(mcast_entry); } } /** * batadv_mcast_mla_tt_add() - add multicast listener announcements * @bat_priv: the bat priv with all the soft interface information * @mcast_list: a list of addresses which are going to get added * * Adds multicast listener announcements from the given mcast_list to the * translation table if they have not been added yet. */ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; if (!mcast_list) return; hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { if (batadv_mcast_mla_is_duplicate(mcast_entry->addr, &bat_priv->mcast.mla_list)) continue; if (!batadv_tt_local_add(bat_priv->soft_iface, mcast_entry->addr, BATADV_NO_FLAGS, BATADV_NULL_IFINDEX, BATADV_NO_MARK)) continue; hlist_del(&mcast_entry->list); hlist_add_head(&mcast_entry->list, &bat_priv->mcast.mla_list); } } /** * batadv_mcast_querier_log() - debug output regarding the querier status on * link * @bat_priv: the bat priv with all the soft interface information * @str_proto: a string for the querier protocol (e.g. "IGMP" or "MLD") * @old_state: the previous querier state on our link * @new_state: the new querier state on our link * * Outputs debug messages to the logging facility with log level 'mcast' * regarding changes to the querier status on the link which are relevant * to our multicast optimizations. * * Usually this is about whether a querier appeared or vanished in * our mesh or whether the querier is in the suboptimal position of being * behind our local bridge segment: Snooping switches will directly * forward listener reports to the querier, therefore batman-adv and * the bridge will potentially not see these listeners - the querier is * potentially shadowing listeners from us then. * * This is only interesting for nodes with a bridge on top of their * soft interface. */ static void batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto, struct batadv_mcast_querier_state *old_state, struct batadv_mcast_querier_state *new_state) { if (!old_state->exists && new_state->exists) batadv_info(bat_priv->soft_iface, "%s Querier appeared\n", str_proto); else if (old_state->exists && !new_state->exists) batadv_info(bat_priv->soft_iface, "%s Querier disappeared - multicast optimizations disabled\n", str_proto); else if (!bat_priv->mcast.mla_flags.bridged && !new_state->exists) batadv_info(bat_priv->soft_iface, "No %s Querier present - multicast optimizations disabled\n", str_proto); if (new_state->exists) { if ((!old_state->shadowing && new_state->shadowing) || (!old_state->exists && new_state->shadowing)) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "%s Querier is behind our bridged segment: Might shadow listeners\n", str_proto); else if (old_state->shadowing && !new_state->shadowing) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "%s Querier is not behind our bridged segment\n", str_proto); } } /** * batadv_mcast_bridge_log() - debug output for topology changes in bridged * setups * @bat_priv: the bat priv with all the soft interface information * @new_flags: flags indicating the new multicast state * * If no bridges are ever used on this node, then this function does nothing. * * Otherwise this function outputs debug information to the 'mcast' log level * which might be relevant to our multicast optimizations. * * More precisely, it outputs information when a bridge interface is added or * removed from a soft interface. And when a bridge is present, it further * outputs information about the querier state which is relevant for the * multicast flags this node is going to set. */ static void batadv_mcast_bridge_log(struct batadv_priv *bat_priv, struct batadv_mcast_mla_flags *new_flags) { struct batadv_mcast_mla_flags *old_flags = &bat_priv->mcast.mla_flags; if (!old_flags->bridged && new_flags->bridged) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Bridge added: Setting Unsnoopables(U)-flag\n"); else if (old_flags->bridged && !new_flags->bridged) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Bridge removed: Unsetting Unsnoopables(U)-flag\n"); if (new_flags->bridged) { batadv_mcast_querier_log(bat_priv, "IGMP", &old_flags->querier_ipv4, &new_flags->querier_ipv4); batadv_mcast_querier_log(bat_priv, "MLD", &old_flags->querier_ipv6, &new_flags->querier_ipv6); } } /** * batadv_mcast_flags_log() - output debug information about mcast flag changes * @bat_priv: the bat priv with all the soft interface information * @flags: TVLV flags indicating the new multicast state * * Whenever the multicast TVLV flags this node announces change, this function * should be used to notify userspace about the change. */ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags) { bool old_enabled = bat_priv->mcast.mla_flags.enabled; u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags; char str_old_flags[] = "[.... . .]"; sprintf(str_old_flags, "[%c%c%c%s%s%c]", (old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", !(old_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Changing multicast flags from '%s' to '[%c%c%c%s%s%c]'\n", old_enabled ? str_old_flags : "<undefined>", (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", !(flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); } /** * batadv_mcast_mla_flags_update() - update multicast flags * @bat_priv: the bat priv with all the soft interface information * @flags: flags indicating the new multicast state * * Updates the own multicast tvlv with our current multicast related settings, * capabilities and inabilities. */ static void batadv_mcast_mla_flags_update(struct batadv_priv *bat_priv, struct batadv_mcast_mla_flags *flags) { struct batadv_tvlv_mcast_data mcast_data; if (!memcmp(flags, &bat_priv->mcast.mla_flags, sizeof(*flags))) return; batadv_mcast_bridge_log(bat_priv, flags); batadv_mcast_flags_log(bat_priv, flags->tvlv_flags); mcast_data.flags = flags->tvlv_flags; memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved)); batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2, &mcast_data, sizeof(mcast_data)); bat_priv->mcast.mla_flags = *flags; } /** * __batadv_mcast_mla_update() - update the own MLAs * @bat_priv: the bat priv with all the soft interface information * * Updates the own multicast listener announcements in the translation * table as well as the own, announced multicast tvlv container. * * Note that non-conflicting reads and writes to bat_priv->mcast.mla_list * in batadv_mcast_mla_tt_retract() and batadv_mcast_mla_tt_add() are * ensured by the non-parallel execution of the worker this function * belongs to. */ static void __batadv_mcast_mla_update(struct batadv_priv *bat_priv) { struct net_device *soft_iface = bat_priv->soft_iface; struct hlist_head mcast_list = HLIST_HEAD_INIT; struct batadv_mcast_mla_flags flags; int ret; flags = batadv_mcast_mla_flags_get(bat_priv); ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list, &flags); if (ret < 0) goto out; ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list, &flags); if (ret < 0) goto out; spin_lock(&bat_priv->mcast.mla_lock); batadv_mcast_mla_tt_retract(bat_priv, &mcast_list); batadv_mcast_mla_tt_add(bat_priv, &mcast_list); batadv_mcast_mla_flags_update(bat_priv, &flags); spin_unlock(&bat_priv->mcast.mla_lock); out: batadv_mcast_mla_list_free(&mcast_list); } /** * batadv_mcast_mla_update() - update the own MLAs * @work: kernel work struct * * Updates the own multicast listener announcements in the translation * table as well as the own, announced multicast tvlv container. * * In the end, reschedules the work timer. */ static void batadv_mcast_mla_update(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_mcast *priv_mcast; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); priv_mcast = container_of(delayed_work, struct batadv_priv_mcast, work); bat_priv = container_of(priv_mcast, struct batadv_priv, mcast); __batadv_mcast_mla_update(bat_priv); batadv_mcast_start_timer(bat_priv); } /** * batadv_mcast_is_report_ipv4() - check for IGMP reports * @skb: the ethernet frame destined for the mesh * * This call might reallocate skb data. * * Checks whether the given frame is a valid IGMP report. * * Return: If so then true, otherwise false. */ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb) { if (ip_mc_check_igmp(skb) < 0) return false; switch (igmp_hdr(skb)->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: case IGMPV3_HOST_MEMBERSHIP_REPORT: return true; } return false; } /** * batadv_mcast_forw_mode_check_ipv4() - check for optimized forwarding * potential * @bat_priv: the bat priv with all the soft interface information * @skb: the IPv4 packet to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given IPv4 packet has the potential to be forwarded with a * mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL or -ENOMEM in case of memory * allocation failure. */ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct iphdr *iphdr; /* We might fail due to out-of-memory -> drop it */ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr))) return -ENOMEM; if (batadv_mcast_is_report_ipv4(skb)) return -EINVAL; iphdr = ip_hdr(skb); /* link-local multicast listeners behind a bridge are * not snoopable (see RFC4541, section 2.1.2.2) */ if (ipv4_is_local_multicast(iphdr->daddr)) *is_unsnoopable = true; else *is_routable = ETH_P_IP; return 0; } /** * batadv_mcast_is_report_ipv6() - check for MLD reports * @skb: the ethernet frame destined for the mesh * * This call might reallocate skb data. * * Checks whether the given frame is a valid MLD report. * * Return: If so then true, otherwise false. */ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb) { if (ipv6_mc_check_mld(skb) < 0) return false; switch (icmp6_hdr(skb)->icmp6_type) { case ICMPV6_MGM_REPORT: case ICMPV6_MLD2_REPORT: return true; } return false; } /** * batadv_mcast_forw_mode_check_ipv6() - check for optimized forwarding * potential * @bat_priv: the bat priv with all the soft interface information * @skb: the IPv6 packet to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given IPv6 packet has the potential to be forwarded with a * mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory */ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct ipv6hdr *ip6hdr; /* We might fail due to out-of-memory -> drop it */ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr))) return -ENOMEM; if (batadv_mcast_is_report_ipv6(skb)) return -EINVAL; ip6hdr = ipv6_hdr(skb); if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) < IPV6_ADDR_SCOPE_LINKLOCAL) return -EINVAL; /* link-local-all-nodes multicast listeners behind a bridge are * not snoopable (see RFC4541, section 3, paragraph 3) */ if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr)) *is_unsnoopable = true; else if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) > IPV6_ADDR_SCOPE_LINKLOCAL) *is_routable = ETH_P_IPV6; return 0; } /** * batadv_mcast_forw_mode_check() - check for optimized forwarding potential * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast frame to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given multicast ethernet frame has the potential to be * forwarded with a mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory */ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct ethhdr *ethhdr = eth_hdr(skb); if (!atomic_read(&bat_priv->multicast_mode)) return -EINVAL; switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb, is_unsnoopable, is_routable); case ETH_P_IPV6: if (!IS_ENABLED(CONFIG_IPV6)) return -EINVAL; return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb, is_unsnoopable, is_routable); default: return -EINVAL; } } /** * batadv_mcast_forw_want_all_ip_count() - count nodes with unspecific mcast * interest * @bat_priv: the bat priv with all the soft interface information * @ethhdr: ethernet header of a packet * * Return: the number of nodes which want all IPv4 multicast traffic if the * given ethhdr is from an IPv4 packet or the number of nodes which want all * IPv6 traffic if it matches an IPv6 packet. */ static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv, struct ethhdr *ethhdr) { switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return atomic_read(&bat_priv->mcast.num_want_all_ipv4); case ETH_P_IPV6: return atomic_read(&bat_priv->mcast.num_want_all_ipv6); default: /* we shouldn't be here... */ return 0; } } /** * batadv_mcast_forw_rtr_count() - count nodes with a multicast router * @bat_priv: the bat priv with all the soft interface information * @protocol: the ethernet protocol type to count multicast routers for * * Return: the number of nodes which want all routable IPv4 multicast traffic * if the protocol is ETH_P_IP or the number of nodes which want all routable * IPv6 traffic if the protocol is ETH_P_IPV6. Otherwise returns 0. */ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv, int protocol) { switch (protocol) { case ETH_P_IP: return atomic_read(&bat_priv->mcast.num_want_all_rtr4); case ETH_P_IPV6: return atomic_read(&bat_priv->mcast.num_want_all_rtr6); default: return 0; } } /** * batadv_mcast_forw_mode_by_count() - get forwarding mode by count * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to check * @vid: the vlan identifier * @is_routable: stores whether the destination is routable * @count: the number of originators the multicast packet need to be sent to * * For a multicast packet with multiple destination originators, checks which * mode to use. For BATADV_FORW_MCAST it also encapsulates the packet with a * complete batman-adv multicast header. * * Return: * BATADV_FORW_MCAST: If all nodes have multicast packet routing * capabilities and an MTU >= 1280 on all hard interfaces (including us) * and the encapsulated multicast packet with all destination addresses * would still fit into an 1280 bytes batman-adv multicast packet * (excluding the outer ethernet frame) and we could successfully push * the full batman-adv multicast packet header. * BATADV_FORW_UCASTS: If the packet cannot be sent in a batman-adv * multicast packet and the amount of batman-adv unicast packets needed * is smaller or equal to the configured multicast fanout. * BATADV_FORW_BCAST: Otherwise. */ static enum batadv_forw_mode batadv_mcast_forw_mode_by_count(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int is_routable, int count) { unsigned int mcast_hdrlen = batadv_mcast_forw_packet_hdrlen(count); u8 own_tvlv_flags = bat_priv->mcast.mla_flags.tvlv_flags; if (!atomic_read(&bat_priv->mcast.num_no_mc_ptype_capa) && own_tvlv_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA && skb->len + mcast_hdrlen <= IPV6_MIN_MTU && batadv_mcast_forw_push(bat_priv, skb, vid, is_routable, count)) return BATADV_FORW_MCAST; if (count <= atomic_read(&bat_priv->multicast_fanout)) return BATADV_FORW_UCASTS; return BATADV_FORW_BCAST; } /** * batadv_mcast_forw_mode() - check on how to forward a multicast packet * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to check * @vid: the vlan identifier * @is_routable: stores whether the destination is routable * * Return: The forwarding mode as enum batadv_forw_mode. */ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int *is_routable) { int ret, tt_count, ip_count, unsnoop_count, total_count; bool is_unsnoopable = false; struct ethhdr *ethhdr; int rtr_count = 0; ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable, is_routable); if (ret == -ENOMEM) return BATADV_FORW_NONE; else if (ret < 0) return BATADV_FORW_BCAST; ethhdr = eth_hdr(skb); tt_count = batadv_tt_global_hash_count(bat_priv, ethhdr->h_dest, BATADV_NO_FLAGS); ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr); unsnoop_count = !is_unsnoopable ? 0 : atomic_read(&bat_priv->mcast.num_want_all_unsnoopables); rtr_count = batadv_mcast_forw_rtr_count(bat_priv, *is_routable); total_count = tt_count + ip_count + unsnoop_count + rtr_count; if (!total_count) return BATADV_FORW_NONE; else if (unsnoop_count) return BATADV_FORW_BCAST; return batadv_mcast_forw_mode_by_count(bat_priv, skb, vid, *is_routable, total_count); } /** * batadv_mcast_forw_send_orig() - send a multicast packet to an originator * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to send * @vid: the vlan identifier * @orig_node: the originator to send the packet to * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ static int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, struct batadv_orig_node *orig_node) { /* Avoid sending multicast-in-unicast packets to other BLA * gateways - they already got the frame from the LAN side * we share with them. * TODO: Refactor to take BLA into account earlier, to avoid * reducing the mcast_fanout count. */ if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { dev_kfree_skb(skb); return NET_XMIT_SUCCESS; } return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, orig_node, vid); } /** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any multicast * listener registered in the translation table. A transmission is performed * via a batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; struct batadv_tt_orig_list_entry *orig_entry; struct batadv_tt_global_entry *tt_global; const u8 *addr = eth_hdr(skb)->h_dest; tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global) goto out; rcu_read_lock(); hlist_for_each_entry_rcu(orig_entry, &tt_global->orig_list, list) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_entry->orig_node); } rcu_read_unlock(); batadv_tt_global_entry_put(tt_global); out: return ret; } /** * batadv_mcast_forw_want_all_ipv4() - forward to nodes with want-all-ipv4 * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV4 flag set. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_ipv4_list, mcast_want_all_ipv4_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all_ipv6() - forward to nodes with want-all-ipv6 * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV6 flag set. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_ipv6_list, mcast_want_all_ipv6_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all() - forward packet to nodes in a want-all list * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV4 or BATADV_MCAST_WANT_ALL_IPV6 flag set. A * transmission is performed via a batman-adv unicast packet for each such * destination node. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ static int batadv_mcast_forw_want_all(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_want_all_ipv4(bat_priv, skb, vid); case ETH_P_IPV6: return batadv_mcast_forw_want_all_ipv6(bat_priv, skb, vid); default: /* we shouldn't be here... */ return NET_XMIT_DROP; } } /** * batadv_mcast_forw_want_all_rtr4() - forward to nodes with want-all-rtr4 * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR4 flag unset. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_rtr4_list, mcast_want_all_rtr4_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all_rtr6() - forward to nodes with want-all-rtr6 * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR6 flag unset. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_rtr6_list, mcast_want_all_rtr6_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_rtr() - forward packet to nodes in a want-all-rtr list * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR4 or BATADV_MCAST_WANT_NO_RTR6 flag unset. A * transmission is performed via a batman-adv unicast packet for each such * destination node. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ static int batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_want_all_rtr4(bat_priv, skb, vid); case ETH_P_IPV6: return batadv_mcast_forw_want_all_rtr6(bat_priv, skb, vid); default: /* we shouldn't be here... */ return NET_XMIT_DROP; } } /** * batadv_mcast_forw_send() - send packet to any detected multicast recipient * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * @is_routable: stores whether the destination is routable * * Sends copies of a frame with multicast destination to any node that signaled * interest in it, that is either via the translation table or the according * want-all flags. A transmission is performed via a batman-adv unicast packet * for each such destination node. * * The given skb is consumed/freed. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int is_routable) { int ret; ret = batadv_mcast_forw_tt(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } ret = batadv_mcast_forw_want_all(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } if (!is_routable) goto skip_mc_router; ret = batadv_mcast_forw_want_rtr(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } skip_mc_router: consume_skb(skb); return ret; } /** * batadv_mcast_want_unsnoop_update() - update unsnoop counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator, * orig, has toggled then this method updates the counter and the list * accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_unsnoopables_node; struct hlist_head *head = &bat_priv->mcast.want_all_unsnoopables_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) { atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) { atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_ipv4_update() - update want-all-ipv4 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_ipv4_node; struct hlist_head *head = &bat_priv->mcast.want_all_ipv4_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) { atomic_dec(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_ipv6_update() - update want-all-ipv6 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_ipv6_node; struct hlist_head *head = &bat_priv->mcast.want_all_ipv6_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) { atomic_dec(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_rtr4_update() - update want-all-rtr4 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_NO_RTR4 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_rtr4_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_rtr4_node; struct hlist_head *head = &bat_priv->mcast.want_all_rtr4_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag set to unset */ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR4) && orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4) { atomic_inc(&bat_priv->mcast.num_want_all_rtr4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag unset to set */ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR4 && !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4)) { atomic_dec(&bat_priv->mcast.num_want_all_rtr4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_rtr6_update() - update want-all-rtr6 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_NO_RTR6 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_rtr6_node; struct hlist_head *head = &bat_priv->mcast.want_all_rtr6_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag set to unset */ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR6) && orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6) { atomic_inc(&bat_priv->mcast.num_want_all_rtr6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag unset to set */ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR6 && !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6)) { atomic_dec(&bat_priv->mcast.num_want_all_rtr6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_have_mc_ptype_update() - update multicast packet type counter * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_HAVE_MC_PTYPE_CAPA flag of this originator, orig, has * toggled then this method updates the counter accordingly. */ static void batadv_mcast_have_mc_ptype_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag set to unset */ if (!(mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) && orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) atomic_inc(&bat_priv->mcast.num_no_mc_ptype_capa); /* switched from flag unset to set */ else if (mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA && !(orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA)) atomic_dec(&bat_priv->mcast.num_no_mc_ptype_capa); } /** * batadv_mcast_tvlv_flags_get() - get multicast flags from an OGM TVLV * @enabled: whether the originator has multicast TVLV support enabled * @tvlv_value: tvlv buffer containing the multicast flags * @tvlv_value_len: tvlv buffer length * * Return: multicast flags for the given tvlv buffer */ static u8 batadv_mcast_tvlv_flags_get(bool enabled, void *tvlv_value, u16 tvlv_value_len) { u8 mcast_flags = BATADV_NO_FLAGS; if (enabled && tvlv_value && tvlv_value_len >= sizeof(mcast_flags)) mcast_flags = *(u8 *)tvlv_value; if (!enabled) { mcast_flags |= BATADV_MCAST_WANT_ALL_IPV4; mcast_flags |= BATADV_MCAST_WANT_ALL_IPV6; } /* remove redundant flags to avoid sending duplicate packets later */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) mcast_flags |= BATADV_MCAST_WANT_NO_RTR4; if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; return mcast_flags; } /** * batadv_mcast_tvlv_ogm_handler() - process incoming multicast tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the multicast data * @tvlv_value_len: tvlv buffer length */ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND); u8 mcast_flags; mcast_flags = batadv_mcast_tvlv_flags_get(orig_mcast_enabled, tvlv_value, tvlv_value_len); spin_lock_bh(&orig->mcast_handler_lock); if (orig_mcast_enabled && !test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } else if (!orig_mcast_enabled && test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { clear_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized); batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr6_update(bat_priv, orig, mcast_flags); batadv_mcast_have_mc_ptype_update(bat_priv, orig, mcast_flags); orig->mcast_flags = mcast_flags; spin_unlock_bh(&orig->mcast_handler_lock); } /** * batadv_mcast_init() - initialize the multicast optimizations structures * @bat_priv: the bat priv with all the soft interface information */ void batadv_mcast_init(struct batadv_priv *bat_priv) { batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, NULL, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_tvlv_handler_register(bat_priv, NULL, NULL, batadv_mcast_forw_tracker_tvlv_handler, BATADV_TVLV_MCAST_TRACKER, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); batadv_mcast_start_timer(bat_priv); } /** * batadv_mcast_mesh_info_put() - put multicast info into a netlink message * @msg: buffer for the message * @bat_priv: the bat priv with all the soft interface information * * Return: 0 or error code. */ int batadv_mcast_mesh_info_put(struct sk_buff *msg, struct batadv_priv *bat_priv) { u32 flags = bat_priv->mcast.mla_flags.tvlv_flags; u32 flags_priv = BATADV_NO_FLAGS; if (bat_priv->mcast.mla_flags.bridged) { flags_priv |= BATADV_MCAST_FLAGS_BRIDGED; if (bat_priv->mcast.mla_flags.querier_ipv4.exists) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS; if (bat_priv->mcast.mla_flags.querier_ipv6.exists) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS; if (bat_priv->mcast.mla_flags.querier_ipv4.shadowing) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING; if (bat_priv->mcast.mla_flags.querier_ipv6.shadowing) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING; } if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, flags) || nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS_PRIV, flags_priv)) return -EMSGSIZE; return 0; } /** * batadv_mcast_flags_dump_entry() - dump one entry of the multicast flags table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @orig_node: originator to dump the multicast flags of * * Return: 0 or error code. */ static int batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_orig_node *orig_node) { void *hdr; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_MCAST_FLAGS); if (!hdr) return -ENOBUFS; genl_dump_check_consistent(cb, hdr); if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig)) { genlmsg_cancel(msg, hdr); return -EMSGSIZE; } if (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig_node->capabilities)) { if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, orig_node->mcast_flags)) { genlmsg_cancel(msg, hdr); return -EMSGSIZE; } } genlmsg_end(msg, hdr); return 0; } /** * batadv_mcast_flags_dump_bucket() - dump one bucket of the multicast flags * table to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: 0 or error code. */ static int batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hashtable *hash, unsigned int bucket, long *idx_skip) { struct batadv_orig_node *orig_node; long idx = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(orig_node, &hash->table[bucket], hash_entry) { if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig_node->capa_initialized)) continue; if (idx < *idx_skip) goto skip; if (batadv_mcast_flags_dump_entry(msg, portid, cb, orig_node)) { spin_unlock_bh(&hash->list_locks[bucket]); *idx_skip = idx; return -EMSGSIZE; } skip: idx++; } spin_unlock_bh(&hash->list_locks[bucket]); return 0; } /** * __batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @bat_priv: the bat priv with all the soft interface information * @bucket: current bucket to dump * @idx: index in current bucket to the next entry to dump * * Return: 0 or error code. */ static int __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_priv *bat_priv, long *bucket, long *idx) { struct batadv_hashtable *hash = bat_priv->orig_hash; long bucket_tmp = *bucket; long idx_tmp = *idx; while (bucket_tmp < hash->size) { if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash, bucket_tmp, &idx_tmp)) break; bucket_tmp++; idx_tmp = 0; } *bucket = bucket_tmp; *idx = idx_tmp; return msg->len; } /** * batadv_mcast_netlink_get_primary() - get primary interface from netlink * callback * @cb: netlink callback structure * @primary_if: the primary interface pointer to return the result in * * Return: 0 or error code. */ static int batadv_mcast_netlink_get_primary(struct netlink_callback *cb, struct batadv_hard_iface **primary_if) { struct batadv_hard_iface *hard_iface = NULL; struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; int ifindex; int ret = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); hard_iface = batadv_primary_if_get_selected(bat_priv); if (!hard_iface || hard_iface->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } out: dev_put(soft_iface); if (!ret && primary_if) *primary_if = hard_iface; else batadv_hardif_put(hard_iface); return ret; } /** * batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct batadv_priv *bat_priv; long *bucket = &cb->args[0]; long *idx = &cb->args[1]; int ret; ret = batadv_mcast_netlink_get_primary(cb, &primary_if); if (ret) return ret; bat_priv = netdev_priv(primary_if->soft_iface); ret = __batadv_mcast_flags_dump(msg, portid, cb, bat_priv, bucket, idx); batadv_hardif_put(primary_if); return ret; } /** * batadv_mcast_free() - free the multicast optimizations structures * @bat_priv: the bat priv with all the soft interface information */ void batadv_mcast_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->mcast.work); batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2); /* safely calling outside of worker, as worker was canceled above */ batadv_mcast_mla_tt_retract(bat_priv, NULL); } /** * batadv_mcast_purge_orig() - reset originator global mcast state modifications * @orig: the originator which is going to get purged */ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) { struct batadv_priv *bat_priv = orig->bat_priv; spin_lock_bh(&orig->mcast_handler_lock); batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_MCAST_WANT_NO_RTR4); batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_MCAST_WANT_NO_RTR6); spin_unlock_bh(&orig->mcast_handler_lock); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Stream Parser * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #ifndef __NET_STRPARSER_H_ #define __NET_STRPARSER_H_ #include <linux/skbuff.h> #include <net/sock.h> #define STRP_STATS_ADD(stat, count) ((stat) += (count)) #define STRP_STATS_INCR(stat) ((stat)++) struct strp_stats { unsigned long long msgs; unsigned long long bytes; unsigned int mem_fail; unsigned int need_more_hdr; unsigned int msg_too_big; unsigned int msg_timeouts; unsigned int bad_hdr_len; }; struct strp_aggr_stats { unsigned long long msgs; unsigned long long bytes; unsigned int mem_fail; unsigned int need_more_hdr; unsigned int msg_too_big; unsigned int msg_timeouts; unsigned int bad_hdr_len; unsigned int aborts; unsigned int interrupted; unsigned int unrecov_intr; }; struct strparser; /* Callbacks are called with lock held for the attached socket */ struct strp_callbacks { int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); int (*read_sock_done)(struct strparser *strp, int err); void (*abort_parser)(struct strparser *strp, int err); void (*lock)(struct strparser *strp); void (*unlock)(struct strparser *strp); }; struct strp_msg { int full_len; int offset; }; struct _strp_msg { /* Internal cb structure. struct strp_msg must be first for passing * to upper layer. */ struct strp_msg strp; int accum_len; }; struct sk_skb_cb { #define SK_SKB_CB_PRIV_LEN 20 unsigned char data[SK_SKB_CB_PRIV_LEN]; /* align strp on cache line boundary within skb->cb[] */ unsigned char pad[4]; struct _strp_msg strp; /* strp users' data follows */ struct tls_msg { u8 control; } tls; /* temp_reg is a temporary register used for bpf_convert_data_end_access * when dst_reg == src_reg. */ u64 temp_reg; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) { return (struct strp_msg *)((void *)skb->cb + offsetof(struct sk_skb_cb, strp)); } /* Structure for an attached lower socket */ struct strparser { struct sock *sk; u32 stopped : 1; u32 paused : 1; u32 aborted : 1; u32 interrupted : 1; u32 unrecov_intr : 1; struct sk_buff **skb_nextp; struct sk_buff *skb_head; unsigned int need_bytes; struct delayed_work msg_timer_work; struct work_struct work; struct strp_stats stats; struct strp_callbacks cb; }; /* Must be called with lock held for attached socket */ static inline void strp_pause(struct strparser *strp) { strp->paused = 1; } /* May be called without holding lock for attached socket */ void strp_unpause(struct strparser *strp); /* Must be called with process lock held (lock_sock) */ void __strp_unpause(struct strparser *strp); static inline void save_strp_stats(struct strparser *strp, struct strp_aggr_stats *agg_stats) { /* Save psock statistics in the mux when psock is being unattached. */ #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += \ strp->stats._stat) SAVE_PSOCK_STATS(msgs); SAVE_PSOCK_STATS(bytes); SAVE_PSOCK_STATS(mem_fail); SAVE_PSOCK_STATS(need_more_hdr); SAVE_PSOCK_STATS(msg_too_big); SAVE_PSOCK_STATS(msg_timeouts); SAVE_PSOCK_STATS(bad_hdr_len); #undef SAVE_PSOCK_STATS if (strp->aborted) agg_stats->aborts++; if (strp->interrupted) agg_stats->interrupted++; if (strp->unrecov_intr) agg_stats->unrecov_intr++; } static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, struct strp_aggr_stats *agg_stats) { #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) SAVE_PSOCK_STATS(msgs); SAVE_PSOCK_STATS(bytes); SAVE_PSOCK_STATS(mem_fail); SAVE_PSOCK_STATS(need_more_hdr); SAVE_PSOCK_STATS(msg_too_big); SAVE_PSOCK_STATS(msg_timeouts); SAVE_PSOCK_STATS(bad_hdr_len); SAVE_PSOCK_STATS(aborts); SAVE_PSOCK_STATS(interrupted); SAVE_PSOCK_STATS(unrecov_intr); #undef SAVE_PSOCK_STATS } void strp_done(struct strparser *strp); void strp_stop(struct strparser *strp); void strp_check_rcv(struct strparser *strp); int strp_init(struct strparser *strp, struct sock *sk, const struct strp_callbacks *cb); void strp_data_ready(struct strparser *strp); int strp_process(struct strparser *strp, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo); #endif /* __NET_STRPARSER_H_ */ |
| 1588 1588 5 5 1559 1559 12955 12965 12949 12947 1980 1980 1980 759 42 1354 42 42 121 121 1249 1249 759 759 759 2692 2692 2692 2692 7493 7496 1615 1614 3280 3282 41 3236 2673 2673 480 480 3039 3039 3034 1085 1085 1087 2170 2171 2170 2013 1017 1141 612 2005 2004 2013 5853 5848 5847 5849 5850 5161 1071 1269 1259 1261 1262 1260 2823 2822 2615 1293 1291 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor LSM hooks. * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include <linux/lsm_hooks.h> #include <linux/moduleparam.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/ptrace.h> #include <linux/ctype.h> #include <linux/sysctl.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/zstd.h> #include <net/sock.h> #include <uapi/linux/mount.h> #include <uapi/linux/lsm.h> #include "include/apparmor.h" #include "include/apparmorfs.h" #include "include/audit.h" #include "include/capability.h" #include "include/cred.h" #include "include/file.h" #include "include/ipc.h" #include "include/net.h" #include "include/path.h" #include "include/label.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/procattr.h" #include "include/mount.h" #include "include/secid.h" /* Flag indicating whether initialization completed */ int apparmor_initialized; union aa_buffer { struct list_head list; DECLARE_FLEX_ARRAY(char, buffer); }; struct aa_local_cache { unsigned int hold; unsigned int count; struct list_head head; }; #define RESERVE_COUNT 2 static int reserve_count = RESERVE_COUNT; static int buffer_count; static LIST_HEAD(aa_global_buffers); static DEFINE_SPINLOCK(aa_buffers_lock); static DEFINE_PER_CPU(struct aa_local_cache, aa_local_buffers); /* * LSM hook functions */ /* * put the associated labels */ static void apparmor_cred_free(struct cred *cred) { aa_put_label(cred_label(cred)); set_cred_label(cred, NULL); } /* * allocate the apparmor part of blank credentials */ static int apparmor_cred_alloc_blank(struct cred *cred, gfp_t gfp) { set_cred_label(cred, NULL); return 0; } /* * prepare new cred label for modification by prepare_cred block */ static int apparmor_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { set_cred_label(new, aa_get_newest_label(cred_label(old))); return 0; } /* * transfer the apparmor data to a blank set of creds */ static void apparmor_cred_transfer(struct cred *new, const struct cred *old) { set_cred_label(new, aa_get_newest_label(cred_label(old))); } static void apparmor_task_free(struct task_struct *task) { aa_free_task_ctx(task_ctx(task)); } static int apparmor_task_alloc(struct task_struct *task, unsigned long clone_flags) { struct aa_task_ctx *new = task_ctx(task); aa_dup_task_ctx(new, task_ctx(current)); return 0; } static int apparmor_ptrace_access_check(struct task_struct *child, unsigned int mode) { struct aa_label *tracer, *tracee; const struct cred *cred; int error; cred = get_task_cred(child); tracee = cred_label(cred); /* ref count on cred */ tracer = __begin_current_label_crit_section(); error = aa_may_ptrace(current_cred(), tracer, cred, tracee, (mode & PTRACE_MODE_READ) ? AA_PTRACE_READ : AA_PTRACE_TRACE); __end_current_label_crit_section(tracer); put_cred(cred); return error; } static int apparmor_ptrace_traceme(struct task_struct *parent) { struct aa_label *tracer, *tracee; const struct cred *cred; int error; tracee = __begin_current_label_crit_section(); cred = get_task_cred(parent); tracer = cred_label(cred); /* ref count on cred */ error = aa_may_ptrace(cred, tracer, current_cred(), tracee, AA_PTRACE_TRACE); put_cred(cred); __end_current_label_crit_section(tracee); return error; } /* Derived from security/commoncap.c:cap_capget */ static int apparmor_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { struct aa_label *label; const struct cred *cred; rcu_read_lock(); cred = __task_cred(target); label = aa_get_newest_cred_label(cred); /* * cap_capget is stacked ahead of this and will * initialize effective and permitted. */ if (!unconfined(label)) { struct aa_profile *profile; struct label_it i; label_for_each_confined(i, label, profile) { struct aa_ruleset *rules; if (COMPLAIN_MODE(profile)) continue; rules = list_first_entry(&profile->rules, typeof(*rules), list); *effective = cap_intersect(*effective, rules->caps.allow); *permitted = cap_intersect(*permitted, rules->caps.allow); } } rcu_read_unlock(); aa_put_label(label); return 0; } static int apparmor_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { struct aa_label *label; int error = 0; label = aa_get_newest_cred_label(cred); if (!unconfined(label)) error = aa_capable(cred, label, cap, opts); aa_put_label(label); return error; } /** * common_perm - basic common permission check wrapper fn for paths * @op: operation being checked * @path: path to check permission of (NOT NULL) * @mask: requested permissions mask * @cond: conditional info for the permission request (NOT NULL) * * Returns: %0 else error code if error or permission denied */ static int common_perm(const char *op, const struct path *path, u32 mask, struct path_cond *cond) { struct aa_label *label; int error = 0; label = __begin_current_label_crit_section(); if (!unconfined(label)) error = aa_path_perm(op, current_cred(), label, path, 0, mask, cond); __end_current_label_crit_section(label); return error; } /** * common_perm_cond - common permission wrapper around inode cond * @op: operation being checked * @path: location to check (NOT NULL) * @mask: requested permissions mask * * Returns: %0 else error code if error or permission denied */ static int common_perm_cond(const char *op, const struct path *path, u32 mask) { vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(path->mnt), d_backing_inode(path->dentry)); struct path_cond cond = { vfsuid_into_kuid(vfsuid), d_backing_inode(path->dentry)->i_mode }; if (!path_mediated_fs(path->dentry)) return 0; return common_perm(op, path, mask, &cond); } /** * common_perm_dir_dentry - common permission wrapper when path is dir, dentry * @op: operation being checked * @dir: directory of the dentry (NOT NULL) * @dentry: dentry to check (NOT NULL) * @mask: requested permissions mask * @cond: conditional info for the permission request (NOT NULL) * * Returns: %0 else error code if error or permission denied */ static int common_perm_dir_dentry(const char *op, const struct path *dir, struct dentry *dentry, u32 mask, struct path_cond *cond) { struct path path = { .mnt = dir->mnt, .dentry = dentry }; return common_perm(op, &path, mask, cond); } /** * common_perm_rm - common permission wrapper for operations doing rm * @op: operation being checked * @dir: directory that the dentry is in (NOT NULL) * @dentry: dentry being rm'd (NOT NULL) * @mask: requested permission mask * * Returns: %0 else error code if error or permission denied */ static int common_perm_rm(const char *op, const struct path *dir, struct dentry *dentry, u32 mask) { struct inode *inode = d_backing_inode(dentry); struct path_cond cond = { }; vfsuid_t vfsuid; if (!inode || !path_mediated_fs(dentry)) return 0; vfsuid = i_uid_into_vfsuid(mnt_idmap(dir->mnt), inode); cond.uid = vfsuid_into_kuid(vfsuid); cond.mode = inode->i_mode; return common_perm_dir_dentry(op, dir, dentry, mask, &cond); } /** * common_perm_create - common permission wrapper for operations doing create * @op: operation being checked * @dir: directory that dentry will be created in (NOT NULL) * @dentry: dentry to create (NOT NULL) * @mask: request permission mask * @mode: created file mode * * Returns: %0 else error code if error or permission denied */ static int common_perm_create(const char *op, const struct path *dir, struct dentry *dentry, u32 mask, umode_t mode) { struct path_cond cond = { current_fsuid(), mode }; if (!path_mediated_fs(dir->dentry)) return 0; return common_perm_dir_dentry(op, dir, dentry, mask, &cond); } static int apparmor_path_unlink(const struct path *dir, struct dentry *dentry) { return common_perm_rm(OP_UNLINK, dir, dentry, AA_MAY_DELETE); } static int apparmor_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { return common_perm_create(OP_MKDIR, dir, dentry, AA_MAY_CREATE, S_IFDIR); } static int apparmor_path_rmdir(const struct path *dir, struct dentry *dentry) { return common_perm_rm(OP_RMDIR, dir, dentry, AA_MAY_DELETE); } static int apparmor_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { return common_perm_create(OP_MKNOD, dir, dentry, AA_MAY_CREATE, mode); } static int apparmor_path_truncate(const struct path *path) { return common_perm_cond(OP_TRUNC, path, MAY_WRITE | AA_MAY_SETATTR); } static int apparmor_file_truncate(struct file *file) { return apparmor_path_truncate(&file->f_path); } static int apparmor_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { return common_perm_create(OP_SYMLINK, dir, dentry, AA_MAY_CREATE, S_IFLNK); } static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct aa_label *label; int error = 0; if (!path_mediated_fs(old_dentry)) return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) error = aa_path_link(current_cred(), label, old_dentry, new_dir, new_dentry); end_current_label_crit_section(label); return error; } static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, const unsigned int flags) { struct aa_label *label; int error = 0; if (!path_mediated_fs(old_dentry)) return 0; if ((flags & RENAME_EXCHANGE) && !path_mediated_fs(new_dentry)) return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) { struct mnt_idmap *idmap = mnt_idmap(old_dir->mnt); vfsuid_t vfsuid; struct path old_path = { .mnt = old_dir->mnt, .dentry = old_dentry }; struct path new_path = { .mnt = new_dir->mnt, .dentry = new_dentry }; struct path_cond cond = { .mode = d_backing_inode(old_dentry)->i_mode }; vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond.uid = vfsuid_into_kuid(vfsuid); if (flags & RENAME_EXCHANGE) { struct path_cond cond_exchange = { .mode = d_backing_inode(new_dentry)->i_mode, }; vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond_exchange.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_RENAME_SRC, current_cred(), label, &new_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond_exchange); if (!error) error = aa_path_perm(OP_RENAME_DEST, current_cred(), label, &old_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond_exchange); } if (!error) error = aa_path_perm(OP_RENAME_SRC, current_cred(), label, &old_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond); if (!error) error = aa_path_perm(OP_RENAME_DEST, current_cred(), label, &new_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond); } end_current_label_crit_section(label); return error; } static int apparmor_path_chmod(const struct path *path, umode_t mode) { return common_perm_cond(OP_CHMOD, path, AA_MAY_CHMOD); } static int apparmor_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { return common_perm_cond(OP_CHOWN, path, AA_MAY_CHOWN); } static int apparmor_inode_getattr(const struct path *path) { return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR); } static int apparmor_file_open(struct file *file) { struct aa_file_ctx *fctx = file_ctx(file); struct aa_label *label; int error = 0; if (!path_mediated_fs(file->f_path.dentry)) return 0; /* If in exec, permission is handled by bprm hooks. * Cache permissions granted by the previous exec check, with * implicit read and executable mmap which are required to * actually execute the image. * * Illogically, FMODE_EXEC is in f_flags, not f_mode. */ if (file->f_flags & __FMODE_EXEC) { fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP; return 0; } label = aa_get_newest_cred_label(file->f_cred); if (!unconfined(label)) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); vfsuid_t vfsuid; struct path_cond cond = { .mode = inode->i_mode, }; vfsuid = i_uid_into_vfsuid(idmap, inode); cond.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_OPEN, file->f_cred, label, &file->f_path, 0, aa_map_file_to_perms(file), &cond); /* todo cache full allowed permissions set and state */ fctx->allow = aa_map_file_to_perms(file); } aa_put_label(label); return error; } static int apparmor_file_alloc_security(struct file *file) { struct aa_file_ctx *ctx = file_ctx(file); struct aa_label *label = begin_current_label_crit_section(); spin_lock_init(&ctx->lock); rcu_assign_pointer(ctx->label, aa_get_label(label)); end_current_label_crit_section(label); return 0; } static void apparmor_file_free_security(struct file *file) { struct aa_file_ctx *ctx = file_ctx(file); if (ctx) aa_put_label(rcu_access_pointer(ctx->label)); } static int common_file_perm(const char *op, struct file *file, u32 mask, bool in_atomic) { struct aa_label *label; int error = 0; /* don't reaudit files closed during inheritance */ if (file->f_path.dentry == aa_null.dentry) return -EACCES; label = __begin_current_label_crit_section(); error = aa_file_perm(op, current_cred(), label, file, mask, in_atomic); __end_current_label_crit_section(label); return error; } static int apparmor_file_receive(struct file *file) { return common_file_perm(OP_FRECEIVE, file, aa_map_file_to_perms(file), false); } static int apparmor_file_permission(struct file *file, int mask) { return common_file_perm(OP_FPERM, file, mask, false); } static int apparmor_file_lock(struct file *file, unsigned int cmd) { u32 mask = AA_MAY_LOCK; if (cmd == F_WRLCK) mask |= MAY_WRITE; return common_file_perm(OP_FLOCK, file, mask, false); } static int common_mmap(const char *op, struct file *file, unsigned long prot, unsigned long flags, bool in_atomic) { int mask = 0; if (!file || !file_ctx(file)) return 0; if (prot & PROT_READ) mask |= MAY_READ; /* * Private mappings don't require write perms since they don't * write back to the files */ if ((prot & PROT_WRITE) && !(flags & MAP_PRIVATE)) mask |= MAY_WRITE; if (prot & PROT_EXEC) mask |= AA_EXEC_MMAP; return common_file_perm(op, file, mask, in_atomic); } static int apparmor_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return common_mmap(OP_FMMAP, file, prot, flags, GFP_ATOMIC); } static int apparmor_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return common_mmap(OP_FMPROT, vma->vm_file, prot, !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0, false); } #ifdef CONFIG_IO_URING static const char *audit_uring_mask(u32 mask) { if (mask & AA_MAY_CREATE_SQPOLL) return "sqpoll"; if (mask & AA_MAY_OVERRIDE_CRED) return "override_creds"; return ""; } static void audit_uring_cb(struct audit_buffer *ab, void *va) { struct apparmor_audit_data *ad = aad_of_va(va); if (ad->request & AA_URING_PERM_MASK) { audit_log_format(ab, " requested=\"%s\"", audit_uring_mask(ad->request)); if (ad->denied & AA_URING_PERM_MASK) { audit_log_format(ab, " denied=\"%s\"", audit_uring_mask(ad->denied)); } } if (ad->uring.target) { audit_log_format(ab, " tcontext="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->uring.target, FLAGS_NONE, GFP_ATOMIC); } } static int profile_uring(struct aa_profile *profile, u32 request, struct aa_label *new, int cap, struct apparmor_audit_data *ad) { unsigned int state; struct aa_ruleset *rules; int error = 0; AA_BUG(!profile); rules = list_first_entry(&profile->rules, typeof(*rules), list); state = RULE_MEDIATES(rules, AA_CLASS_IO_URING); if (state) { struct aa_perms perms = { }; if (new) { aa_label_match(profile, rules, new, state, false, request, &perms); } else { perms = *aa_lookup_perms(rules->policy, state); } aa_apply_modes_to_perms(profile, &perms); error = aa_check_perms(profile, &perms, request, ad, audit_uring_cb); } return error; } /** * apparmor_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int apparmor_uring_override_creds(const struct cred *new) { struct aa_profile *profile; struct aa_label *label; int error; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING, OP_URING_OVERRIDE); ad.uring.target = cred_label(new); label = __begin_current_label_crit_section(); error = fn_for_each(label, profile, profile_uring(profile, AA_MAY_OVERRIDE_CRED, cred_label(new), CAP_SYS_ADMIN, &ad)); __end_current_label_crit_section(label); return error; } /** * apparmor_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int apparmor_uring_sqpoll(void) { struct aa_profile *profile; struct aa_label *label; int error; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING, OP_URING_SQPOLL); label = __begin_current_label_crit_section(); error = fn_for_each(label, profile, profile_uring(profile, AA_MAY_CREATE_SQPOLL, NULL, CAP_SYS_ADMIN, &ad)); __end_current_label_crit_section(label); return error; } #endif /* CONFIG_IO_URING */ static int apparmor_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { struct aa_label *label; int error = 0; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; flags &= ~AA_MS_IGNORE_MASK; label = __begin_current_label_crit_section(); if (!unconfined(label)) { if (flags & MS_REMOUNT) error = aa_remount(current_cred(), label, path, flags, data); else if (flags & MS_BIND) error = aa_bind_mount(current_cred(), label, path, dev_name, flags); else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) error = aa_mount_change_type(current_cred(), label, path, flags); else if (flags & MS_MOVE) error = aa_move_mount_old(current_cred(), label, path, dev_name); else error = aa_new_mount(current_cred(), label, dev_name, path, type, flags, data); } __end_current_label_crit_section(label); return error; } static int apparmor_move_mount(const struct path *from_path, const struct path *to_path) { struct aa_label *label; int error = 0; label = __begin_current_label_crit_section(); if (!unconfined(label)) error = aa_move_mount(current_cred(), label, from_path, to_path); __end_current_label_crit_section(label); return error; } static int apparmor_sb_umount(struct vfsmount *mnt, int flags) { struct aa_label *label; int error = 0; label = __begin_current_label_crit_section(); if (!unconfined(label)) error = aa_umount(current_cred(), label, mnt, flags); __end_current_label_crit_section(label); return error; } static int apparmor_sb_pivotroot(const struct path *old_path, const struct path *new_path) { struct aa_label *label; int error = 0; label = aa_get_current_label(); if (!unconfined(label)) error = aa_pivotroot(current_cred(), label, old_path, new_path); aa_put_label(label); return error; } static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx, size_t *size, u32 flags) { int error = -ENOENT; struct aa_task_ctx *ctx = task_ctx(current); struct aa_label *label = NULL; char *value; switch (attr) { case LSM_ATTR_CURRENT: label = aa_get_newest_label(cred_label(current_cred())); break; case LSM_ATTR_PREV: if (ctx->previous) label = aa_get_newest_label(ctx->previous); break; case LSM_ATTR_EXEC: if (ctx->onexec) label = aa_get_newest_label(ctx->onexec); break; default: error = -EOPNOTSUPP; break; } if (label) { error = aa_getprocattr(label, &value, false); if (error > 0) error = lsm_fill_user_ctx(lx, size, value, error, LSM_ID_APPARMOR, 0); kfree(value); } aa_put_label(label); if (error < 0) return error; return 1; } static int apparmor_getprocattr(struct task_struct *task, const char *name, char **value) { int error = -ENOENT; /* released below */ const struct cred *cred = get_task_cred(task); struct aa_task_ctx *ctx = task_ctx(current); struct aa_label *label = NULL; if (strcmp(name, "current") == 0) label = aa_get_newest_label(cred_label(cred)); else if (strcmp(name, "prev") == 0 && ctx->previous) label = aa_get_newest_label(ctx->previous); else if (strcmp(name, "exec") == 0 && ctx->onexec) label = aa_get_newest_label(ctx->onexec); else error = -EINVAL; if (label) error = aa_getprocattr(label, value, true); aa_put_label(label); put_cred(cred); return error; } static int do_setattr(u64 attr, void *value, size_t size) { char *command, *largs = NULL, *args = value; size_t arg_size; int error; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, OP_SETPROCATTR); if (size == 0) return -EINVAL; /* AppArmor requires that the buffer must be null terminated atm */ if (args[size - 1] != '\0') { /* null terminate */ largs = args = kmalloc(size + 1, GFP_KERNEL); if (!args) return -ENOMEM; memcpy(args, value, size); args[size] = '\0'; } error = -EINVAL; args = strim(args); command = strsep(&args, " "); if (!args) goto out; args = skip_spaces(args); if (!*args) goto out; arg_size = size - (args - (largs ? largs : (char *) value)); if (attr == LSM_ATTR_CURRENT) { if (strcmp(command, "changehat") == 0) { error = aa_setprocattr_changehat(args, arg_size, AA_CHANGE_NOFLAGS); } else if (strcmp(command, "permhat") == 0) { error = aa_setprocattr_changehat(args, arg_size, AA_CHANGE_TEST); } else if (strcmp(command, "changeprofile") == 0) { error = aa_change_profile(args, AA_CHANGE_NOFLAGS); } else if (strcmp(command, "permprofile") == 0) { error = aa_change_profile(args, AA_CHANGE_TEST); } else if (strcmp(command, "stack") == 0) { error = aa_change_profile(args, AA_CHANGE_STACK); } else goto fail; } else if (attr == LSM_ATTR_EXEC) { if (strcmp(command, "exec") == 0) error = aa_change_profile(args, AA_CHANGE_ONEXEC); else if (strcmp(command, "stack") == 0) error = aa_change_profile(args, (AA_CHANGE_ONEXEC | AA_CHANGE_STACK)); else goto fail; } else /* only support the "current" and "exec" process attributes */ goto fail; if (!error) error = size; out: kfree(largs); return error; fail: ad.subj_label = begin_current_label_crit_section(); if (attr == LSM_ATTR_CURRENT) ad.info = "current"; else if (attr == LSM_ATTR_EXEC) ad.info = "exec"; else ad.info = "invalid"; ad.error = error = -EINVAL; aa_audit_msg(AUDIT_APPARMOR_DENIED, &ad, NULL); end_current_label_crit_section(ad.subj_label); goto out; } static int apparmor_setselfattr(unsigned int attr, struct lsm_ctx *ctx, size_t size, u32 flags) { int rc; if (attr != LSM_ATTR_CURRENT && attr != LSM_ATTR_EXEC) return -EOPNOTSUPP; rc = do_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int apparmor_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return do_setattr(attr, value, size); return -EINVAL; } /** * apparmor_bprm_committing_creds - do task cleanup on committing new creds * @bprm: binprm for the exec (NOT NULL) */ static void apparmor_bprm_committing_creds(const struct linux_binprm *bprm) { struct aa_label *label = aa_current_raw_label(); struct aa_label *new_label = cred_label(bprm->cred); /* bail out if unconfined or not changing profile */ if ((new_label->proxy == label->proxy) || (unconfined(new_label))) return; aa_inherit_files(bprm->cred, current->files); current->pdeath_signal = 0; /* reset soft limits and set hard limits for the new label */ __aa_transition_rlimits(label, new_label); } /** * apparmor_bprm_committed_creds() - do cleanup after new creds committed * @bprm: binprm for the exec (NOT NULL) */ static void apparmor_bprm_committed_creds(const struct linux_binprm *bprm) { /* clear out temporary/transitional state from the context */ aa_clear_task_ctx_trans(task_ctx(current)); return; } static void apparmor_current_getsecid_subj(u32 *secid) { struct aa_label *label = __begin_current_label_crit_section(); *secid = label->secid; __end_current_label_crit_section(label); } static void apparmor_task_getsecid_obj(struct task_struct *p, u32 *secid) { struct aa_label *label = aa_get_task_label(p); *secid = label->secid; aa_put_label(label); } static int apparmor_task_setrlimit(struct task_struct *task, unsigned int resource, struct rlimit *new_rlim) { struct aa_label *label = __begin_current_label_crit_section(); int error = 0; if (!unconfined(label)) error = aa_task_setrlimit(current_cred(), label, task, resource, new_rlim); __end_current_label_crit_section(label); return error; } static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo *info, int sig, const struct cred *cred) { const struct cred *tc; struct aa_label *cl, *tl; int error; tc = get_task_cred(target); tl = aa_get_newest_cred_label(tc); if (cred) { /* * Dealing with USB IO specific behavior */ cl = aa_get_newest_cred_label(cred); error = aa_may_signal(cred, cl, tc, tl, sig); aa_put_label(cl); } else { cl = __begin_current_label_crit_section(); error = aa_may_signal(current_cred(), cl, tc, tl, sig); __end_current_label_crit_section(cl); } aa_put_label(tl); put_cred(tc); return error; } static int apparmor_userns_create(const struct cred *cred) { struct aa_label *label; struct aa_profile *profile; int error = 0; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_NS, OP_USERNS_CREATE); ad.subj_cred = current_cred(); label = begin_current_label_crit_section(); if (!unconfined(label)) { error = fn_for_each(label, profile, aa_profile_ns_perm(profile, &ad, AA_USERNS_CREATE)); } end_current_label_crit_section(label); return error; } static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) { struct aa_sk_ctx *ctx; ctx = kzalloc(sizeof(*ctx), flags); if (!ctx) return -ENOMEM; sk->sk_security = ctx; return 0; } static void apparmor_sk_free_security(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); sk->sk_security = NULL; aa_put_label(ctx->label); aa_put_label(ctx->peer); kfree(ctx); } /** * apparmor_sk_clone_security - clone the sk_security field * @sk: sock to have security cloned * @newsk: sock getting clone */ static void apparmor_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct aa_sk_ctx *ctx = aa_sock(sk); struct aa_sk_ctx *new = aa_sock(newsk); if (new->label) aa_put_label(new->label); new->label = aa_get_label(ctx->label); if (new->peer) aa_put_label(new->peer); new->peer = aa_get_label(ctx->peer); } static int apparmor_socket_create(int family, int type, int protocol, int kern) { struct aa_label *label; int error = 0; AA_BUG(in_interrupt()); label = begin_current_label_crit_section(); if (!(kern || unconfined(label))) error = af_select(family, create_perm(label, family, type, protocol), aa_af_perm(current_cred(), label, OP_CREATE, AA_MAY_CREATE, family, type, protocol)); end_current_label_crit_section(label); return error; } /** * apparmor_socket_post_create - setup the per-socket security struct * @sock: socket that is being setup * @family: family of socket being created * @type: type of the socket * @ptotocol: protocol of the socket * @kern: socket is a special kernel socket * * Note: * - kernel sockets labeled kernel_t used to use unconfined * - socket may not have sk here if created with sock_create_lite or * sock_alloc. These should be accept cases which will be handled in * sock_graft. */ static int apparmor_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { struct aa_label *label; if (kern) { label = aa_get_label(kernel_t); } else label = aa_get_current_label(); if (sock->sk) { struct aa_sk_ctx *ctx = aa_sock(sock->sk); aa_put_label(ctx->label); ctx->label = aa_get_label(label); } aa_put_label(label); return 0; } static int apparmor_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!address); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, bind_perm(sock, address, addrlen), aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk)); } static int apparmor_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!address); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, connect_perm(sock, address, addrlen), aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk)); } static int apparmor_socket_listen(struct socket *sock, int backlog) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, listen_perm(sock, backlog), aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk)); } /* * Note: while @newsock is created and has some information, the accept * has not been done. */ static int apparmor_socket_accept(struct socket *sock, struct socket *newsock) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!newsock); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, accept_perm(sock, newsock), aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk)); } static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, struct msghdr *msg, int size) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!msg); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, msg_perm(op, request, sock, msg, size), aa_sk_perm(op, request, sock->sk)); } static int apparmor_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); } static int apparmor_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size); } /* revaliation, get/set attr, shutdown */ static int aa_sock_perm(const char *op, u32 request, struct socket *sock) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, sock_perm(op, request, sock), aa_sk_perm(op, request, sock->sk)); } static int apparmor_socket_getsockname(struct socket *sock) { return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock); } static int apparmor_socket_getpeername(struct socket *sock) { return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock); } /* revaliation, get/set attr, opt */ static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock, int level, int optname) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); return af_select(sock->sk->sk_family, opt_perm(op, request, sock, level, optname), aa_sk_perm(op, request, sock->sk)); } static int apparmor_socket_getsockopt(struct socket *sock, int level, int optname) { return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock, level, optname); } static int apparmor_socket_setsockopt(struct socket *sock, int level, int optname) { return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock, level, optname); } static int apparmor_socket_shutdown(struct socket *sock, int how) { return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); } #ifdef CONFIG_NETWORK_SECMARK /** * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk * @sk: sk to associate @skb with * @skb: skb to check for perms * * Note: can not sleep may be called with locks held * * dont want protocol specific in __skb_recv_datagram() * to deny an incoming connection socket_sock_rcv_skb() */ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct aa_sk_ctx *ctx = aa_sock(sk); if (!skb->secmark) return 0; return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE, skb->secmark, sk); } #endif static struct aa_label *sk_peer_label(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); if (ctx->peer) return ctx->peer; return ERR_PTR(-ENOPROTOOPT); } /** * apparmor_socket_getpeersec_stream - get security context of peer * @sock: socket that we are trying to get the peer context of * @optval: output - buffer to copy peer name to * @optlen: output - size of copied name in @optval * @len: size of @optval buffer * Returns: 0 on success, -errno of failure * * Note: for tcp only valid if using ipsec or cipso on lan */ static int apparmor_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { char *name = NULL; int slen, error = 0; struct aa_label *label; struct aa_label *peer; label = begin_current_label_crit_section(); peer = sk_peer_label(sock->sk); if (IS_ERR(peer)) { error = PTR_ERR(peer); goto done; } slen = aa_label_asxprint(&name, labels_ns(label), peer, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED, GFP_KERNEL); /* don't include terminating \0 in slen, it breaks some apps */ if (slen < 0) { error = -ENOMEM; goto done; } if (slen > len) { error = -ERANGE; goto done_len; } if (copy_to_sockptr(optval, name, slen)) error = -EFAULT; done_len: if (copy_to_sockptr(optlen, &slen, sizeof(slen))) error = -EFAULT; done: end_current_label_crit_section(label); kfree(name); return error; } /** * apparmor_socket_getpeersec_dgram - get security label of packet * @sock: the peer socket * @skb: packet data * @secid: pointer to where to put the secid of the packet * * Sets the netlabel socket state on sk from parent */ static int apparmor_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { /* TODO: requires secid support */ return -ENOPROTOOPT; } /** * apparmor_sock_graft - Initialize newly created socket * @sk: child sock * @parent: parent socket * * Note: could set off of SOCK_CTX(parent) but need to track inode and we can * just set sk security information off of current creating process label * Labeling of sk for accept case - probably should be sock based * instead of task, because of the case where an implicitly labeled * socket is shared by different tasks. */ static void apparmor_sock_graft(struct sock *sk, struct socket *parent) { struct aa_sk_ctx *ctx = aa_sock(sk); if (!ctx->label) ctx->label = aa_get_current_label(); } #ifdef CONFIG_NETWORK_SECMARK static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct aa_sk_ctx *ctx = aa_sock(sk); if (!skb->secmark) return 0; return apparmor_secmark_check(ctx->label, OP_CONNECT, AA_MAY_CONNECT, skb->secmark, sk); } #endif /* * The cred blob is a pointer to, not an instance of, an aa_label. */ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct aa_label *), .lbs_file = sizeof(struct aa_file_ctx), .lbs_task = sizeof(struct aa_task_ctx), }; static const struct lsm_id apparmor_lsmid = { .name = "apparmor", .id = LSM_ID_APPARMOR, }; static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), LSM_HOOK_INIT(capget, apparmor_capget), LSM_HOOK_INIT(capable, apparmor_capable), LSM_HOOK_INIT(move_mount, apparmor_move_mount), LSM_HOOK_INIT(sb_mount, apparmor_sb_mount), LSM_HOOK_INIT(sb_umount, apparmor_sb_umount), LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot), LSM_HOOK_INIT(path_link, apparmor_path_link), LSM_HOOK_INIT(path_unlink, apparmor_path_unlink), LSM_HOOK_INIT(path_symlink, apparmor_path_symlink), LSM_HOOK_INIT(path_mkdir, apparmor_path_mkdir), LSM_HOOK_INIT(path_rmdir, apparmor_path_rmdir), LSM_HOOK_INIT(path_mknod, apparmor_path_mknod), LSM_HOOK_INIT(path_rename, apparmor_path_rename), LSM_HOOK_INIT(path_chmod, apparmor_path_chmod), LSM_HOOK_INIT(path_chown, apparmor_path_chown), LSM_HOOK_INIT(path_truncate, apparmor_path_truncate), LSM_HOOK_INIT(inode_getattr, apparmor_inode_getattr), LSM_HOOK_INIT(file_open, apparmor_file_open), LSM_HOOK_INIT(file_receive, apparmor_file_receive), LSM_HOOK_INIT(file_permission, apparmor_file_permission), LSM_HOOK_INIT(file_alloc_security, apparmor_file_alloc_security), LSM_HOOK_INIT(file_free_security, apparmor_file_free_security), LSM_HOOK_INIT(mmap_file, apparmor_mmap_file), LSM_HOOK_INIT(file_mprotect, apparmor_file_mprotect), LSM_HOOK_INIT(file_lock, apparmor_file_lock), LSM_HOOK_INIT(file_truncate, apparmor_file_truncate), LSM_HOOK_INIT(getselfattr, apparmor_getselfattr), LSM_HOOK_INIT(setselfattr, apparmor_setselfattr), LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), LSM_HOOK_INIT(socket_create, apparmor_socket_create), LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create), LSM_HOOK_INIT(socket_bind, apparmor_socket_bind), LSM_HOOK_INIT(socket_connect, apparmor_socket_connect), LSM_HOOK_INIT(socket_listen, apparmor_socket_listen), LSM_HOOK_INIT(socket_accept, apparmor_socket_accept), LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown), #ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb), #endif LSM_HOOK_INIT(socket_getpeersec_stream, apparmor_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, apparmor_socket_getpeersec_dgram), LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), #ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(inet_conn_request, apparmor_inet_conn_request), #endif LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank), LSM_HOOK_INIT(cred_free, apparmor_cred_free), LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare), LSM_HOOK_INIT(cred_transfer, apparmor_cred_transfer), LSM_HOOK_INIT(bprm_creds_for_exec, apparmor_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, apparmor_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds), LSM_HOOK_INIT(task_free, apparmor_task_free), LSM_HOOK_INIT(task_alloc, apparmor_task_alloc), LSM_HOOK_INIT(current_getsecid_subj, apparmor_current_getsecid_subj), LSM_HOOK_INIT(task_getsecid_obj, apparmor_task_getsecid_obj), LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit), LSM_HOOK_INIT(task_kill, apparmor_task_kill), LSM_HOOK_INIT(userns_create, apparmor_userns_create), #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, aa_audit_rule_init), LSM_HOOK_INIT(audit_rule_known, aa_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, aa_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, aa_audit_rule_free), #endif LSM_HOOK_INIT(secid_to_secctx, apparmor_secid_to_secctx), LSM_HOOK_INIT(secctx_to_secid, apparmor_secctx_to_secid), LSM_HOOK_INIT(release_secctx, apparmor_release_secctx), #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, apparmor_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, apparmor_uring_sqpoll), #endif }; /* * AppArmor sysfs module parameters */ static int param_set_aabool(const char *val, const struct kernel_param *kp); static int param_get_aabool(char *buffer, const struct kernel_param *kp); #define param_check_aabool param_check_bool static const struct kernel_param_ops param_ops_aabool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aabool, .get = param_get_aabool }; static int param_set_aauint(const char *val, const struct kernel_param *kp); static int param_get_aauint(char *buffer, const struct kernel_param *kp); #define param_check_aauint param_check_uint static const struct kernel_param_ops param_ops_aauint = { .set = param_set_aauint, .get = param_get_aauint }; static int param_set_aacompressionlevel(const char *val, const struct kernel_param *kp); static int param_get_aacompressionlevel(char *buffer, const struct kernel_param *kp); #define param_check_aacompressionlevel param_check_int static const struct kernel_param_ops param_ops_aacompressionlevel = { .set = param_set_aacompressionlevel, .get = param_get_aacompressionlevel }; static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp); static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp); #define param_check_aalockpolicy param_check_bool static const struct kernel_param_ops param_ops_aalockpolicy = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aalockpolicy, .get = param_get_aalockpolicy }; static int param_set_audit(const char *val, const struct kernel_param *kp); static int param_get_audit(char *buffer, const struct kernel_param *kp); static int param_set_mode(const char *val, const struct kernel_param *kp); static int param_get_mode(char *buffer, const struct kernel_param *kp); /* Flag values, also controllable via /sys/module/apparmor/parameters * We define special types as we want to do additional mediation. */ /* AppArmor global enforcement switch - complain, enforce, kill */ enum profile_mode aa_g_profile_mode = APPARMOR_ENFORCE; module_param_call(mode, param_set_mode, param_get_mode, &aa_g_profile_mode, S_IRUSR | S_IWUSR); /* whether policy verification hashing is enabled */ bool aa_g_hash_policy = IS_ENABLED(CONFIG_SECURITY_APPARMOR_HASH_DEFAULT); #ifdef CONFIG_SECURITY_APPARMOR_HASH module_param_named(hash_policy, aa_g_hash_policy, aabool, S_IRUSR | S_IWUSR); #endif /* whether policy exactly as loaded is retained for debug and checkpointing */ bool aa_g_export_binary = IS_ENABLED(CONFIG_SECURITY_APPARMOR_EXPORT_BINARY); #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY module_param_named(export_binary, aa_g_export_binary, aabool, 0600); #endif /* policy loaddata compression level */ int aa_g_rawdata_compression_level = AA_DEFAULT_CLEVEL; module_param_named(rawdata_compression_level, aa_g_rawdata_compression_level, aacompressionlevel, 0400); /* Debug mode */ bool aa_g_debug = IS_ENABLED(CONFIG_SECURITY_APPARMOR_DEBUG_MESSAGES); module_param_named(debug, aa_g_debug, aabool, S_IRUSR | S_IWUSR); /* Audit mode */ enum audit_mode aa_g_audit; module_param_call(audit, param_set_audit, param_get_audit, &aa_g_audit, S_IRUSR | S_IWUSR); /* Determines if audit header is included in audited messages. This * provides more context if the audit daemon is not running */ bool aa_g_audit_header = true; module_param_named(audit_header, aa_g_audit_header, aabool, S_IRUSR | S_IWUSR); /* lock out loading/removal of policy * TODO: add in at boot loading of policy, which is the only way to * load policy, if lock_policy is set */ bool aa_g_lock_policy; module_param_named(lock_policy, aa_g_lock_policy, aalockpolicy, S_IRUSR | S_IWUSR); /* Syscall logging mode */ bool aa_g_logsyscall; module_param_named(logsyscall, aa_g_logsyscall, aabool, S_IRUSR | S_IWUSR); /* Maximum pathname length before accesses will start getting rejected */ unsigned int aa_g_path_max = 2 * PATH_MAX; module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR); /* Determines how paranoid loading of policy is and how much verification * on the loaded policy is done. * DEPRECATED: read only as strict checking of load is always done now * that none root users (user namespaces) can load policy. */ bool aa_g_paranoid_load = IS_ENABLED(CONFIG_SECURITY_APPARMOR_PARANOID_LOAD); module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO); static int param_get_aaintbool(char *buffer, const struct kernel_param *kp); static int param_set_aaintbool(const char *val, const struct kernel_param *kp); #define param_check_aaintbool param_check_int static const struct kernel_param_ops param_ops_aaintbool = { .set = param_set_aaintbool, .get = param_get_aaintbool }; /* Boot time disable flag */ static int apparmor_enabled __ro_after_init = 1; module_param_named(enabled, apparmor_enabled, aaintbool, 0444); static int __init apparmor_enabled_setup(char *str) { unsigned long enabled; int error = kstrtoul(str, 0, &enabled); if (!error) apparmor_enabled = enabled ? 1 : 0; return 1; } __setup("apparmor=", apparmor_enabled_setup); /* set global flag turning off the ability to load policy */ static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } static int param_set_aabool(const char *val, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } static int param_get_aabool(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } static int param_set_aauint(const char *val, const struct kernel_param *kp) { int error; if (!apparmor_enabled) return -EINVAL; /* file is ro but enforce 2nd line check */ if (apparmor_initialized) return -EPERM; error = param_set_uint(val, kp); aa_g_path_max = max_t(uint32_t, aa_g_path_max, sizeof(union aa_buffer)); pr_info("AppArmor: buffer size set to %d bytes\n", aa_g_path_max); return error; } static int param_get_aauint(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_uint(buffer, kp); } /* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */ static int param_set_aaintbool(const char *val, const struct kernel_param *kp) { struct kernel_param kp_local; bool value; int error; if (apparmor_initialized) return -EPERM; /* Create local copy, with arg pointing to bool type. */ value = !!*((int *)kp->arg); memcpy(&kp_local, kp, sizeof(kp_local)); kp_local.arg = &value; error = param_set_bool(val, &kp_local); if (!error) *((int *)kp->arg) = *((bool *)kp_local.arg); return error; } /* * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to * 1/0, this converts the "int that is actually bool" back to bool for * display in the /sys filesystem, while keeping it "int" for the LSM * infrastructure. */ static int param_get_aaintbool(char *buffer, const struct kernel_param *kp) { struct kernel_param kp_local; bool value; /* Create local copy, with arg pointing to bool type. */ value = !!*((int *)kp->arg); memcpy(&kp_local, kp, sizeof(kp_local)); kp_local.arg = &value; return param_get_bool(buffer, &kp_local); } static int param_set_aacompressionlevel(const char *val, const struct kernel_param *kp) { int error; if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized) return -EPERM; error = param_set_int(val, kp); aa_g_rawdata_compression_level = clamp(aa_g_rawdata_compression_level, AA_MIN_CLEVEL, AA_MAX_CLEVEL); pr_info("AppArmor: policy rawdata compression level set to %d\n", aa_g_rawdata_compression_level); return error; } static int param_get_aacompressionlevel(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_int(buffer, kp); } static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sprintf(buffer, "%s", audit_mode_names[aa_g_audit]); } static int param_set_audit(const char *val, const struct kernel_param *kp) { int i; if (!apparmor_enabled) return -EINVAL; if (!val) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(audit_mode_names, AUDIT_MAX_INDEX, val); if (i < 0) return -EINVAL; aa_g_audit = i; return 0; } static int param_get_mode(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sprintf(buffer, "%s", aa_profile_mode_names[aa_g_profile_mode]); } static int param_set_mode(const char *val, const struct kernel_param *kp) { int i; if (!apparmor_enabled) return -EINVAL; if (!val) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(aa_profile_mode_names, APPARMOR_MODE_NAMES_MAX_INDEX, val); if (i < 0) return -EINVAL; aa_g_profile_mode = i; return 0; } char *aa_get_buffer(bool in_atomic) { union aa_buffer *aa_buf; struct aa_local_cache *cache; bool try_again = true; gfp_t flags = (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); /* use per cpu cached buffers first */ cache = get_cpu_ptr(&aa_local_buffers); if (!list_empty(&cache->head)) { aa_buf = list_first_entry(&cache->head, union aa_buffer, list); list_del(&aa_buf->list); cache->hold--; cache->count--; put_cpu_ptr(&aa_local_buffers); return &aa_buf->buffer[0]; } put_cpu_ptr(&aa_local_buffers); if (!spin_trylock(&aa_buffers_lock)) { cache = get_cpu_ptr(&aa_local_buffers); cache->hold += 1; put_cpu_ptr(&aa_local_buffers); spin_lock(&aa_buffers_lock); } else { cache = get_cpu_ptr(&aa_local_buffers); put_cpu_ptr(&aa_local_buffers); } retry: if (buffer_count > reserve_count || (in_atomic && !list_empty(&aa_global_buffers))) { aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer, list); list_del(&aa_buf->list); buffer_count--; spin_unlock(&aa_buffers_lock); return aa_buf->buffer; } if (in_atomic) { /* * out of reserve buffers and in atomic context so increase * how many buffers to keep in reserve */ reserve_count++; flags = GFP_ATOMIC; } spin_unlock(&aa_buffers_lock); if (!in_atomic) might_sleep(); aa_buf = kmalloc(aa_g_path_max, flags); if (!aa_buf) { if (try_again) { try_again = false; spin_lock(&aa_buffers_lock); goto retry; } pr_warn_once("AppArmor: Failed to allocate a memory buffer.\n"); return NULL; } return aa_buf->buffer; } void aa_put_buffer(char *buf) { union aa_buffer *aa_buf; struct aa_local_cache *cache; if (!buf) return; aa_buf = container_of(buf, union aa_buffer, buffer[0]); cache = get_cpu_ptr(&aa_local_buffers); if (!cache->hold) { put_cpu_ptr(&aa_local_buffers); if (spin_trylock(&aa_buffers_lock)) { /* put back on global list */ list_add(&aa_buf->list, &aa_global_buffers); buffer_count++; spin_unlock(&aa_buffers_lock); cache = get_cpu_ptr(&aa_local_buffers); put_cpu_ptr(&aa_local_buffers); return; } /* contention on global list, fallback to percpu */ cache = get_cpu_ptr(&aa_local_buffers); cache->hold += 1; } /* cache in percpu list */ list_add(&aa_buf->list, &cache->head); cache->count++; put_cpu_ptr(&aa_local_buffers); } /* * AppArmor init functions */ /** * set_init_ctx - set a task context and profile on the first task. * * TODO: allow setting an alternate profile than unconfined */ static int __init set_init_ctx(void) { struct cred *cred = (__force struct cred *)current->real_cred; set_cred_label(cred, aa_get_label(ns_unconfined(root_ns))); return 0; } static void destroy_buffers(void) { union aa_buffer *aa_buf; spin_lock(&aa_buffers_lock); while (!list_empty(&aa_global_buffers)) { aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer, list); list_del(&aa_buf->list); spin_unlock(&aa_buffers_lock); kfree(aa_buf); spin_lock(&aa_buffers_lock); } spin_unlock(&aa_buffers_lock); } static int __init alloc_buffers(void) { union aa_buffer *aa_buf; int i, num; /* * per cpu set of cached allocated buffers used to help reduce * lock contention */ for_each_possible_cpu(i) { per_cpu(aa_local_buffers, i).hold = 0; per_cpu(aa_local_buffers, i).count = 0; INIT_LIST_HEAD(&per_cpu(aa_local_buffers, i).head); } /* * A function may require two buffers at once. Usually the buffers are * used for a short period of time and are shared. On UP kernel buffers * two should be enough, with more CPUs it is possible that more * buffers will be used simultaneously. The preallocated pool may grow. * This preallocation has also the side-effect that AppArmor will be * disabled early at boot if aa_g_path_max is extremly high. */ if (num_online_cpus() > 1) num = 4 + RESERVE_COUNT; else num = 2 + RESERVE_COUNT; for (i = 0; i < num; i++) { aa_buf = kmalloc(aa_g_path_max, GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (!aa_buf) { destroy_buffers(); return -ENOMEM; } aa_put_buffer(aa_buf->buffer); } return 0; } #ifdef CONFIG_SYSCTL static int apparmor_dointvec(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!aa_current_policy_admin_capable(NULL)) return -EPERM; if (!apparmor_enabled) return -EINVAL; return proc_dointvec(table, write, buffer, lenp, ppos); } static struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { .procname = "unprivileged_userns_apparmor_policy", .data = &unprivileged_userns_apparmor_policy, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, #endif /* CONFIG_USER_NS */ { .procname = "apparmor_display_secid_mode", .data = &apparmor_display_secid_mode, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, { .procname = "apparmor_restrict_unprivileged_unconfined", .data = &aa_unprivileged_unconfined_restricted, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, { } }; static int __init apparmor_init_sysctl(void) { return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM; } #else static inline int apparmor_init_sysctl(void) { return 0; } #endif /* CONFIG_SYSCTL */ #if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK) static unsigned int apparmor_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct aa_sk_ctx *ctx; struct sock *sk; if (!skb->secmark) return NF_ACCEPT; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; ctx = aa_sock(sk); if (!apparmor_secmark_check(ctx->label, OP_SENDMSG, AA_MAY_SEND, skb->secmark, sk)) return NF_ACCEPT; return NF_DROP_ERR(-ECONNREFUSED); } static const struct nf_hook_ops apparmor_nf_ops[] = { { .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif }; static int __net_init apparmor_nf_register(struct net *net) { return nf_register_net_hooks(net, apparmor_nf_ops, ARRAY_SIZE(apparmor_nf_ops)); } static void __net_exit apparmor_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, apparmor_nf_ops, ARRAY_SIZE(apparmor_nf_ops)); } static struct pernet_operations apparmor_net_ops = { .init = apparmor_nf_register, .exit = apparmor_nf_unregister, }; static int __init apparmor_nf_ip_init(void) { int err; if (!apparmor_enabled) return 0; err = register_pernet_subsys(&apparmor_net_ops); if (err) panic("Apparmor: register_pernet_subsys: error %d\n", err); return 0; } __initcall(apparmor_nf_ip_init); #endif static char nulldfa_src[] = { #include "nulldfa.in" }; static struct aa_dfa *nulldfa; static char stacksplitdfa_src[] = { #include "stacksplitdfa.in" }; struct aa_dfa *stacksplitdfa; struct aa_policydb *nullpdb; static int __init aa_setup_dfa_engine(void) { int error = -ENOMEM; nullpdb = aa_alloc_pdb(GFP_KERNEL); if (!nullpdb) return -ENOMEM; nulldfa = aa_dfa_unpack(nulldfa_src, sizeof(nulldfa_src), TO_ACCEPT1_FLAG(YYTD_DATA32) | TO_ACCEPT2_FLAG(YYTD_DATA32)); if (IS_ERR(nulldfa)) { error = PTR_ERR(nulldfa); goto fail; } nullpdb->dfa = aa_get_dfa(nulldfa); nullpdb->perms = kcalloc(2, sizeof(struct aa_perms), GFP_KERNEL); if (!nullpdb->perms) goto fail; nullpdb->size = 2; stacksplitdfa = aa_dfa_unpack(stacksplitdfa_src, sizeof(stacksplitdfa_src), TO_ACCEPT1_FLAG(YYTD_DATA32) | TO_ACCEPT2_FLAG(YYTD_DATA32)); if (IS_ERR(stacksplitdfa)) { error = PTR_ERR(stacksplitdfa); goto fail; } return 0; fail: aa_put_pdb(nullpdb); aa_put_dfa(nulldfa); nullpdb = NULL; nulldfa = NULL; stacksplitdfa = NULL; return error; } static void __init aa_teardown_dfa_engine(void) { aa_put_dfa(stacksplitdfa); aa_put_dfa(nulldfa); aa_put_pdb(nullpdb); nullpdb = NULL; stacksplitdfa = NULL; nulldfa = NULL; } static int __init apparmor_init(void) { int error; error = aa_setup_dfa_engine(); if (error) { AA_ERROR("Unable to setup dfa engine\n"); goto alloc_out; } error = aa_alloc_root_ns(); if (error) { AA_ERROR("Unable to allocate default profile namespace\n"); goto alloc_out; } error = apparmor_init_sysctl(); if (error) { AA_ERROR("Unable to register sysctls\n"); goto alloc_out; } error = alloc_buffers(); if (error) { AA_ERROR("Unable to allocate work buffers\n"); goto alloc_out; } error = set_init_ctx(); if (error) { AA_ERROR("Failed to set context on init task\n"); aa_free_root_ns(); goto buffers_out; } security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks), &apparmor_lsmid); /* Report that AppArmor successfully initialized */ apparmor_initialized = 1; if (aa_g_profile_mode == APPARMOR_COMPLAIN) aa_info_message("AppArmor initialized: complain mode enabled"); else if (aa_g_profile_mode == APPARMOR_KILL) aa_info_message("AppArmor initialized: kill mode enabled"); else aa_info_message("AppArmor initialized"); return error; buffers_out: destroy_buffers(); alloc_out: aa_destroy_aafs(); aa_teardown_dfa_engine(); apparmor_enabled = false; return error; } DEFINE_LSM(apparmor) = { .name = "apparmor", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &apparmor_enabled, .blobs = &apparmor_blob_sizes, .init = apparmor_init, }; |
| 30 30 30 30 30 7 7 30 30 30 30 30 30 30 30 30 30 30 30 30 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * The HSR spec says never to forward the same frame twice on the same * interface. A frame is identified by its source MAC address and its HSR * sequence number. This code keeps track of senders and their sequence numbers * to allow filtering of duplicate frames, and to detect HSR ring errors. * Same code handles filtering of duplicates for PRP as well. */ #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/rculist.h> #include "hsr_main.h" #include "hsr_framereg.h" #include "hsr_netlink.h" /* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, * false otherwise. */ static bool seq_nr_after(u16 a, u16 b) { /* Remove inconsistency where * seq_nr_after(a, b) == seq_nr_before(a, b) */ if ((int)b - a == 32768) return false; return (((s16)(b - a)) < 0); } #define seq_nr_before(a, b) seq_nr_after((b), (a)) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_self_node *sn; bool ret = false; rcu_read_lock(); sn = rcu_dereference(hsr->self_node); if (!sn) { WARN_ONCE(1, "HSR: No self node\n"); goto out; } if (ether_addr_equal(addr, sn->macaddress_A) || ether_addr_equal(addr, sn->macaddress_B)) ret = true; out: rcu_read_unlock(); return ret; } /* Search for mac entry. Caller must hold rcu read lock. */ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, const unsigned char addr[ETH_ALEN]) { struct hsr_node *node; list_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, addr)) return node; } return NULL; } /* Helper for device init; the self_node is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], const unsigned char addr_b[ETH_ALEN]) { struct hsr_self_node *sn, *old; sn = kmalloc(sizeof(*sn), GFP_KERNEL); if (!sn) return -ENOMEM; ether_addr_copy(sn->macaddress_A, addr_a); ether_addr_copy(sn->macaddress_B, addr_b); spin_lock_bh(&hsr->list_lock); old = rcu_replace_pointer(hsr->self_node, sn, lockdep_is_held(&hsr->list_lock)); spin_unlock_bh(&hsr->list_lock); if (old) kfree_rcu(old, rcu_head); return 0; } void hsr_del_self_node(struct hsr_priv *hsr) { struct hsr_self_node *old; spin_lock_bh(&hsr->list_lock); old = rcu_replace_pointer(hsr->self_node, NULL, lockdep_is_held(&hsr->list_lock)); spin_unlock_bh(&hsr->list_lock); if (old) kfree_rcu(old, rcu_head); } void hsr_del_nodes(struct list_head *node_db) { struct hsr_node *node; struct hsr_node *tmp; list_for_each_entry_safe(node, tmp, node_db, mac_list) kfree(node); } void prp_handle_san_frame(bool san, enum hsr_port_type port, struct hsr_node *node) { /* Mark if the SAN node is over LAN_A or LAN_B */ if (port == HSR_PT_SLAVE_A) { node->san_a = true; return; } if (port == HSR_PT_SLAVE_B) node->san_b = true; } /* Allocate an hsr_node and add it to node_db. 'addr' is the node's address_A; * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, struct list_head *node_db, unsigned char addr[], u16 seq_out, bool san, enum hsr_port_type rx_port) { struct hsr_node *new_node, *node; unsigned long now; int i; new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); if (!new_node) return NULL; ether_addr_copy(new_node->macaddress_A, addr); spin_lock_init(&new_node->seq_out_lock); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) { new_node->time_in[i] = now; new_node->time_out[i] = now; } for (i = 0; i < HSR_PT_PORTS; i++) new_node->seq_out[i] = seq_out; if (san && hsr->proto_ops->handle_san_frame) hsr->proto_ops->handle_san_frame(san, rx_port, new_node); spin_lock_bh(&hsr->list_lock); list_for_each_entry_rcu(node, node_db, mac_list, lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) goto out; } list_add_tail_rcu(&new_node->mac_list, node_db); spin_unlock_bh(&hsr->list_lock); return new_node; out: spin_unlock_bh(&hsr->list_lock); kfree(new_node); return node; } void prp_update_san_info(struct hsr_node *node, bool is_sup) { if (!is_sup) return; node->san_a = false; node->san_b = false; } /* Get the hsr_node from which 'skb' was sent. */ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port) { struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; struct prp_rct *rct; bool san = false; u16 seq_out; if (!skb_mac_header_was_set(skb)) return NULL; ethhdr = (struct ethhdr *)skb_mac_header(skb); list_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); return node; } if (ether_addr_equal(node->macaddress_B, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); return node; } } /* Everyone may create a node entry, connected node to a HSR/PRP * device. */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ seq_out = hsr_get_skb_sequence_nr(skb) - 1; } else { rct = skb_get_PRP_rct(skb); if (rct && prp_check_lsdu_size(skb, rct, is_sup)) { seq_out = prp_get_skb_sequence_nr(rct); } else { if (rx_port != HSR_PT_MASTER) san = true; seq_out = HSR_SEQNR_START; } } return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out, san, rx_port); } /* Use the Supervision frame's info about an eventual macaddress_B for merging * nodes that has previously had their macaddress_B registered as a separate * node. */ void hsr_handle_sup_frame(struct hsr_frame_info *frame) { struct hsr_node *node_curr = frame->node_src; struct hsr_port *port_rcv = frame->port_rcv; struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_sup_tlv; struct hsr_node *node_real; struct sk_buff *skb = NULL; struct list_head *node_db; struct ethhdr *ethhdr; int i; unsigned int pull_size = 0; unsigned int total_pull_size = 0; /* Here either frame->skb_hsr or frame->skb_prp should be * valid as supervision frame always will have protocol * header info. */ if (frame->skb_hsr) skb = frame->skb_hsr; else if (frame->skb_prp) skb = frame->skb_prp; else if (frame->skb_std) skb = frame->skb_std; if (!skb) return; /* Leave the ethernet header. */ pull_size = sizeof(struct ethhdr); skb_pull(skb, pull_size); total_pull_size += pull_size; ethhdr = (struct ethhdr *)skb_mac_header(skb); /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; /* get HSR sup payload */ hsr_sp = (struct hsr_sup_payload *)skb->data; /* Merge node_curr (registered on macaddress_B) into node_real */ node_db = &port_rcv->hsr->node_db; node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1, true, port_rcv->type); if (!node_real) goto done; /* No mem */ if (node_real == node_curr) /* Node has already been merged */ goto done; /* Leave the first HSR sup payload. */ pull_size = sizeof(struct hsr_sup_payload); skb_pull(skb, pull_size); total_pull_size += pull_size; /* Get second supervision tlv */ hsr_sup_tlv = (struct hsr_sup_tlv *)skb->data; /* And check if it is a redbox mac TLV */ if (hsr_sup_tlv->HSR_TLV_type == PRP_TLV_REDBOX_MAC) { /* We could stop here after pushing hsr_sup_payload, * or proceed and allow macaddress_B and for redboxes. */ /* Sanity check length */ if (hsr_sup_tlv->HSR_TLV_length != 6) goto done; /* Leave the second HSR sup tlv. */ pull_size = sizeof(struct hsr_sup_tlv); skb_pull(skb, pull_size); total_pull_size += pull_size; /* Get redbox mac address. */ hsr_sp = (struct hsr_sup_payload *)skb->data; /* Check if redbox mac and node mac are equal. */ if (!ether_addr_equal(node_real->macaddress_A, hsr_sp->macaddress_A)) { /* This is a redbox supervision frame for a VDAN! */ goto done; } } ether_addr_copy(node_real->macaddress_B, ethhdr->h_source); spin_lock_bh(&node_real->seq_out_lock); for (i = 0; i < HSR_PT_PORTS; i++) { if (!node_curr->time_in_stale[i] && time_after(node_curr->time_in[i], node_real->time_in[i])) { node_real->time_in[i] = node_curr->time_in[i]; node_real->time_in_stale[i] = node_curr->time_in_stale[i]; } if (seq_nr_after(node_curr->seq_out[i], node_real->seq_out[i])) node_real->seq_out[i] = node_curr->seq_out[i]; } spin_unlock_bh(&node_real->seq_out_lock); node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); if (!node_curr->removed) { list_del_rcu(&node_curr->mac_list); node_curr->removed = true; kfree_rcu(node_curr, rcu_head); } spin_unlock_bh(&hsr->list_lock); done: /* Push back here */ skb_push(skb, total_pull_size); } /* 'skb' is a frame meant for this host, that is to be passed to upper layers. * * If the frame was sent by a node's B interface, replace the source * address with that node's "official" address (macaddress_A) so that upper * layers recognize where it came from. */ void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); return; } memcpy(ð_hdr(skb)->h_source, node->macaddress_A, ETH_ALEN); } /* 'skb' is a frame meant for another host. * 'port' is the outgoing interface * * Substitute the target (dest) MAC address if necessary, so the it matches the * recipient interface MAC address, regardless of whether that is the * recipient's A or B interface. * This is needed to keep the packets flowing through switches that learn on * which "side" the different interfaces are. */ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, struct hsr_port *port) { struct hsr_node *node_dst; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); return; } if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest)) return; node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } if (port->type != node_dst->addr_B_port) return; if (is_valid_ether_addr(node_dst->macaddress_B)) ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); } void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, u16 sequence_nr) { /* Don't register incoming frames without a valid sequence number. This * ensures entries of restarted nodes gets pruned so that they can * re-register and resume communications. */ if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && seq_nr_before(sequence_nr, node->seq_out[port->type])) return; node->time_in[port->type] = jiffies; node->time_in_stale[port->type] = false; } /* 'skb' is a HSR Ethernet frame (with a HSR tag inserted), with a valid * ethhdr->h_source address and skb->mac_header set. * * Return: * 1 if frame can be shown to have been sent recently on this interface, * 0 otherwise, or * negative error code on error */ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr) { spin_lock_bh(&node->seq_out_lock); if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) && time_is_after_jiffies(node->time_out[port->type] + msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) { spin_unlock_bh(&node->seq_out_lock); return 1; } node->time_out[port->type] = jiffies; node->seq_out[port->type] = sequence_nr; spin_unlock_bh(&node->seq_out_lock); return 0; } static struct hsr_port *get_late_port(struct hsr_priv *hsr, struct hsr_node *node) { if (node->time_in_stale[HSR_PT_SLAVE_A]) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (node->time_in_stale[HSR_PT_SLAVE_B]) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (time_after(node->time_in[HSR_PT_SLAVE_B], node->time_in[HSR_PT_SLAVE_A] + msecs_to_jiffies(MAX_SLAVE_DIFF))) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (time_after(node->time_in[HSR_PT_SLAVE_A], node->time_in[HSR_PT_SLAVE_B] + msecs_to_jiffies(MAX_SLAVE_DIFF))) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); return NULL; } /* Remove stale sequence_nr records. Called by timer every * HSR_LIFE_CHECK_INTERVAL (two seconds or so). */ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; spin_lock_bh(&hsr->list_lock); list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly * pruned leading to packet loss. */ if (hsr_addr_is_self(hsr, node->macaddress_A)) continue; /* Shorthand */ time_a = node->time_in[HSR_PT_SLAVE_A]; time_b = node->time_in[HSR_PT_SLAVE_B]; /* Check for timestamps old enough to risk wrap-around */ if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) node->time_in_stale[HSR_PT_SLAVE_A] = true; if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) node->time_in_stale[HSR_PT_SLAVE_B] = true; /* Get age of newest frame from node. * At least one time_in is OK here; nodes get pruned long * before both time_ins can get stale */ timestamp = time_a; if (node->time_in_stale[HSR_PT_SLAVE_A] || (!node->time_in_stale[HSR_PT_SLAVE_B] && time_after(time_b, time_a))) timestamp = time_b; /* Warn of ring error only as long as we get frames at all */ if (time_is_after_jiffies(timestamp + msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { rcu_read_lock(); port = get_late_port(hsr, node); if (port) hsr_nl_ringerror(hsr, node->macaddress_A, port); rcu_read_unlock(); } /* Prune old entries */ if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { hsr_nl_nodedown(hsr, node->macaddress_A); if (!node->removed) { list_del_rcu(&node->mac_list); node->removed = true; /* Note that we need to free this entry later: */ kfree_rcu(node, rcu_head); } } } spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); } void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { struct hsr_node *node; if (!_pos) { node = list_first_or_null_rcu(&hsr->node_db, struct hsr_node, mac_list); if (node) ether_addr_copy(addr, node->macaddress_A); return node; } node = _pos; list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) { ether_addr_copy(addr, node->macaddress_A); return node; } return NULL; } int hsr_get_node_data(struct hsr_priv *hsr, const unsigned char *addr, unsigned char addr_b[ETH_ALEN], unsigned int *addr_b_ifindex, int *if1_age, u16 *if1_seq, int *if2_age, u16 *if2_seq) { struct hsr_node *node; struct hsr_port *port; unsigned long tdiff; node = find_node_by_addr_A(&hsr->node_db, addr); if (!node) return -ENOENT; ether_addr_copy(addr_b, node->macaddress_B); tdiff = jiffies - node->time_in[HSR_PT_SLAVE_A]; if (node->time_in_stale[HSR_PT_SLAVE_A]) *if1_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) *if1_age = INT_MAX; #endif else *if1_age = jiffies_to_msecs(tdiff); tdiff = jiffies - node->time_in[HSR_PT_SLAVE_B]; if (node->time_in_stale[HSR_PT_SLAVE_B]) *if2_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) *if2_age = INT_MAX; #endif else *if2_age = jiffies_to_msecs(tdiff); /* Present sequence numbers as if they were incoming on interface */ *if1_seq = node->seq_out[HSR_PT_SLAVE_B]; *if2_seq = node->seq_out[HSR_PT_SLAVE_A]; if (node->addr_B_port != HSR_PT_NONE) { port = hsr_port_get_hsr(hsr, node->addr_B_port); *addr_b_ifindex = port->dev->ifindex; } else { *addr_b_ifindex = -1; } return 0; } |
| 21572 21613 21561 | 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 | /* * Stack trace management functions * * Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <linux/export.h> #include <linux/uaccess.h> #include <asm/stacktrace.h> #include <asm/unwind.h> void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { struct unwind_state state; unsigned long addr; if (regs && !consume_entry(cookie, regs->ip)) return; for (unwind_start(&state, task, regs, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || !consume_entry(cookie, addr)) break; } } int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task) { struct unwind_state state; struct pt_regs *regs; unsigned long addr; for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { regs = unwind_get_entry_regs(&state, NULL); if (regs) { /* Success path for user tasks */ if (user_mode(regs)) return 0; /* * Kernel mode registers on the stack indicate an * in-kernel interrupt or exception (e.g., preemption * or a page fault), which can make frame pointers * unreliable. */ if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } addr = unwind_get_return_address(&state); /* * A NULL or invalid return address probably means there's some * generated code which __kernel_text_address() doesn't know * about. */ if (!addr) return -EINVAL; if (!consume_entry(cookie, addr)) return -EINVAL; } /* Check for stack corruption */ if (unwind_error(&state)) return -EINVAL; return 0; } /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ struct stack_frame_user { const void __user *next_fp; unsigned long ret_addr; }; static int copy_stack_frame(const struct stack_frame_user __user *fp, struct stack_frame_user *frame) { int ret; if (!__access_ok(fp, sizeof(*frame))) return 0; ret = 1; pagefault_disable(); if (__get_user(frame->next_fp, &fp->next_fp) || __get_user(frame->ret_addr, &fp->ret_addr)) ret = 0; pagefault_enable(); return ret; } void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, const struct pt_regs *regs) { const void __user *fp = (const void __user *)regs->bp; if (!consume_entry(cookie, regs->ip)) return; while (1) { struct stack_frame_user frame; frame.next_fp = NULL; frame.ret_addr = 0; if (!copy_stack_frame(fp, &frame)) break; if ((unsigned long)fp < regs->sp) break; if (!frame.ret_addr) break; if (!consume_entry(cookie, frame.ret_addr)) break; fp = frame.next_fp; } } |
| 1008 1008 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ #include <linux/jump_label.h> #include <linux/uaccess.h> #include <linux/export.h> #include <linux/string.h> #include <linux/types.h> #include <asm/mce.h> #ifdef CONFIG_X86_MCE static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key); void enable_copy_mc_fragile(void) { static_branch_inc(©_mc_fragile_key); } #define copy_mc_fragile_enabled (static_branch_unlikely(©_mc_fragile_key)) /* * Similar to copy_user_handle_tail, probe for the write fault point, or * source exception point. */ __visible notrace unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len) { for (; len; --len, to++, from++) if (copy_mc_fragile(to, from, 1)) break; return len; } #else /* * No point in doing careful copying, or consulting a static key when * there is no #MC handler in the CONFIG_X86_MCE=n case. */ void enable_copy_mc_fragile(void) { } #define copy_mc_fragile_enabled (0) #endif unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned len); /** * copy_mc_to_kernel - memory copy that handles source exceptions * * @dst: destination address * @src: source address * @len: number of bytes to copy * * Call into the 'fragile' version on systems that benefit from avoiding * corner case poison consumption scenarios, For example, accessing * poison across 2 cachelines with a single instruction. Almost all * other uses case can use copy_mc_enhanced_fast_string() for a fast * recoverable copy, or fallback to plain memcpy. * * Return 0 for success, or number of bytes not copied if there was an * exception. */ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) { if (copy_mc_fragile_enabled) return copy_mc_fragile(dst, src, len); if (static_cpu_has(X86_FEATURE_ERMS)) return copy_mc_enhanced_fast_string(dst, src, len); memcpy(dst, src, len); return 0; } EXPORT_SYMBOL_GPL(copy_mc_to_kernel); unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len) { unsigned long ret; if (copy_mc_fragile_enabled) { __uaccess_begin(); ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); return ret; } if (static_cpu_has(X86_FEATURE_ERMS)) { __uaccess_begin(); ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); return ret; } return copy_user_generic((__force void *)dst, src, len); } |
| 52 22 8929 10 8928 7120 8352 8630 5104 426 411 425 351 8654 8115 8649 927 2744 6829 8114 8649 8112 10 10 42 144 3 8924 8919 8927 148 3 3 3 3 8652 8654 26 29 735 8659 8650 507 8561 3273 2991 5244 6352 5501 6 2574 470 5074 6652 5256 5240 6746 426 283 289 426 8305 6761 7375 8307 8652 8356 8640 7983 5618 8251 898 396 8648 280 392 464 496 927 8630 701 8651 554 8650 354 799 278 322 807 817 81 817 73 95 813 221 8652 38 8656 8628 221 8653 6746 6444 8656 8655 8652 8655 8560 6746 8548 7355 818 818 818 817 818 10 10 10 9 9 42 42 42 818 818 3512 256 7573 8655 3556 7576 7572 7576 7571 810 209 209 209 209 8653 8657 8654 16 8652 220 8624 8652 8657 8652 35 3 8657 8652 219 42 42 8627 8655 52 8656 8657 8188 3050 861 386 818 816 814 1 818 3 3 30 546 1 517 517 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->index = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->index; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { if (move_front) list_move(&chunk->list, &pcpu_chunk_lists[slot]); else list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); /* leave isolated chunks in-place */ if (chunk->isolated) return; if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, start, end); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } /* * If the allocation is not atomic, some blocks may not be * populated with pages, while we account it here. The number * of pages will be added back with pcpu_chunk_populated() * when populating pages. */ if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int start, end; start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); start = find_next_zero_bit(chunk->populated, end, start); if (start >= end) return true; end = find_next_bit(chunk->populated, end, start + 1); *next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * This is an optimization to prevent scanning by assuming if the * allocation cannot fit in the global hint, there is memory pressure * and creating a new chunk would happen soon. */ if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; region_size = ALIGN(start_offset + map_size, PAGE_SIZE); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->alloc_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->bound_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->md_blocks) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); #ifdef CONFIG_MEMCG_KMEM /* first chunk is free to use */ chunk->obj_cgroups = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef CONFIG_MEMCG_KMEM if (!mem_cgroup_kmem_disabled()) { chunk->obj_cgroups = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct obj_cgroup *), gfp); if (!chunk->obj_cgroups) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef CONFIG_MEMCG_KMEM objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef CONFIG_MEMCG_KMEM pcpu_mem_free(chunk->obj_cgroups); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG_KMEM static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = current_obj_cgroup(); if (!objcg) return true; if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; *objcgp = objcg; return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (likely(chunk && chunk->obj_cgroups)) { obj_cgroup_get(objcg); chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, pcpu_obj_full_size(size)); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (unlikely(!chunk->obj_cgroups)) return; objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; if (!objcg) return; chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -pcpu_obj_full_size(size)); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG_KMEM */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG_KMEM */ /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) { pcpu_reintegrate_chunk(chunk); goto area_found; } } } spin_unlock_irqrestore(&pcpu_lock, flags); if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_end, rs, re; rs = PFN_DOWN(off); page_end = PFN_UP(off + size); for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, chunk->base_addr, off, ptr, pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); if (!is_atomic) dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } /** * __alloc_percpu_gfp - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @gfp: allocation flags * * Allocate zero-filled percpu area of @size bytes aligned at @align. If * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can * be called from any context but is a lot more likely to fail. If @gfp * has __GFP_NOWARN then no warning will be triggered on invalid or failed * allocation requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) { return pcpu_alloc(size, align, false, gfp); } EXPORT_SYMBOL_GPL(__alloc_percpu_gfp); /** * __alloc_percpu - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL). */ void __percpu *__alloc_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, false, GFP_KERNEL); } EXPORT_SYMBOL_GPL(__alloc_percpu); /** * __alloc_reserved_percpu - allocate reserved percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Allocate zero-filled percpu area of @size bytes aligned at @align * from reserved percpu area if arch has set it up; otherwise, * allocation is served from the same dynamic area. Might sleep. * Might trigger writeouts. * * CONTEXT: * Does GFP_KERNEL allocation. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, true, GFP_KERNEL); } /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; if (!empty_only || chunk->nr_empty_pop_pages == 0) list_move(&chunk->list, &to_free); } if (list_empty(&to_free)) return; spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } spin_lock_irq(&pcpu_lock); } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; pcpu_chunk_populated(chunk, rs, rs + nr); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ spin_unlock_irq(&pcpu_lock); chunk = pcpu_create_chunk(gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (chunk) { pcpu_chunk_relocate(chunk, -1); goto retry_pop; } } } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { struct pcpu_chunk *chunk; struct pcpu_block_md *block; int freed_page_start, freed_page_end; int i, end; bool reintegrate; lockdep_assert_held(&pcpu_lock); /* * Once a chunk is isolated to the to_depopulate list, the chunk is no * longer discoverable to allocations whom may populate pages. The only * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ while ((chunk = list_first_entry_or_null( &pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list))) { WARN_ON(chunk->immutable); /* * Scan chunk's pages in the reverse order to keep populated * pages close to the beginning of the chunk. */ freed_page_start = chunk->nr_pages; freed_page_end = 0; reintegrate = false; for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { /* no more work to do */ if (chunk->nr_empty_pop_pages == 0) break; /* reintegrate chunk to prevent atomic alloc failures */ if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; } /* * If the page is empty and populated, start or * extend the (i, end) range. If i == 0, decrease * i and perform the depopulation to cover the last * (first) page in the chunk. */ block = chunk->md_blocks + i; if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && test_bit(i, chunk->populated)) { if (end == -1) end = i; if (i > 0) continue; i--; } /* depopulate if there is an active range */ if (end == -1) continue; spin_unlock_irq(&pcpu_lock); pcpu_depopulate_chunk(chunk, i + 1, end + 1); cond_resched(); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, i + 1, end + 1); freed_page_start = min(freed_page_start, i + 1); freed_page_end = max(freed_page_end, end + 1); /* reset the range and continue */ end = -1; } /* batch tlb flush per chunk to amortize cost */ if (freed_page_start < freed_page_end) { spin_unlock_irq(&pcpu_lock); pcpu_post_unmap_tlb_flush(chunk, freed_page_start, freed_page_end); cond_resched(); spin_lock_irq(&pcpu_lock); } if (reintegrate || chunk->free_bytes == pcpu_unit_size) pcpu_reintegrate_chunk(chunk); else list_move_tail(&chunk->list, &pcpu_chunk_lists[pcpu_sidelined_slot]); } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us * to grow other chunks. This then gives pcpu_reclaim_populated() time * to move fully free chunks to the active list to be freed if * appropriate. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); pcpu_balance_free(false); pcpu_reclaim_populated(); pcpu_balance_populated(); pcpu_balance_free(true); spin_unlock_irq(&pcpu_lock); mutex_unlock(&pcpu_alloc_mutex); } /** * pcpu_alloc_size - the size of the dynamic percpu area * @ptr: pointer to the dynamic percpu area * * Returns the size of the @ptr allocation. This is undefined for statically * defined percpu variables as there is no corresponding chunk->bound_map. * * RETURNS: * The size of the dynamic percpu area. * * CONTEXT: * Can be called from atomic context. */ size_t pcpu_alloc_size(void __percpu *ptr) { struct pcpu_chunk *chunk; unsigned long bit_off, end; void *addr; if (!ptr) return 0; addr = __pcpu_ptr_to_addr(ptr); /* No pcpu_lock here: ptr has not been freed, so chunk is still alive */ chunk = pcpu_chunk_addr_search(addr); bit_off = (addr - chunk->base_addr) / PCPU_MIN_ALLOC_SIZE; end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); return (end - bit_off) * PCPU_MIN_ALLOC_SIZE; } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_memcg_free_hook(chunk, off, size); /* * If there are more than one fully free chunks, wake up grim reaper. * If the chunk is isolated, it may be in the process of being * reclaimed. Let reclaim manage cleaning up of that chunk. */ if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free(ai, ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; unsigned long tmp_addr; size_t alloc_size; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_offsets) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_sizes) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_off) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The slots after the active slots are: * sidelined_slot - isolated, depopulated chunks * free_slot - fully free chunks * to_depopulate_slot - isolated, chunks to depopulate */ pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk: * This chunk is broken up into 3 parts: * < static | [reserved] | dynamic > * - static - there is no backing chunk because these allocations can * never be freed. * - reserved (pcpu_reserved_chunk) - exists primarily to serve * allocations from module load. * - dynamic (pcpu_first_chunk) - serves the dynamic part of the first * chunk. */ tmp_addr = (unsigned long)base_addr + static_size; if (ai->reserved_size) pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, ai->reserved_size); tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size); pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; static struct cpumask mask __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); cpumask_clear(&mask); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; cpumask_copy(&mask, cpu_possible_mask); /* group cpus according to their proximity */ for (group = 0; !cpumask_empty(&mask); group++) { /* pop the group's first cpu */ cpu = cpumask_first(&mask); group_map[cpu] = group; group_cnt[group]++; cpumask_clear_cpu(cpu, &mask); for_each_cpu(tcpu, &mask) { if (!cpu_distance_fn || (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE && cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) { group_map[tcpu] = group; group_cnt[group]++; cpumask_clear_cpu(tcpu, &mask); } } } nr_groups = group; /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA int node = NUMA_NO_NODE; void *ptr; if (cpu_to_nd_fn) node = cpu_to_nd_fn(cpu); if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", cpu, size, (u64)__pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", cpu, size, node, (u64)__pa(ptr)); } return ptr; #else return memblock_alloc_from(size, align, goal); #endif } static void __init pcpu_fc_free(void *ptr, size_t size) { memblock_free(ptr, size); } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <asm/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE PAGE_SIZE #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE PAGE_SIZE #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE PAGE_SIZE #endif void __init __weak pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (pgd_none(*pgd)) { p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); if (!p4d) goto err_alloc; pgd_populate(&init_mm, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); if (!pud) goto err_alloc; p4d_populate(&init_mm, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); if (!pmd) goto err_alloc; pud_populate(&init_mm, pud, pmd); } pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) { pte_t *new; new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); if (!new) goto err_alloc; pmd_populate_kernel(&init_mm, pmd, new); } return; err_alloc: panic("%s: Failed to allocate memory\n", __func__); } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); if (!pages) panic("%s: Failed to allocate %zu bytes\n", __func__, pages_size); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 28 32 28 28 28 28 28 28 28 28 28 28 41 41 41 32 28 41 41 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "device.h" #include "peer.h" #include "socket.h" #include "queueing.h" #include "messages.h" #include <linux/ctype.h> #include <linux/net.h> #include <linux/if_vlan.h> #include <linux/if_ether.h> #include <linux/inetdevice.h> #include <net/udp_tunnel.h> #include <net/ipv6.h> static int send4(struct wg_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache) { struct flowi4 fl = { .saddr = endpoint->src4.s_addr, .daddr = endpoint->addr4.sin_addr.s_addr, .fl4_dport = endpoint->addr4.sin_port, .flowi4_mark = wg->fwmark, .flowi4_proto = IPPROTO_UDP }; struct rtable *rt = NULL; struct sock *sock; int ret = 0; skb_mark_not_on_list(skb); skb->dev = wg->dev; skb->mark = wg->fwmark; rcu_read_lock_bh(); sock = rcu_dereference_bh(wg->sock4); if (unlikely(!sock)) { ret = -ENONET; goto err; } fl.fl4_sport = inet_sk(sock)->inet_sport; if (cache) rt = dst_cache_get_ip4(cache, &fl.saddr); if (!rt) { security_sk_classify_flow(sock, flowi4_to_flowi_common(&fl)); if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, fl.saddr, RT_SCOPE_HOST))) { endpoint->src4.s_addr = 0; endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); } rt = ip_route_output_flow(sock_net(sock), &fl, sock); if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && rt->dst.dev->ifindex != endpoint->src_if4)))) { endpoint->src4.s_addr = 0; endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); if (!IS_ERR(rt)) ip_rt_put(rt); rt = ip_route_output_flow(sock_net(sock), &fl, sock); } if (IS_ERR(rt)) { ret = PTR_ERR(rt); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; } if (cache) dst_cache_set_ip4(cache, &rt->dst, fl.saddr); } skb->ignore_df = 1; udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds, ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, fl.fl4_dport, false, false); goto out; err: kfree_skb(skb); out: rcu_read_unlock_bh(); return ret; } static int send6(struct wg_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache) { #if IS_ENABLED(CONFIG_IPV6) struct flowi6 fl = { .saddr = endpoint->src6, .daddr = endpoint->addr6.sin6_addr, .fl6_dport = endpoint->addr6.sin6_port, .flowi6_mark = wg->fwmark, .flowi6_oif = endpoint->addr6.sin6_scope_id, .flowi6_proto = IPPROTO_UDP /* TODO: addr->sin6_flowinfo */ }; struct dst_entry *dst = NULL; struct sock *sock; int ret = 0; skb_mark_not_on_list(skb); skb->dev = wg->dev; skb->mark = wg->fwmark; rcu_read_lock_bh(); sock = rcu_dereference_bh(wg->sock6); if (unlikely(!sock)) { ret = -ENONET; goto err; } fl.fl6_sport = inet_sk(sock)->inet_sport; if (cache) dst = dst_cache_get_ip6(cache, &fl.saddr); if (!dst) { security_sk_classify_flow(sock, flowi6_to_flowi_common(&fl)); if (unlikely(!ipv6_addr_any(&fl.saddr) && !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) { endpoint->src6 = fl.saddr = in6addr_any; if (cache) dst_cache_reset(cache); } dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl, NULL); if (IS_ERR(dst)) { ret = PTR_ERR(dst); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; } if (cache) dst_cache_set_ip6(cache, dst, &fl.saddr); } skb->ignore_df = 1; udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds, ip6_dst_hoplimit(dst), 0, fl.fl6_sport, fl.fl6_dport, false); goto out; err: kfree_skb(skb); out: rcu_read_unlock_bh(); return ret; #else kfree_skb(skb); return -EAFNOSUPPORT; #endif } int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, u8 ds) { size_t skb_len = skb->len; int ret = -EAFNOSUPPORT; read_lock_bh(&peer->endpoint_lock); if (peer->endpoint.addr.sa_family == AF_INET) ret = send4(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache); else if (peer->endpoint.addr.sa_family == AF_INET6) ret = send6(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache); else dev_kfree_skb(skb); if (likely(!ret)) peer->tx_bytes += skb_len; read_unlock_bh(&peer->endpoint_lock); return ret; } int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *buffer, size_t len, u8 ds) { struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); if (unlikely(!skb)) return -ENOMEM; skb_reserve(skb, SKB_HEADER_LEN); skb_set_inner_network_header(skb, 0); skb_put_data(skb, buffer, len); return wg_socket_send_skb_to_peer(peer, skb, ds); } int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg, struct sk_buff *in_skb, void *buffer, size_t len) { int ret = 0; struct sk_buff *skb; struct endpoint endpoint; if (unlikely(!in_skb)) return -EINVAL; ret = wg_socket_endpoint_from_skb(&endpoint, in_skb); if (unlikely(ret < 0)) return ret; skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); if (unlikely(!skb)) return -ENOMEM; skb_reserve(skb, SKB_HEADER_LEN); skb_set_inner_network_header(skb, 0); skb_put_data(skb, buffer, len); if (endpoint.addr.sa_family == AF_INET) ret = send4(wg, skb, &endpoint, 0, NULL); else if (endpoint.addr.sa_family == AF_INET6) ret = send6(wg, skb, &endpoint, 0, NULL); /* No other possibilities if the endpoint is valid, which it is, * as we checked above. */ return ret; } int wg_socket_endpoint_from_skb(struct endpoint *endpoint, const struct sk_buff *skb) { memset(endpoint, 0, sizeof(*endpoint)); if (skb->protocol == htons(ETH_P_IP)) { endpoint->addr4.sin_family = AF_INET; endpoint->addr4.sin_port = udp_hdr(skb)->source; endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr; endpoint->src4.s_addr = ip_hdr(skb)->daddr; endpoint->src_if4 = skb->skb_iif; } else if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { endpoint->addr6.sin6_family = AF_INET6; endpoint->addr6.sin6_port = udp_hdr(skb)->source; endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr; endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id( &ipv6_hdr(skb)->saddr, skb->skb_iif); endpoint->src6 = ipv6_hdr(skb)->daddr; } else { return -EINVAL; } return 0; } static bool endpoint_eq(const struct endpoint *a, const struct endpoint *b) { return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET && a->addr4.sin_port == b->addr4.sin_port && a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr && a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) || (a->addr.sa_family == AF_INET6 && b->addr.sa_family == AF_INET6 && a->addr6.sin6_port == b->addr6.sin6_port && ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) && a->addr6.sin6_scope_id == b->addr6.sin6_scope_id && ipv6_addr_equal(&a->src6, &b->src6)) || unlikely(!a->addr.sa_family && !b->addr.sa_family); } void wg_socket_set_peer_endpoint(struct wg_peer *peer, const struct endpoint *endpoint) { /* First we check unlocked, in order to optimize, since it's pretty rare * that an endpoint will change. If we happen to be mid-write, and two * CPUs wind up writing the same thing or something slightly different, * it doesn't really matter much either. */ if (endpoint_eq(endpoint, &peer->endpoint)) return; write_lock_bh(&peer->endpoint_lock); if (endpoint->addr.sa_family == AF_INET) { peer->endpoint.addr4 = endpoint->addr4; peer->endpoint.src4 = endpoint->src4; peer->endpoint.src_if4 = endpoint->src_if4; } else if (IS_ENABLED(CONFIG_IPV6) && endpoint->addr.sa_family == AF_INET6) { peer->endpoint.addr6 = endpoint->addr6; peer->endpoint.src6 = endpoint->src6; } else { goto out; } dst_cache_reset(&peer->endpoint_cache); out: write_unlock_bh(&peer->endpoint_lock); } void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer, const struct sk_buff *skb) { struct endpoint endpoint; if (!wg_socket_endpoint_from_skb(&endpoint, skb)) wg_socket_set_peer_endpoint(peer, &endpoint); } void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer) { write_lock_bh(&peer->endpoint_lock); memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6)); dst_cache_reset_now(&peer->endpoint_cache); write_unlock_bh(&peer->endpoint_lock); } static int wg_receive(struct sock *sk, struct sk_buff *skb) { struct wg_device *wg; if (unlikely(!sk)) goto err; wg = sk->sk_user_data; if (unlikely(!wg)) goto err; skb_mark_not_on_list(skb); wg_packet_receive(wg, skb); return 0; err: kfree_skb(skb); return 0; } static void sock_free(struct sock *sock) { if (unlikely(!sock)) return; sk_clear_memalloc(sock); udp_tunnel_sock_release(sock->sk_socket); } static void set_sock_opts(struct socket *sock) { sock->sk->sk_allocation = GFP_ATOMIC; sock->sk->sk_sndbuf = INT_MAX; sk_set_memalloc(sock->sk); } int wg_socket_init(struct wg_device *wg, u16 port) { struct net *net; int ret; struct udp_tunnel_sock_cfg cfg = { .sk_user_data = wg, .encap_type = 1, .encap_rcv = wg_receive }; struct socket *new4 = NULL, *new6 = NULL; struct udp_port_cfg port4 = { .family = AF_INET, .local_ip.s_addr = htonl(INADDR_ANY), .local_udp_port = htons(port), .use_udp_checksums = true }; #if IS_ENABLED(CONFIG_IPV6) int retries = 0; struct udp_port_cfg port6 = { .family = AF_INET6, .local_ip6 = IN6ADDR_ANY_INIT, .use_udp6_tx_checksums = true, .use_udp6_rx_checksums = true, .ipv6_v6only = true }; #endif rcu_read_lock(); net = rcu_dereference(wg->creating_net); net = net ? maybe_get_net(net) : NULL; rcu_read_unlock(); if (unlikely(!net)) return -ENONET; #if IS_ENABLED(CONFIG_IPV6) retry: #endif ret = udp_sock_create(net, &port4, &new4); if (ret < 0) { pr_err("%s: Could not create IPv4 socket\n", wg->dev->name); goto out; } set_sock_opts(new4); setup_udp_tunnel_sock(net, new4, &cfg); #if IS_ENABLED(CONFIG_IPV6) if (ipv6_mod_enabled()) { port6.local_udp_port = inet_sk(new4->sk)->inet_sport; ret = udp_sock_create(net, &port6, &new6); if (ret < 0) { udp_tunnel_sock_release(new4); if (ret == -EADDRINUSE && !port && retries++ < 100) goto retry; pr_err("%s: Could not create IPv6 socket\n", wg->dev->name); goto out; } set_sock_opts(new6); setup_udp_tunnel_sock(net, new6, &cfg); } #endif wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL); ret = 0; out: put_net(net); return ret; } void wg_socket_reinit(struct wg_device *wg, struct sock *new4, struct sock *new6) { struct sock *old4, *old6; mutex_lock(&wg->socket_update_lock); old4 = rcu_dereference_protected(wg->sock4, lockdep_is_held(&wg->socket_update_lock)); old6 = rcu_dereference_protected(wg->sock6, lockdep_is_held(&wg->socket_update_lock)); rcu_assign_pointer(wg->sock4, new4); rcu_assign_pointer(wg->sock6, new6); if (new4) wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); synchronize_net(); sock_free(old4); sock_free(old6); } |
| 71 601 600 37 37 37 37 37 37 37 37 37 37 37 82 82 89 4 89 89 13 82 13 89 74 71 1 2 26 26 26 26 26 26 26 26 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inet fragments management * * Authors: Pavel Emelyanov <xemul@openvz.org> * Started as consolidation of ipv4/ip_fragment.c, * ipv6/reassembly. and ipv6 nf conntrack reassembly */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> #include <net/ip.h> #include <net/ipv6.h> /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. * * Invariants: * - next_frag is NULL at the tail of a "run"; * - the head of a "run" has the sum of all fragment lengths in frag_run_len. */ struct ipfrag_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; }; struct sk_buff *next_frag; int frag_run_len; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) static void fragcb_clear(struct sk_buff *skb) { RB_CLEAR_NODE(&skb->rbnode); FRAG_CB(skb)->next_frag = NULL; FRAG_CB(skb)->frag_run_len = skb->len; } /* Append skb to the last "run". */ static void fragrun_append_to_last(struct inet_frag_queue *q, struct sk_buff *skb) { fragcb_clear(skb); FRAG_CB(q->last_run_head)->frag_run_len += skb->len; FRAG_CB(q->fragments_tail)->next_frag = skb; q->fragments_tail = skb; } /* Create a new "run" with the skb. */ static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); fragcb_clear(skb); if (q->last_run_head) rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, &q->last_run_head->rbnode.rb_right); else rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); rb_insert_color(&skb->rbnode, &q->rb_fragments); q->fragments_tail = skb; q->last_run_head = skb; } /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field */ const u8 ip_frag_ecn_table[16] = { /* at least one fragment had CE, and others ECT_0 or ECT_1 */ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE, /* invalid combinations : drop frame */ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, }; EXPORT_SYMBOL(ip_frag_ecn_table); int inet_frags_init(struct inet_frags *f) { f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, NULL); if (!f->frags_cachep) return -ENOMEM; refcount_set(&f->refcnt, 1); init_completion(&f->completion); return 0; } EXPORT_SYMBOL(inet_frags_init); void inet_frags_fini(struct inet_frags *f) { if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); wait_for_completion(&f->completion); kmem_cache_destroy(f->frags_cachep); f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini); /* called from rhashtable_free_and_destroy() at netns_frags dismantle */ static void inet_frags_free_cb(void *ptr, void *arg) { struct inet_frag_queue *fq = ptr; int count; count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; } else if (fq->flags & INET_FRAG_HASH_DEAD) { count++; } spin_unlock_bh(&fq->lock); if (refcount_sub_and_test(count, &fq->refcnt)) inet_frag_destroy(fq); } static LLIST_HEAD(fqdir_free_list); static void fqdir_free_fn(struct work_struct *work) { struct llist_node *kill_list; struct fqdir *fqdir, *tmp; struct inet_frags *f; /* Atomically snapshot the list of fqdirs to free */ kill_list = llist_del_all(&fqdir_free_list); /* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu) * have completed, since they need to dereference fqdir. * Would it not be nice to have kfree_rcu_barrier() ? :) */ rcu_barrier(); llist_for_each_entry_safe(fqdir, tmp, kill_list, free_list) { f = fqdir->f; if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); kfree(fqdir); } } static DECLARE_WORK(fqdir_free_work, fqdir_free_fn); static void fqdir_work_fn(struct work_struct *work) { struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work); rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) queue_work(system_wq, &fqdir_free_work); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) { struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); int res; if (!fqdir) return -ENOMEM; fqdir->f = f; fqdir->net = net; res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); if (res < 0) { kfree(fqdir); return res; } refcount_inc(&f->refcnt); *fqdirp = fqdir; return 0; } EXPORT_SYMBOL(fqdir_init); static struct workqueue_struct *inet_frag_wq; static int __init inet_frag_wq_init(void) { inet_frag_wq = create_workqueue("inet_frag_wq"); if (!inet_frag_wq) panic("Could not create inet frag workq"); return 0; } pure_initcall(inet_frag_wq_init); void fqdir_exit(struct fqdir *fqdir) { INIT_WORK(&fqdir->destroy_work, fqdir_work_fn); queue_work(inet_frag_wq, &fqdir->destroy_work); } EXPORT_SYMBOL(fqdir_exit); void inet_frag_kill(struct inet_frag_queue *fq) { if (del_timer(&fq->timer)) refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { struct fqdir *fqdir = fq->fqdir; fq->flags |= INET_FRAG_COMPLETE; rcu_read_lock(); /* The RCU read lock provides a memory barrier * guaranteeing that if fqdir->dead is false then * the hash table destruction will not start until * after we unlock. Paired with fqdir_pre_exit(). */ if (!READ_ONCE(fqdir->dead)) { rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, fqdir->f->rhash_params); refcount_dec(&fq->refcnt); } else { fq->flags |= INET_FRAG_HASH_DEAD; } rcu_read_unlock(); } } EXPORT_SYMBOL(inet_frag_kill); static void inet_frag_destroy_rcu(struct rcu_head *head) { struct inet_frag_queue *q = container_of(head, struct inet_frag_queue, rcu); struct inet_frags *f = q->fqdir->f; if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); } unsigned int inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason) { 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); while (skb) { struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; kfree_skb_reason(skb, reason); skb = next; } } return sum; } EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { unsigned int sum, sum_truesize = 0; enum skb_drop_reason reason; struct inet_frags *f; struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); reason = (q->flags & INET_FRAG_DROP) ? SKB_DROP_REASON_FRAG_REASM_TIMEOUT : SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); sub_frag_mem_limit(fqdir, sum); } EXPORT_SYMBOL(inet_frag_destroy); static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, struct inet_frags *f, void *arg) { struct inet_frag_queue *q; q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; q->fqdir = fqdir; f->constructor(q, arg); add_frag_mem_limit(fqdir, f->qsize); timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 3); return q; } static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, void *arg, struct inet_frag_queue **prev) { struct inet_frags *f = fqdir->f; struct inet_frag_queue *q; q = inet_frag_alloc(fqdir, f, arg); if (!q) { *prev = ERR_PTR(-ENOMEM); return NULL; } mod_timer(&q->timer, jiffies + fqdir->timeout); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); return NULL; } return q; } /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) { /* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */ long high_thresh = READ_ONCE(fqdir->high_thresh); struct inet_frag_queue *fq = NULL, *prev; if (!high_thresh || frag_mem_limit(fqdir) > high_thresh) return NULL; rcu_read_lock(); prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; } rcu_read_unlock(); return fq; } EXPORT_SYMBOL(inet_frag_find); int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, int offset, int end) { struct sk_buff *last = q->fragments_tail; /* RFC5722, Section 4, amended by Errata ID : 3089 * When reassembling an IPv6 datagram, if * one or more its constituent fragments is determined to be an * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * * Duplicates, however, should be ignored (i.e. skb dropped, but the * queue/fragments kept for later reassembly). */ if (!last) fragrun_create(q, skb); /* First fragment. */ else if (last->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ if (offset < last->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; if (offset == last->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); } else { /* Binary search. Note that skb can become the first fragment, * but not the last (covered above). */ struct rb_node **rbn, *parent; rbn = &q->rb_fragments.rb_node; do { struct sk_buff *curr; int curr_run_end; parent = *rbn; curr = rb_to_skb(parent); curr_run_end = curr->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; if (end <= curr->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; else if (offset >= curr->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else return IPFRAG_OVERLAP; } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. */ fragcb_clear(skb); rb_link_node(&skb->rbnode, parent, rbn); rb_insert_color(&skb->rbnode, &q->rb_fragments); } skb->ip_defrag_offset = offset; return IPFRAG_OK; } EXPORT_SYMBOL(inet_frag_queue_insert); void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); struct sk_buff **nextp; int delta; if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); if (!fp) return NULL; FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; else rb_replace_node(&skb->rbnode, &fp->rbnode, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); consume_skb(head); head = skb; } WARN_ON(head->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) return NULL; delta += head->truesize; if (delta) add_frag_mem_limit(q->fqdir, delta); /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; clone = alloc_skb(0, GFP_ATOMIC); if (!clone) return NULL; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->data_len = head->data_len - plen; clone->len = clone->data_len; head->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; add_frag_mem_limit(q->fqdir, clone->truesize); skb_shinfo(head)->frag_list = clone; nextp = &clone->next; } else { nextp = &skb_shinfo(head)->frag_list; } return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; int sum_truesize; skb_push(head, head->data - skb_network_header(head)); /* Traverse the tree in order, to build frag_list. */ fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; bool stolen; int delta; sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); if (try_coalesce && skb_try_coalesce(head, fp, &stolen, &delta)) { kfree_skb_partial(fp, stolen); } else { fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; head->truesize += fp->truesize; *nextp = fp; nextp = &fp->next; } fp = next_frag; } /* Move to the next run. */ if (rbn) { struct rb_node *rbnext = rb_next(rbn); fp = rb_to_skb(rbn); rb_erase(rbn, &q->rb_fragments); rbn = rbnext; } } sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; } EXPORT_SYMBOL(inet_frag_reasm_finish); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) { struct sk_buff *head, *skb; head = skb_rb_first(&q->rb_fragments); if (!head) return NULL; skb = FRAG_CB(head)->next_frag; if (skb) rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); else rb_erase(&head->rbnode, &q->rb_fragments); memset(&head->rbnode, 0, sizeof(head->rbnode)); barrier(); if (head == q->fragments_tail) q->fragments_tail = NULL; sub_frag_mem_limit(q->fqdir, head->truesize); return head; } EXPORT_SYMBOL(inet_frag_pull_head); |
| 7225 2357 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; ino_t ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf; /* Size of read buffer. */ size_t readbuf_size; /* Buffer for writing. */ char *write_buf; /* Size of write buffer. */ size_t writebuf_size; /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** Function prototypes. **********/ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ |
| 822 822 810 35 822 822 12954 12897 810 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 | // SPDX-License-Identifier: GPL-2.0 /* * SafeSetID Linux Security Module * * Author: Micah Morton <mortonm@chromium.org> * * Copyright (C) 2018 The Chromium OS Authors. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, as * published by the Free Software Foundation. * */ #define pr_fmt(fmt) "SafeSetID: " fmt #include <linux/lsm_hooks.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <uapi/linux/lsm.h> #include "lsm.h" /* Flag indicating whether initialization completed */ int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; /* Compute a decision for a transition from @src to @dst under @policy. */ enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy, kid_t src, kid_t dst) { struct setid_rule *rule; enum sid_policy_type result = SIDPOL_DEFAULT; if (policy->type == UID) { hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) { if (!uid_eq(rule->src_id.uid, src.uid)) continue; if (uid_eq(rule->dst_id.uid, dst.uid)) return SIDPOL_ALLOWED; result = SIDPOL_CONSTRAINED; } } else if (policy->type == GID) { hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) { if (!gid_eq(rule->src_id.gid, src.gid)) continue; if (gid_eq(rule->dst_id.gid, dst.gid)){ return SIDPOL_ALLOWED; } result = SIDPOL_CONSTRAINED; } } else { /* Should not reach here, report the ID as contrainsted */ result = SIDPOL_CONSTRAINED; } return result; } /* * Compute a decision for a transition from @src to @dst under the active * policy. */ static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type) { enum sid_policy_type result = SIDPOL_DEFAULT; struct setid_ruleset *pol; rcu_read_lock(); if (new_type == UID) pol = rcu_dereference(safesetid_setuid_rules); else if (new_type == GID) pol = rcu_dereference(safesetid_setgid_rules); else { /* Should not reach here */ result = SIDPOL_CONSTRAINED; rcu_read_unlock(); return result; } if (pol) { pol->type = new_type; result = _setid_policy_lookup(pol, src, dst); } rcu_read_unlock(); return result; } static int safesetid_security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { /* We're only interested in CAP_SETUID and CAP_SETGID. */ if (cap != CAP_SETUID && cap != CAP_SETGID) return 0; /* * If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we * want to let it go through here; the real security check happens later, in * the task_fix_set{u/g}id or task_fix_setgroups hooks. */ if ((opts & CAP_OPT_INSETID) != 0) return 0; switch (cap) { case CAP_SETUID: /* * If no policy applies to this task, allow the use of CAP_SETUID for * other purposes. */ if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*uid() (e.g. setting up userns uid mappings). */ pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n", __kuid_val(cred->uid)); return -EPERM; case CAP_SETGID: /* * If no policy applies to this task, allow the use of CAP_SETGID for * other purposes. */ if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*gid() (e.g. setting up userns gid mappings). */ pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n", __kgid_val(cred->gid)); return -EPERM; default: /* Error, the only capabilities were checking for is CAP_SETUID/GID */ return 0; } return 0; } /* * Check whether a caller with old credentials @old is allowed to switch to * credentials that contain @new_id. */ static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type) { bool permitted; /* If our old creds already had this ID in it, it's fine. */ if (new_type == UID) { if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) || uid_eq(new_id.uid, old->suid)) return true; } else if (new_type == GID){ if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) || gid_eq(new_id.gid, old->sgid)) return true; } else /* Error, new_type is an invalid type */ return false; /* * Transitions to new UIDs require a check against the policy of the old * RUID. */ permitted = setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED; if (!permitted) { if (new_type == UID) { pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n", __kuid_val(old->uid), __kuid_val(old->euid), __kuid_val(old->suid), __kuid_val(new_id.uid)); } else if (new_type == GID) { pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n", __kgid_val(old->gid), __kgid_val(old->egid), __kgid_val(old->sgid), __kgid_val(new_id.gid)); } else /* Error, new_type is an invalid type */ return false; } return permitted; } /* * Check whether there is either an exception for user under old cred struct to * set*uid to user under new cred struct, or the UID transition is allowed (by * Linux set*uid rules) even without CAP_SETUID. */ static int safesetid_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setuid restrictions for our old RUID. */ if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old) { int i; /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; get_group_info(new->group_info); for (i = 0; i < new->group_info->ngroups; i++) { if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) { put_group_info(new->group_info); /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } } put_group_info(new->group_info); return 0; } static const struct lsm_id safesetid_lsmid = { .name = "safesetid", .id = LSM_ID_SAFESETID, }; static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups), LSM_HOOK_INIT(capable, safesetid_security_capable) }; static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, ARRAY_SIZE(safesetid_security_hooks), &safesetid_lsmid); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; return 0; } DEFINE_LSM(safesetid_security_init) = { .init = safesetid_security_init, .name = "safesetid", }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_LOCAL64_H #define _ASM_GENERIC_LOCAL64_H #include <linux/percpu.h> #include <asm/types.h> /* * A signed long type for operations which are atomic for a single CPU. * Usually used in combination with per-cpu variables. * * This is the default implementation, which uses atomic64_t. Which is * rather pointless. The whole point behind local64_t is that some processors * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs * running on this CPU. local64_t allows exploitation of such capabilities. */ /* Implement in terms of atomics. */ #if BITS_PER_LONG == 64 #include <asm/local.h> typedef struct { local_t a; } local64_t; #define LOCAL64_INIT(i) { LOCAL_INIT(i) } #define local64_read(l) local_read(&(l)->a) #define local64_set(l,i) local_set((&(l)->a),(i)) #define local64_inc(l) local_inc(&(l)->a) #define local64_dec(l) local_dec(&(l)->a) #define local64_add(i,l) local_add((i),(&(l)->a)) #define local64_sub(i,l) local_sub((i),(&(l)->a)) #define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a)) #define local64_dec_and_test(l) local_dec_and_test(&(l)->a) #define local64_inc_and_test(l) local_inc_and_test(&(l)->a) #define local64_add_negative(i, l) local_add_negative((i), (&(l)->a)) #define local64_add_return(i, l) local_add_return((i), (&(l)->a)) #define local64_sub_return(i, l) local_sub_return((i), (&(l)->a)) #define local64_inc_return(l) local_inc_return(&(l)->a) static inline s64 local64_cmpxchg(local64_t *l, s64 old, s64 new) { return local_cmpxchg(&l->a, old, new); } static inline bool local64_try_cmpxchg(local64_t *l, s64 *old, s64 new) { return local_try_cmpxchg(&l->a, (long *)old, new); } #define local64_xchg(l, n) local_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a) /* Non-atomic variants, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ #define __local64_inc(l) local64_set((l), local64_read(l) + 1) #define __local64_dec(l) local64_set((l), local64_read(l) - 1) #define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) #define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) #else /* BITS_PER_LONG != 64 */ #include <linux/atomic.h> /* Don't use typedef: don't want them to be mixed with atomic_t's. */ typedef struct { atomic64_t a; } local64_t; #define LOCAL64_INIT(i) { ATOMIC_LONG_INIT(i) } #define local64_read(l) atomic64_read(&(l)->a) #define local64_set(l,i) atomic64_set((&(l)->a),(i)) #define local64_inc(l) atomic64_inc(&(l)->a) #define local64_dec(l) atomic64_dec(&(l)->a) #define local64_add(i,l) atomic64_add((i),(&(l)->a)) #define local64_sub(i,l) atomic64_sub((i),(&(l)->a)) #define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a)) #define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a) #define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a) #define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a)) #define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a)) #define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a)) #define local64_inc_return(l) atomic64_inc_return(&(l)->a) #define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n)) #define local64_try_cmpxchg(l, po, n) atomic64_try_cmpxchg((&(l)->a), (po), (n)) #define local64_xchg(l, n) atomic64_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a) /* Non-atomic variants, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ #define __local64_inc(l) local64_set((l), local64_read(l) + 1) #define __local64_dec(l) local64_set((l), local64_read(l) - 1) #define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) #define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) #endif /* BITS_PER_LONG != 64 */ #endif /* _ASM_GENERIC_LOCAL64_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H #include <linux/completion.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/types.h> /* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 #define CRYPTO_ALG_TYPE_LSKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_AKCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_SIG 0x00000007 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_HASH 0x0000000e #define CRYPTO_ALG_TYPE_SHASH 0x0000000e #define CRYPTO_ALG_TYPE_AHASH 0x0000000f #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 #define CRYPTO_ALG_DYING 0x00000040 #define CRYPTO_ALG_ASYNC 0x00000080 /* * Set if the algorithm (or an algorithm which it uses) requires another * algorithm of the same type to handle corner cases. */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 /* * Set if the algorithm has passed automated run-time testing. Note that * if there is no run-time testing for a given algorithm it is considered * to have passed. */ #define CRYPTO_ALG_TESTED 0x00000400 /* * Set if the algorithm is an instance that is built from templates. */ #define CRYPTO_ALG_INSTANCE 0x00000800 /* Set this bit if the algorithm provided is hardware accelerated but * not available to userspace via instruction set or so. */ #define CRYPTO_ALG_KERN_DRIVER_ONLY 0x00001000 /* * Mark a cipher as a service implementation only usable by another * cipher and never by a normal user of the kernel crypto API */ #define CRYPTO_ALG_INTERNAL 0x00002000 /* * Set if the algorithm has a ->setkey() method but can be used without * calling it first, i.e. there is a default key. */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 /* * Don't trigger module loading */ #define CRYPTO_NOLOAD 0x00008000 /* * The algorithm may allocate memory during request processing, i.e. during * encryption, decryption, or hashing. Users can request an algorithm with this * flag unset if they can't handle memory allocation failures. * * This flag is currently only implemented for algorithms of type "skcipher", * "aead", "ahash", "shash", and "cipher". Algorithms of other types might not * have this flag set even if they allocate memory. * * In some edge cases, algorithms can allocate memory regardless of this flag. * To avoid these cases, users must obey the following usage constraints: * skcipher: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - If the data were to be divided into chunks of size * crypto_skcipher_walksize() (with any remainder going at the end), no * chunk can cross a page boundary or a scatterlist element boundary. * aead: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - The first scatterlist element must contain all the associated data, * and its pages must be !PageHighMem. * - If the plaintext/ciphertext were to be divided into chunks of size * crypto_aead_walksize() (with the remainder going at the end), no chunk * can cross a page boundary or a scatterlist element boundary. * ahash: * - crypto_ahash_finup() must not be used unless the algorithm implements * ->finup() natively. */ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* * Mark an algorithm as a service implementation only usable by a * template and never by a normal user of the kernel crypto API. * This is intended to be used by algorithms that are themselves * not FIPS-approved but may instead be used to implement parts of * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). */ #define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 /* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 #define CRYPTO_TFM_REQ_MASK 0x000fff00 #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 /* * Miscellaneous stuff. */ #define CRYPTO_MAX_ALG_NAME 128 /* * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment * faults for C data types. On architectures that support non-cache coherent * DMA, such as ARM or arm64, it also takes into account the minimal alignment * that is required to ensure that the context struct member does not share any * cachelines with the rest of the struct. This is needed to ensure that cache * maintenance for non-coherent DMA (cache invalidation in particular) does not * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct crypto_tfm; struct crypto_type; struct module; typedef void (*crypto_completion_t)(void *req, int err); /** * DOC: Block Cipher Context Data Structures * * These data structures define the operating context for each block cipher * type. */ struct crypto_async_request { struct list_head list; crypto_completion_t complete; void *data; struct crypto_tfm *tfm; u32 flags; }; /** * DOC: Block Cipher Algorithm Definitions * * These data structures define modular crypto algorithm implementations, * managed via crypto_register_alg() and crypto_unregister_alg(). */ /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is * the smallest key length supported by this transformation * algorithm. This must be set to one of the pre-defined * values as this is not hardware specific. Possible values * for this field can be found via git grep "_MIN_KEY_SIZE" * include/crypto/ * @cia_max_keysize: Maximum key size supported by the transformation. This is * the largest key length supported by this transformation * algorithm. This must be set to one of the pre-defined values * as this is not hardware specific. Possible values for this * field can be found via git grep "_MAX_KEY_SIZE" * include/crypto/ * @cia_setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function * can be called multiple times during the existence of the * transformation object, so one must make sure the key is properly * reprogrammed into the hardware. This function is also * responsible for checking the key length for validity. * @cia_encrypt: Encrypt a single block. This function is used to encrypt a * single block of data, which must be @cra_blocksize big. This * always operates on a full @cra_blocksize and it is not possible * to encrypt a block of smaller size. The supplied buffers must * therefore also be at least of @cra_blocksize size. Both the * input and output buffers are always aligned to @cra_alignmask. * In case either of the input or output buffer supplied by user * of the crypto API is not aligned to @cra_alignmask, the crypto * API will re-align the buffers. The re-alignment means that a * new buffer will be allocated, the data will be copied into the * new buffer, then the processing will happen on the new buffer, * then the data will be copied back into the original buffer and * finally the new buffer will be freed. In case a software * fallback was put in place in the @cra_init call, this function * might need to use the fallback if the algorithm doesn't support * all of the key sizes. In case the key was stored in * transformation context, the key might need to be re-programmed * into the hardware in this function. This function shall not * modify the transformation context, as this function may be * called in parallel with the same transformation object. * @cia_decrypt: Decrypt a single block. This is a reverse counterpart to * @cia_encrypt, and the conditions are exactly the same. * * All fields are mandatory and must be filled. */ struct cipher_alg { unsigned int cia_min_keysize; unsigned int cia_max_keysize; int (*cia_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); void (*cia_encrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; /** * struct compress_alg - compression/decompression algorithm * @coa_compress: Compress a buffer of specified length, storing the resulting * data in the specified buffer. Return the length of the * compressed data in dlen. * @coa_decompress: Decompress the source buffer, storing the uncompressed * data in the specified buffer. The length of the data is * returned in dlen. * * All fields are mandatory. */ struct compress_alg { int (*coa_compress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int (*coa_decompress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); }; #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress /** * struct crypto_alg - definition of a cryptograpic cipher algorithm * @cra_flags: Flags describing this transformation. See include/linux/crypto.h * CRYPTO_ALG_* flags for the flags which go in here. Those are * used for fine-tuning the description of the transformation * algorithm. * @cra_blocksize: Minimum block size of this transformation. The size in bytes * of the smallest possible unit which can be transformed with * this algorithm. The users must respect this value. * In case of HASH transformation, it is possible for a smaller * block than @cra_blocksize to be passed to the crypto API for * transformation, in case of any other transformation type, an * error will be returned upon any attempt to transform smaller * than @cra_blocksize chunks. * @cra_ctxsize: Size of the operational context of the transformation. This * value informs the kernel crypto API about the memory size * needed to be allocated for the transformation context. * @cra_alignmask: For cipher, skcipher, lskcipher, and aead algorithms this is * 1 less than the alignment, in bytes, that the algorithm * implementation requires for input and output buffers. When * the crypto API is invoked with buffers that are not aligned * to this alignment, the crypto API automatically utilizes * appropriately aligned temporary buffers to comply with what * the algorithm needs. (For scatterlists this happens only if * the algorithm uses the skcipher_walk helper functions.) This * misalignment handling carries a performance penalty, so it is * preferred that algorithms do not set a nonzero alignmask. * Also, crypto API users may wish to allocate buffers aligned * to the alignmask of the algorithm being used, in order to * avoid the API having to realign them. Note: the alignmask is * not supported for hash algorithms and is always 0 for them. * @cra_priority: Priority of this transformation implementation. In case * multiple transformations with same @cra_name are available to * the Crypto API, the kernel will use the one with highest * @cra_priority. * @cra_name: Generic name (usable by multiple implementations) of the * transformation algorithm. This is the name of the transformation * itself. This field is used by the kernel when looking up the * providers of particular transformation. * @cra_driver_name: Unique name of the transformation provider. This is the * name of the provider of the transformation. This can be any * arbitrary value, but in the usual case, this contains the * name of the chip or provider and the name of the * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all * transformation types. There are multiple options, such as * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of * multiple structures. Depending on the type of transformation selected * by @cra_type and @cra_flags above, the associated structure must be * filled with callbacks. This field might be empty. This is the case * for ahash, shash. * @cra_init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right * after the transformation context was allocated. In case the * cryptographic hardware has some special requirements which need to * be handled by software, this function shall check for the precise * requirement of the transformation and put any software fallbacks * in place. * @cra_exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @cra_init, used to remove various changes set in * @cra_init. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. * See @struct @compress_alg. * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE * @cra_list: internally used * @cra_users: internally used * @cra_refcnt: internally used * @cra_destroy: internally used * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. */ struct crypto_alg { struct list_head cra_list; struct list_head cra_users; u32 cra_flags; unsigned int cra_blocksize; unsigned int cra_ctxsize; unsigned int cra_alignmask; int cra_priority; refcount_t cra_refcnt; char cra_name[CRYPTO_MAX_ALG_NAME]; char cra_driver_name[CRYPTO_MAX_ALG_NAME]; const struct crypto_type *cra_type; union { struct cipher_alg cipher; struct compress_alg compress; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); void (*cra_exit)(struct crypto_tfm *tfm); void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; } CRYPTO_MINALIGN_ATTR; /* * A helper struct for waiting for completion of async crypto ops */ struct crypto_wait { struct completion completion; int err; }; /* * Macro for declaring a crypto op async wait object on stack */ #define DECLARE_CRYPTO_WAIT(_wait) \ struct crypto_wait _wait = { \ COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 } /* * Async ops completion helper functioons */ void crypto_req_done(void *req, int err); static inline int crypto_wait_req(int err, struct crypto_wait *wait) { switch (err) { case -EINPROGRESS: case -EBUSY: wait_for_completion(&wait->completion); reinit_completion(&wait->completion); err = wait->err; break; } return err; } static inline void crypto_init_wait(struct crypto_wait *wait) { init_completion(&wait->completion); } /* * Algorithm query interface. */ int crypto_has_alg(const char *name, u32 type, u32 mask); /* * Transforms: user-instantiated objects which encapsulate algorithms * and core processing logic. Managed via crypto_alloc_*() and * crypto_free_*(), as well as the various helpers below. */ struct crypto_tfm { refcount_t refcnt; u32 crt_flags; int node; void (*exit)(struct crypto_tfm *tfm); struct crypto_alg *__crt_alg; void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_comp { struct crypto_tfm base; }; /* * Transform user interface. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); static inline void crypto_free_tfm(struct crypto_tfm *tfm) { return crypto_destroy_tfm(tfm, tfm); } /* * Transform helpers which query the underlying algorithm. */ static inline const char *crypto_tfm_alg_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_name; } static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_driver_name; } static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; } static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_alignmask; } static inline u32 crypto_tfm_get_flags(struct crypto_tfm *tfm) { return tfm->crt_flags; } static inline void crypto_tfm_set_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags |= flags; } static inline void crypto_tfm_clear_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags &= ~flags; } static inline unsigned int crypto_tfm_ctx_alignment(void) { struct crypto_tfm *tfm; return __alignof__(tfm->__crt_ctx); } static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; } static inline struct crypto_comp *crypto_alloc_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return __crypto_comp_cast(crypto_alloc_base(alg_name, type, mask)); } static inline struct crypto_tfm *crypto_comp_tfm(struct crypto_comp *tfm) { return &tfm->base; } static inline void crypto_free_comp(struct crypto_comp *tfm) { crypto_free_tfm(crypto_comp_tfm(tfm)); } static inline int crypto_has_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return crypto_has_alg(alg_name, type, mask); } static inline const char *crypto_comp_name(struct crypto_comp *tfm) { return crypto_tfm_alg_name(crypto_comp_tfm(tfm)); } int crypto_comp_compress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int crypto_comp_decompress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); #endif /* _LINUX_CRYPTO_H */ |
| 7 41 21 20 31 20 8 2 12 97 97 52 15 52 47 9 86 92 128 120 245 216 13 85 5 2 103 86 2 49 46 5 43 43 194 51 57 36 16 7 23 42 41 41 6 1 40 42 42 73 73 73 73 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* scm.c - Socket level control messages processing. * * Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Alignment and value checking mods by Craig Metz */ #include <linux/module.h> #include <linux/signal.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/io_uring.h> #include <linux/uaccess.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> #include <net/af_unix.h> /* * Only allow a user to send credentials, that they could set with * setu(g)id. */ static __inline__ int scm_check_creds(struct ucred *creds) { const struct cred *cred = current_cred(); kuid_t uid = make_kuid(cred->user_ns, creds->uid); kgid_t gid = make_kgid(cred->user_ns, creds->gid); if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; if ((creds->pid == task_tgid_vnr(current) || ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; } static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) { int *fdp = (int*)CMSG_DATA(cmsg); struct scm_fp_list *fpl = *fplp; struct file **fpp; int i, num; num = (cmsg->cmsg_len - sizeof(struct cmsghdr))/sizeof(int); if (num <= 0) return 0; if (num > SCM_MAX_FD) return -EINVAL; if (!fpl) { fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL_ACCOUNT); if (!fpl) return -ENOMEM; *fplp = fpl; fpl->count = 0; fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; if (fpl->count + num > fpl->max) return -EINVAL; /* * Verify the descriptors and increment the usage count. */ for (i=0; i< num; i++) { int fd = fdp[i]; struct file *file; if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } if (unix_get_socket(file)) fpl->count_unix++; *fpp++ = file; fpl->count++; } if (!fpl->user) fpl->user = get_uid(current_user()); return num; } void __scm_destroy(struct scm_cookie *scm) { struct scm_fp_list *fpl = scm->fp; int i; if (fpl) { scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); free_uid(fpl->user); kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct cmsghdr *cmsg; int err; for_each_cmsghdr(cmsg, msg) { err = -EINVAL; /* Verify that cmsg_len is at least sizeof(struct cmsghdr) */ /* The first check was omitted in <= 2.2.5. The reasoning was that parser checks cmsg_len in any case, so that additional check would be work duplication. But if cmsg_level is not SOL_SOCKET, we do not check for too short ancillary data object at all! Oops. OK, let's add it... */ if (!CMSG_OK(msg, cmsg)) goto error; if (cmsg->cmsg_level != SOL_SOCKET) continue; switch (cmsg->cmsg_type) { case SCM_RIGHTS: if (!ops || ops->family != PF_UNIX) goto error; err=scm_fp_copy(cmsg, &p->fp); if (err<0) goto error; break; case SCM_CREDENTIALS: { struct ucred creds; kuid_t uid; kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); err = scm_check_creds(&creds); if (err) goto error; p->creds.pid = creds.pid; if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; pid = find_get_pid(creds.pid); if (!pid) goto error; put_pid(p->pid); p->pid = pid; } err = -EINVAL; uid = make_kuid(current_user_ns(), creds.uid); gid = make_kgid(current_user_ns(), creds.gid); if (!uid_valid(uid) || !gid_valid(gid)) goto error; p->creds.uid = uid; p->creds.gid = gid; break; } default: goto error; } } if (p->fp && !p->fp->count) { kfree(p->fp); p->fp = NULL; } return 0; error: scm_destroy(p); return err; } EXPORT_SYMBOL(__scm_send); int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) { int cmlen = CMSG_LEN(len); if (msg->msg_flags & MSG_CMSG_COMPAT) return put_cmsg_compat(msg, level, type, len, data); if (!msg->msg_control || msg->msg_controllen < sizeof(struct cmsghdr)) { msg->msg_flags |= MSG_CTRUNC; return 0; /* XXX: return error? check spec. */ } if (msg->msg_controllen < cmlen) { msg->msg_flags |= MSG_CTRUNC; cmlen = msg->msg_controllen; } if (msg->msg_control_is_user) { struct cmsghdr __user *cm = msg->msg_control_user; check_object_size(data, cmlen - sizeof(*cm), true); if (!user_write_access_begin(cm, cmlen)) goto efault; unsafe_put_user(cmlen, &cm->cmsg_len, efault_end); unsafe_put_user(level, &cm->cmsg_level, efault_end); unsafe_put_user(type, &cm->cmsg_type, efault_end); unsafe_copy_to_user(CMSG_USER_DATA(cm), data, cmlen - sizeof(*cm), efault_end); user_write_access_end(); } else { struct cmsghdr *cm = msg->msg_control; cm->cmsg_level = level; cm->cmsg_type = type; cm->cmsg_len = cmlen; memcpy(CMSG_DATA(cm), data, cmlen - sizeof(*cm)); } cmlen = min(CMSG_SPACE(len), msg->msg_controllen); if (msg->msg_control_is_user) msg->msg_control_user += cmlen; else msg->msg_control += cmlen; msg->msg_controllen -= cmlen; return 0; efault_end: user_write_access_end(); efault: return -EFAULT; } EXPORT_SYMBOL(put_cmsg); void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping64); void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping); static int scm_max_fds(struct msghdr *msg) { if (msg->msg_controllen <= sizeof(struct cmsghdr)) return 0; return (msg->msg_controllen - sizeof(struct cmsghdr)) / sizeof(int); } void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm = (__force struct cmsghdr __user *)msg->msg_control_user; unsigned int o_flags = (msg->msg_flags & MSG_CMSG_CLOEXEC) ? O_CLOEXEC : 0; int fdmax = min_t(int, scm_max_fds(msg), scm->fp->count); int __user *cmsg_data = CMSG_USER_DATA(cm); int err = 0, i; /* no use for FD passing from kernel space callers */ if (WARN_ON_ONCE(!msg->msg_control_is_user)) return; if (msg->msg_flags & MSG_CMSG_COMPAT) { scm_detach_fds_compat(msg, scm); return; } for (i = 0; i < fdmax; i++) { err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } if (i > 0) { int cmlen = CMSG_LEN(i * sizeof(int)); err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_SPACE(i * sizeof(int)); if (msg->msg_controllen < cmlen) cmlen = msg->msg_controllen; msg->msg_control_user += cmlen; msg->msg_controllen -= cmlen; } } if (i < scm->fp->count || (scm->fp->count && fdmax <= 0)) msg->msg_flags |= MSG_CTRUNC; /* * All of the files that fit in the message have had their usage counts * incremented, so we just free the list. */ __scm_destroy(scm); } EXPORT_SYMBOL(scm_detach_fds); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) { struct scm_fp_list *new_fpl; int i; if (!fpl) return NULL; new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), GFP_KERNEL_ACCOUNT); if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); } return new_fpl; } EXPORT_SYMBOL(scm_fp_dup); |
| 3283 5914 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/idr.h * * 2002-10-18 written by Jim Houston jim.houston@ccur.com * Copyright (C) 2002 by Concurrent Computer Corporation * * Small id to pointer translation service avoiding fixed sized * tables. */ #ifndef __IDR_H__ #define __IDR_H__ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> struct idr { struct radix_tree_root idr_rt; unsigned int idr_base; unsigned int idr_next; }; /* * The IDR API does not expose the tagging functionality of the radix tree * to users. Use tag 0 to track whether a node has free space below it. */ #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ #define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ (1 << (ROOT_TAG_SHIFT + IDR_FREE))) #define IDR_INIT_BASE(name, base) { \ .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ #define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** * DEFINE_IDR() - Define a statically-allocated IDR. * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator * @idr: idr handle * * The value returned is the value that will be next returned from * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ static inline unsigned int idr_get_cursor(const struct idr *idr) { return READ_ONCE(idr->idr_next); } /** * idr_set_cursor - Set the current position of the cyclic allocator * @idr: idr handle * @val: new position * * The next call to idr_alloc_cyclic() will return @val if it is free * (otherwise the search will start from this position). */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { WRITE_ONCE(idr->idr_next, val); } /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) * * idr_find() is able to be called locklessly, using RCU. The caller must * ensure calls to this function are made within rcu_read_lock() regions. * Other readers (lock-free or otherwise) and modifications may be running * concurrently. * * It is still required that the caller manage the synchronization and * lifetimes of the items. So if RCU lock-free lookups are used, typically * this would mean that the items have their own locks, or are amenable to * lock-free access; and that the items are freed by RCU (or only freed after * having been deleted from the idr tree *and* a synchronize_rcu() grace * period). */ #define idr_lock(idr) xa_lock(&(idr)->idr_rt) #define idr_unlock(idr) xa_unlock(&(idr)->idr_rt) #define idr_lock_bh(idr) xa_lock_bh(&(idr)->idr_rt) #define idr_unlock_bh(idr) xa_unlock_bh(&(idr)->idr_rt) #define idr_lock_irq(idr) xa_lock_irq(&(idr)->idr_rt) #define idr_unlock_irq(idr) xa_unlock_irq(&(idr)->idr_rt) #define idr_lock_irqsave(idr, flags) \ xa_lock_irqsave(&(idr)->idr_rt, flags) #define idr_unlock_irqrestore(idr, flags) \ xa_unlock_irqrestore(&(idr)->idr_rt, flags) void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id, unsigned long max, gfp_t); int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t); void *idr_remove(struct idr *, unsigned long id); void *idr_find(const struct idr *, unsigned long id); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); void *idr_get_next_ul(struct idr *, unsigned long *nextid); void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); /** * idr_init_base() - Initialise an IDR. * @idr: IDR handle. * @base: The base value for the IDR. * * This variation of idr_init() creates an IDR which will allocate IDs * starting at %base. */ static inline void idr_init_base(struct idr *idr, int base) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); idr->idr_base = base; idr->idr_next = 0; } /** * idr_init() - Initialise an IDR. * @idr: IDR handle. * * Initialise a dynamically allocated IDR. To initialise a * statically allocated IDR, use DEFINE_IDR(). */ static inline void idr_init(struct idr *idr) { idr_init_base(idr, 0); } /** * idr_is_empty() - Are there any IDs allocated? * @idr: IDR handle. * * Return: %true if any IDs have been allocated from this IDR. */ static inline bool idr_is_empty(const struct idr *idr) { return radix_tree_empty(&idr->idr_rt) && radix_tree_tagged(&idr->idr_rt, IDR_FREE); } /** * idr_preload_end - end preload section started with idr_preload() * * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ static inline void idr_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } /** * idr_for_each_entry() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_ul(idr, entry, tmp, id) \ for (tmp = 0, id = 0; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. */ #define idr_for_each_entry_continue(idr, entry, id) \ for ((entry) = idr_get_next((idr), &(id)); \ entry; \ ++id, (entry) = idr_get_next((idr), &(id))) /** * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. * After normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ for (tmp = id; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; struct ida { struct xarray xa; }; #define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) #define IDA_INIT(name) { \ .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); void ida_destroy(struct ida *ida); /** * ida_alloc() - Allocate an unused ID. * @ida: IDA handle. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc(struct ida *ida, gfp_t gfp) { return ida_alloc_range(ida, 0, ~0, gfp); } /** * ida_alloc_min() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) { return ida_alloc_range(ida, min, ~0, gfp); } /** * ida_alloc_max() - Allocate an unused ID. * @ida: IDA handle. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and @max, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) { return ida_alloc_range(ida, 0, max, gfp); } static inline void ida_init(struct ida *ida) { xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } /* * ida_simple_get() and ida_simple_remove() are deprecated. Use * ida_alloc() and ida_free() instead respectively. */ #define ida_simple_get(ida, start, end, gfp) \ ida_alloc_range(ida, start, (end) - 1, gfp) #define ida_simple_remove(ida, id) ida_free(ida, id) static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); } #endif /* __IDR_H__ */ |
| 1027 896 896 896 896 1027 1027 1027 1027 29 728 44 740 740 740 740 1040 99 896 896 896 896 896 896 896 896 989 989 989 706 989 989 954 989 978 896 989 989 918 918 914 1044 1043 1044 1044 1041 934 740 1194 1194 1194 1194 1194 1194 97 97 97 97 1194 1194 1194 97 97 97 97 97 1035 1035 1035 1035 1035 1035 1035 1035 1035 1030 1030 1030 1030 1030 888 1027 1027 1030 1030 1030 1030 1030 1030 1342 1342 1342 1159 1159 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; if (bg_thresh >= thresh) bg_thresh = thresh / 2; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; return dirty; } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } static int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; unsigned long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; unsigned long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty throttling threshold * @dtc: dirty_throttle_context of interest * * Note that balance_dirty_pages() will only seriously take it as a hard limit * when sleeping max_pause per page is not enough to keep the dirty pages under * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this BDI's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb), .thresh = thresh }; return __wb_calc_thresh(&gdtc); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded != wb->dirty_exceeded) wb->dirty_exceeded = dirty_exceeded; if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); wb->dirty_sleep = now; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; unsigned long reclaimable; unsigned long thresh; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; } return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, {} }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by write_cache_pages * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is * that write_cache_pages (or whoever calls this function) will then use * TOWRITE tag to identify pages eligible for writeback. This mechanism is * used to avoid livelocking of writeback by a process steadily creating new * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. * * To avoid livelocks (when other process dirties new pages), we first tag * pages which should be written back with TOWRITE tag and only then start * writing them. For data-integrity sync we have to be careful so that we do * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). * * To avoid deadlocks between range_cyclic writeback and callers that hold * pages in PageWriteback to aggregate IO until write_cache_pages() returns, * we do not loop back to the start of the file. Doing so causes a page * lock/page writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping back to the start * of the file violates that rule and causes deadlocks. * * Return: %0 on success, negative error code otherwise */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; int error; struct folio_batch fbatch; int nr_folios; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; xa_mark_t tag; folio_batch_init(&fbatch); if (wbc->range_cyclic) { index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { tag_pages_for_writeback(mapping, index, end); tag = PAGECACHE_TAG_TOWRITE; } else { tag = PAGECACHE_TAG_DIRTY; } done_index = index; while (!done && (index <= end)) { int i; nr_folios = filemap_get_folios_tag(mapping, &index, end, tag, &fbatch); if (nr_folios == 0) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; unsigned long nr; done_index = folio->index; folio_lock(folio); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data integrity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(folio->mapping != mapping)) { continue_unlock: folio_unlock(folio); continue; } if (!folio_test_dirty(folio)) { /* someone wrote it for us */ goto continue_unlock; } if (folio_test_writeback(folio)) { if (wbc->sync_mode != WB_SYNC_NONE) folio_wait_writeback(folio); else goto continue_unlock; } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); error = writepage(folio, wbc, data); nr = folio_nr_pages(folio); if (unlikely(error)) { /* * Handle errors according to the type of * writeback. There's no need to continue for * background writeback. Just push done_index * past this page so media errors won't choke * writeout for the entire file. For integrity * writeback, we must process the entire dirty * set regardless of errors because the fs may * still have state to clear for each page. In * that case we continue processing and return * the first error. */ if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } else if (wbc->sync_mode != WB_SYNC_ALL) { ret = error; done_index = folio->index + nr; done = 1; break; } if (!ret) ret = error; } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ wbc->nr_to_write -= nr; if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } folio_batch_release(&fbatch); cond_resched(); } /* * If we hit the last page and there is more work to be done: wrap * back the index back to the start of the file for the next * time we are called. */ if (wbc->range_cyclic && !done) done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } EXPORT_SYMBOL(write_cache_pages); static int writepage_cb(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(&folio->page, wbc); mapping_set_error(mapping, ret); return ret; } int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); } else if (mapping->a_ops->writepage) { struct blk_plug plug; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, writepage_cb, mapping); blk_finish_plug(&plug); } else { /* deal with chardevs and other special files */ ret = 0; } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * Caller must hold folio_memcg_lock(). * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache, and mark * the inode dirty. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold folio_memcg_lock(). Most callers have the folio * locked. A few have the folio blocked from truncation through other * means (eg zap_vma_pages() has it mapped and is holding the page table * lock). This can also be called from mark_buffer_dirty(), which I * cannot prove is always protected against truncate. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { folio_memcg_lock(folio); if (folio_test_set_dirty(folio)) { folio_memcg_unlock(folio); return false; } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); folio_memcg_unlock(folio); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 12 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * TCPv6 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, ip6_gro_compute_pseudo)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } return tcp_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; tcp_gro_complete(skb); return 0; } static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct tcphdr *th; if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up pseudo header, usually expect stack to have done * this. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); } return tcp_gso_segment(skb, features); } static const struct net_offload tcpv6_offload = { .callbacks = { .gso_segment = tcp6_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, }; int __init tcpv6_offload_init(void) { return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); } |
| 12 12 12 12 4 4 79 78 1 3 1 2 7 185 185 283 283 283 283 283 283 283 283 127 64 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/rcupdate.h> #include <net/tcp.h> void tcp_fastopen_init_key_once(struct net *net) { u8 key[TCP_FASTOPEN_KEY_LENGTH]; struct tcp_fastopen_context *ctxt; rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) { rcu_read_unlock(); return; } rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. * * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); tcp_fastopen_reset_cipher(net, NULL, key, NULL); } static void tcp_fastopen_ctx_free(struct rcu_head *head) { struct tcp_fastopen_context *ctx = container_of(head, struct tcp_fastopen_context, rcu); kfree_sensitive(ctx); } void tcp_fastopen_destroy_cipher(struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference_protected( inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); if (ctx) call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); } void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; ctxt = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, NULL); if (ctxt) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key) { struct tcp_fastopen_context *ctx, *octx; struct fastopen_queue *q; int err = 0; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto out; } ctx->key[0].key[0] = get_unaligned_le64(primary_key); ctx->key[0].key[1] = get_unaligned_le64(primary_key + 8); if (backup_key) { ctx->key[1].key[0] = get_unaligned_le64(backup_key); ctx->key[1].key[1] = get_unaligned_le64(backup_key + 8); ctx->num = 2; } else { ctx->num = 1; } if (sk) { q = &inet_csk(sk)->icsk_accept_queue.fastopenq; octx = xchg((__force struct tcp_fastopen_context **)&q->ctx, ctx); } else { octx = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, ctx); } if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); out: return err; } int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key) { struct tcp_fastopen_context *ctx; int n_keys = 0, i; rcu_read_lock(); if (icsk) ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); else ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctx) { n_keys = tcp_fastopen_context_len(ctx); for (i = 0; i < n_keys; i++) { put_unaligned_le64(ctx->key[i].key[0], key + (i * 2)); put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1); } } rcu_read_unlock(); return n_keys; } static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, struct sk_buff *syn, const siphash_key_t *key, struct tcp_fastopen_cookie *foc) { BUILD_BUG_ON(TCP_FASTOPEN_COOKIE_SIZE != sizeof(u64)); if (req->rsk_ops->family == AF_INET) { const struct iphdr *iph = ip_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&iph->saddr, sizeof(iph->saddr) + sizeof(iph->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #if IS_ENABLED(CONFIG_IPV6) if (req->rsk_ops->family == AF_INET6) { const struct ipv6hdr *ip6h = ipv6_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&ip6h->saddr, sizeof(ip6h->saddr) + sizeof(ip6h->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #endif return false; } /* Generate the fastopen cookie by applying SipHash to both the source and * destination addresses. */ static void tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (ctx) __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[0], foc); rcu_read_unlock(); } /* If an incoming SYN or SYNACK frame contains a payload and/or FIN, * queue this additional data / FIN. */ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb_dst_drop(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects * skb->len to include the tcp_hdrlen. Hence, it should * be called before __skb_pull(). */ tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; __skb_queue_tail(&sk->sk_receive_queue, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, * as we certainly are not changing upper 32bit value (0) */ tp->bytes_received = skb->len; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); } /* returns 0 - no key match, 1 for primary, 2 for backup */ static int tcp_fastopen_cookie_gen_check(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *orig, struct tcp_fastopen_cookie *valid_foc) { struct tcp_fastopen_cookie search_foc = { .len = -1 }; struct tcp_fastopen_cookie *foc = valid_foc; struct tcp_fastopen_context *ctx; int i, ret = 0; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (!ctx) goto out; for (i = 0; i < tcp_fastopen_context_len(ctx); i++) { __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[i], foc); if (tcp_fastopen_cookie_match(foc, orig)) { ret = i + 1; goto out; } foc = &search_foc; } out: rcu_read_unlock(); return ret; } static struct sock *tcp_fastopen_create_child(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; struct sock *child; bool own_req; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, NULL, &own_req); if (!child) return NULL; spin_lock(&queue->fastopenq.lock); queue->fastopenq.qlen++; spin_unlock(&queue->fastopenq.lock); /* Initialize the child socket. Have to fix some values to take * into account the child is a Fast Open socket and is created * only out of the bits carried in the SYN packet. */ tp = tcp_sk(child); rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash * because it's been added to the accept queue directly. */ req->timeout = tcp_timeout_init(child); inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, req->timeout, TCP_RTO_MAX); refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ return child; } static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying * to validating the cookie in order to avoid burning CPU cycles * unnecessarily. * * XXX (TFO) - The implication of checking the max_qlen before * processing a cookie request is that clients can't differentiate * between qlen overflow causing Fast Open to be disabled * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; max_qlen = READ_ONCE(fastopenq->max_qlen); if (max_qlen == 0) return false; if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); spin_unlock(&fastopenq->lock); return false; } fastopenq->rskq_rst_head = req1->dl_next; fastopenq->qlen--; spin_unlock(&fastopenq->lock); reqsk_put(req1); } return true; } static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } /* Returns true if we should perform Fast Open on the SYN. The cookie (foc) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len == 0) { /* Client requests a cookie. */ tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc); } else if (foc->len > 0) { ret = tcp_fastopen_cookie_gen_check(sk, req, skb, foc, &valid_foc); if (!ret) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else { /* Cookie is valid. Create a (full) child socket to * accept the data in SYN before returning a SYN-ACK to * ack the data. If we fail to create the socket, fall * back and ack the ISN only but includes the same * cookie. * * Note: Data-less SYN with valid cookie is allowed to * send data in SYN_RECV state. */ fastopen: child = tcp_fastopen_create_child(sk, skb, req); if (child) { if (ret == 2) { valid_foc.exp = foc->exp; *foc = valid_foc; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEALTKEY); } else { foc->len = -1; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); return child; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } } valid_foc.exp = foc->exp; *foc = valid_foc; return NULL; } bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { const struct dst_entry *dst; tcp_fastopen_cache_get(sk, mss, cookie); /* Firewall blackhole issue check */ if (tcp_fastopen_active_should_disable(sk)) { cookie->len = -1; return false; } dst = __sk_dst_get(sk); if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) { cookie->len = -1; return true; } if (cookie->len > 0) return true; tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE; return false; } /* This function checks if we want to defer sending SYN until the first * write(). We defer under the following conditions: * 1. fastopen_connect sockopt is set * 2. we have a valid cookie * Return value: return true if we want to defer until application writes data * return false if we want to send out SYN immediately */ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) { struct tcp_fastopen_cookie cookie = { .len = 0 }; struct tcp_sock *tp = tcp_sk(sk); u16 mss; if (tp->fastopen_connect && !tp->fastopen_req) { if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { inet_set_bit(DEFER_CONNECT, sk); return true; } /* Alloc fastopen_req in order for FO option to be included * in SYN */ tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req), sk->sk_allocation); if (tp->fastopen_req) tp->fastopen_req->cookie = cookie; else *err = -ENOBUFS; } return false; } EXPORT_SYMBOL(tcp_fastopen_defer_connect); /* * The following code block is to deal with middle box issues with TFO: * Middlebox firewall issues can potentially cause server's data being * blackholed after a successful 3WHS using TFO. * The proposed solution is to disable active TFO globally under the * following circumstances: * 1. client side TFO socket receives out of order FIN * 2. client side TFO socket receives out of order RST * 3. client side TFO socket has timed out three times consecutively during * or after handshake * We disable active side TFO globally for 1hr at first. Then if it * happens again, we disable it for 2h, then 4h, 8h, ... * And we reset the timeout back to 1hr when we see a successful active * TFO connection with data exchanges. */ /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)) return; /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). * We want net->ipv4.tfo_active_disable_stamp to be updated first. */ smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable * Return true if we are still in the active TFO disable period * Return false if timeout already expired and we should use active TFO */ bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout); unsigned long timeout; int tfo_da_times; int multiplier; if (!tfo_bh_timeout) return false; tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); if (!tfo_da_times) return false; /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ smp_rmb(); /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + multiplier * tfo_bh_timeout * HZ; if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO * condition and reset tfo_active_disable_times */ tcp_sk(sk)->syn_fastopen_ch = 1; return false; } /* Disable active TFO if FIN is the only packet in the ofo queue * and no data is received. * Also check if we can reset tfo_active_disable_times if data is * received successfully on a marked active TFO sockets opened on * a non-loopback interface */ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst; struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { skb = skb_rb_first(&tp->out_of_order_queue); if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; } } } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired) { u32 timeouts = inet_csk(sk)->icsk_retransmits; struct tcp_sock *tp = tcp_sk(sk); /* Broken middle-boxes may black-hole Fast Open connection during or * even after the handshake. Be extremely conservative and pause * Fast Open globally after hitting the third consecutive timeout or * exceeding the configured timeout limit. */ if ((tp->syn_fastopen || tp->syn_data || tp->syn_data_acked) && (timeouts == 2 || (timeouts < 2 && expired))) { tcp_fastopen_active_disable(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); } } |
| 8 8 8 8 8 8 8 2 4 3 4 2 2 8 8 8 8 8 5 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm_input.c * * Changes: * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/bottom_half.h> #include <linux/cache.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/percpu.h> #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/dst_metadata.h> #include "xfrm_inout.h" struct xfrm_trans_tasklet { struct work_struct work; spinlock_t queue_lock; struct sk_buff_head queue; }; struct xfrm_trans_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); struct net *net; }; #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1]; static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev; static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family > AF_INET6)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_input_afinfo_lock); if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) err = -EEXIST; else rcu_assign_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], afinfo); spin_unlock_bh(&xfrm_input_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_input_register_afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; spin_lock_bh(&xfrm_input_afinfo_lock); if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) { if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo)) err = -EINVAL; else RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL); } spin_unlock_bh(&xfrm_input_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_input_unregister_afinfo); static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(u8 family, bool is_ipip) { const struct xfrm_input_afinfo *afinfo; if (WARN_ON_ONCE(family > AF_INET6)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_input_afinfo[is_ipip][family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol, int err) { bool is_ipip = (protocol == IPPROTO_IPIP || protocol == IPPROTO_IPV6); const struct xfrm_input_afinfo *afinfo; int ret; afinfo = xfrm_input_get_afinfo(family, is_ipip); if (!afinfo) return -EAFNOSUPPORT; ret = afinfo->callback(skb, protocol, err); rcu_read_unlock(); return ret; } struct sec_path *secpath_set(struct sk_buff *skb) { struct sec_path *sp, *tmp = skb_ext_find(skb, SKB_EXT_SEC_PATH); sp = skb_ext_add(skb, SKB_EXT_SEC_PATH); if (!sp) return NULL; if (tmp) /* reused existing one (was COW'd if needed) */ return sp; /* allocated new secpath */ memset(sp->ovec, 0, sizeof(sp->ovec)); sp->olen = 0; sp->len = 0; sp->verified_cnt = 0; return sp; } EXPORT_SYMBOL(secpath_set); /* Fetch spi and seq from ipsec header */ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { int offset, offset_seq; int hlen; switch (nexthdr) { case IPPROTO_AH: hlen = sizeof(struct ip_auth_hdr); offset = offsetof(struct ip_auth_hdr, spi); offset_seq = offsetof(struct ip_auth_hdr, seq_no); break; case IPPROTO_ESP: hlen = sizeof(struct ip_esp_hdr); offset = offsetof(struct ip_esp_hdr, spi); offset_seq = offsetof(struct ip_esp_hdr, seq_no); break; case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; *spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2))); *seq = 0; return 0; default: return 1; } if (!pskb_may_pull(skb, hlen)) return -EINVAL; *spi = *(__be32 *)(skb_transport_header(skb) + offset); *seq = *(__be32 *)(skb_transport_header(skb) + offset_seq); return 0; } EXPORT_SYMBOL(xfrm_parse_spi); static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) { struct iphdr *iph; int optlen = 0; int err = -EINVAL; skb->protocol = htons(ETH_P_IP); if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) { struct ip_beet_phdr *ph; int phlen; if (!pskb_may_pull(skb, sizeof(*ph))) goto out; ph = (struct ip_beet_phdr *)skb->data; phlen = sizeof(*ph) + ph->padlen; optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen); if (optlen < 0 || optlen & 3 || optlen > 250) goto out; XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr; if (!pskb_may_pull(skb, phlen)) goto out; __skb_pull(skb, phlen); } skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); iph = ip_hdr(skb); iph->ihl += optlen / 4; iph->tot_len = htons(skb->len); iph->daddr = x->sel.daddr.a4; iph->saddr = x->sel.saddr.a4; iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); err = 0; out: return err; } static void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) IP_ECN_set_ce(inner_iph); } static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; skb->protocol = htons(ETH_P_IP); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); if (skb->mac_len) eth_hdr(skb)->h_proto = skb->protocol; err = 0; out: return err; } static void ipip6_ecn_decapsulate(struct sk_buff *skb) { struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) IP6_ECN_set_ce(skb, inner_iph); } static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; skb->protocol = htons(ETH_P_IPV6); if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); if (skb->mac_len) eth_hdr(skb)->h_proto = skb->protocol; err = 0; out: return err; } static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; int size = sizeof(struct ipv6hdr); int err; skb->protocol = htons(ETH_P_IPV6); err = skb_cow_head(skb, size + skb->mac_len); if (err) goto out; __skb_push(skb, size); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(skb->len - size); ip6h->daddr = x->sel.daddr.in6; ip6h->saddr = x->sel.saddr.in6; err = 0; out: return err; } /* Remove encapsulation header. * * The IP header will be moved over the top of the encapsulation * header. * * On entry, the transport header shall point to where the IP header * should be and the network header shall be set to where the IP * header currently is. skb->data shall point to the start of the * payload. */ static int xfrm_inner_mode_encap_remove(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.mode) { case XFRM_MODE_BEET: switch (x->sel.family) { case AF_INET: return xfrm4_remove_beet_encap(x, skb); case AF_INET6: return xfrm6_remove_beet_encap(x, skb); } break; case XFRM_MODE_TUNNEL: switch (XFRM_MODE_SKB_CB(skb)->protocol) { case IPPROTO_IPIP: return xfrm4_remove_tunnel_encap(x, skb); case IPPROTO_IPV6: return xfrm6_remove_tunnel_encap(x, skb); break; } return -EINVAL; } WARN_ON_ONCE(1); return -EOPNOTSUPP; } static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.family) { case AF_INET: xfrm4_extract_header(skb); break; case AF_INET6: xfrm6_extract_header(skb); break; default: WARN_ON_ONCE(1); return -EAFNOSUPPORT; } return xfrm_inner_mode_encap_remove(x, skb); } /* Remove encapsulation header. * * The IP header will be moved over the top of the encapsulation header. * * On entry, skb_transport_header() shall point to where the IP header * should be and skb_network_header() shall be set to where the IP header * currently is. skb->data shall point to the start of the payload. */ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); skb_reset_transport_header(skb); return 0; } static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); skb->network_header = skb->transport_header; } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); return 0; #else WARN_ON_ONCE(1); return -EAFNOSUPPORT; #endif } static int xfrm_inner_mode_input(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: return xfrm_prepare_input(x, skb); case XFRM_MODE_TRANSPORT: if (x->props.family == AF_INET) return xfrm4_transport_input(x, skb); if (x->props.family == AF_INET6) return xfrm6_transport_input(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: WARN_ON_ONCE(1); break; default: WARN_ON_ONCE(1); break; } return -EOPNOTSUPP; } int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; struct net *net = dev_net(skb->dev); int err; __be32 seq; __be32 seq_hi; struct xfrm_state *x = NULL; xfrm_address_t *daddr; u32 mark = skb->mark; unsigned int family = AF_UNSPEC; int decaps = 0; int async = 0; bool xfrm_gro = false; bool crypto_done = false; struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) { x = xfrm_input_state(skb); if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); if (encap_type == -1) dev_put(skb->dev); goto drop; } family = x->props.family; /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { async = 1; seq = XFRM_SKB_CB(skb)->seq.input.low; goto resume; } /* GRO call */ seq = XFRM_SPI_SKB_CB(skb)->seq; if (xo && (xo->flags & CRYPTO_DONE)) { crypto_done = true; family = XFRM_SPI_SKB_CB(skb)->family; if (!(xo->status & CRYPTO_SUCCESS)) { if (xo->status & (CRYPTO_TRANSPORT_AH_AUTH_FAILED | CRYPTO_TRANSPORT_ESP_AUTH_FAILED | CRYPTO_TUNNEL_AH_AUTH_FAILED | CRYPTO_TUNNEL_ESP_AUTH_FAILED)) { xfrm_audit_state_icvfail(x, skb, x->type->proto); x->stats.integrity_failed++; XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop; } if (xo->status & CRYPTO_INVALID_PROTOCOL) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } if (xfrm_parse_spi(skb, nexthdr, &spi, &seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } } goto lock; } family = XFRM_SPI_SKB_CB(skb)->family; /* if tunnel is present override skb->mark value with tunnel i_key */ switch (family) { case AF_INET: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); break; case AF_INET6: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); break; } sp = secpath_set(skb); if (!sp) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } seq = 0; if (!spi && xfrm_parse_spi(skb, nexthdr, &spi, &seq)) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } daddr = (xfrm_address_t *)(skb_network_header(skb) + XFRM_SPI_SKB_CB(skb)->daddroff); do { sp = skb_sec_path(skb); if (sp->len == XFRM_MAX_DEPTH) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; } skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } lock: spin_lock(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); goto drop_unlock; } if ((x->encap ? x->encap->encap_type : 0) != encap_type) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); goto drop_unlock; } if (xfrm_replay_check(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } if (xfrm_state_check_expire(x)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED); goto drop_unlock; } spin_unlock(&x->lock); if (xfrm_tunnel_check(skb, x, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } seq_hi = htonl(xfrm_replay_seqhi(x, seq)); XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; dev_hold(skb->dev); if (crypto_done) nexthdr = x->type_offload->input_tail(x, skb); else nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: dev_put(skb->dev); spin_lock(&x->lock); if (nexthdr < 0) { if (nexthdr == -EBADMSG) { xfrm_audit_state_icvfail(x, skb, x->type->proto); x->stats.integrity_failed++; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop_unlock; } /* only the first xfrm gets the encap type */ encap_type = 0; if (xfrm_replay_recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } xfrm_replay_advance(x, seq); x->curlft.bytes += skb->len; x->curlft.packets++; x->lastused = ktime_get_real_seconds(); spin_unlock(&x->lock); XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; if (xfrm_inner_mode_input(x, skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) { decaps = 1; break; } /* * We need the inner address. However, we only get here for * transport mode so the outer address is identical. */ daddr = &x->id.daddr; family = x->props.family; err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } crypto_done = false; } while (!err); err = xfrm_rcv_cb(skb, family, x->type->proto, 0); if (err) goto drop; nf_reset_ct(skb); if (decaps) { sp = skb_sec_path(skb); if (sp) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return 0; } else { xo = xfrm_offload(skb); if (xo) xfrm_gro = xo->flags & XFRM_GRO; err = -EAFNOSUPPORT; rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(x->props.family); if (likely(afinfo)) err = afinfo->transport_finish(skb, xfrm_gro || async); rcu_read_unlock(); if (xfrm_gro) { sp = skb_sec_path(skb); if (sp) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return err; } return err; } drop_unlock: spin_unlock(&x->lock); drop: xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1); kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm_input); int xfrm_input_resume(struct sk_buff *skb, int nexthdr) { return xfrm_input(skb, nexthdr, 0, -1); } EXPORT_SYMBOL(xfrm_input_resume); static void xfrm_trans_reinject(struct work_struct *work) { struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work); struct sk_buff_head queue; struct sk_buff *skb; __skb_queue_head_init(&queue); spin_lock_bh(&trans->queue_lock); skb_queue_splice_init(&trans->queue, &queue); spin_unlock_bh(&trans->queue_lock); local_bh_disable(); while ((skb = __skb_dequeue(&queue))) XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net, NULL, skb); local_bh_enable(); } int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)) { struct xfrm_trans_tasklet *trans; trans = this_cpu_ptr(&xfrm_trans_tasklet); if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); XFRM_TRANS_SKB_CB(skb)->finish = finish; XFRM_TRANS_SKB_CB(skb)->net = net; spin_lock_bh(&trans->queue_lock); __skb_queue_tail(&trans->queue, skb); spin_unlock_bh(&trans->queue_lock); schedule_work(&trans->work); return 0; } EXPORT_SYMBOL(xfrm_trans_queue_net); int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)) { return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish); } EXPORT_SYMBOL(xfrm_trans_queue); void __init xfrm_input_init(void) { int err; int i; init_dummy_netdev(&xfrm_napi_dev); err = gro_cells_init(&gro_cells, &xfrm_napi_dev); if (err) gro_cells.cells = NULL; for_each_possible_cpu(i) { struct xfrm_trans_tasklet *trans; trans = &per_cpu(xfrm_trans_tasklet, i); spin_lock_init(&trans->queue_lock); __skb_queue_head_init(&trans->queue); INIT_WORK(&trans->work, xfrm_trans_reinject); } } |
| 1 1 1 1 27 25 2 1 1 27 27 27 27 27 27 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> #include "futex.h" /* * READ this before attempting to hack on futexes! * * Basic futex operation and ordering guarantees * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires * the hash bucket lock. After that it reads the futex user space value * again and verifies that the data has not changed. If it has not changed * it enqueues itself into the hash bucket, releases the hash bucket lock * and schedules. * * The waker side modifies the user space value of the futex and calls * futex_wake(). This function computes the hash bucket and acquires the * hash bucket lock. Then it looks for waiters on that futex in the hash * bucket and wakes them. * * In futex wake up scenarios where no tasks are blocked on a futex, taking * the hb spinlock can be avoided and simply return. In order for this * optimization to work, ordering guarantees must exist so that the waiter * being added to the list is acknowledged when the list is concurrently being * checked by the waker, avoiding scenarios like the following: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * uval = *futex; * *futex = newval; * sys_futex(WAKE, futex); * futex_wake(futex); * if (queue_empty()) * return; * if (uval == val) * lock(hash_bucket(futex)); * queue(); * unlock(hash_bucket(futex)); * schedule(); * * This would cause the waiter on CPU 0 to wait forever because it * missed the transition of the user space value from val to newval * and the waker did not find the waiter in the hash bucket queue. * * The correct serialization ensures that a waiter either observes * the changed user space value before blocking or is woken by a * concurrent waker: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * * waiters++; (a) * smp_mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | * | * uval = *futex; | * | *futex = newval; * | sys_futex(WAKE, futex); * | futex_wake(futex); * | * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); * else wake_waiters(futex); * waiters--; (b) unlock(hash_bucket(futex)); * * Where (A) orders the waiters increment and the futex value read through * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write * to futex and the waiters read (see futex_hb_waiters_pending()). * * This yields the following case (where X:=waiters, Y:=futex): * * X = Y = 0 * * w[X]=1 w[Y]=1 * MB MB * r[Y]=y r[X]=x * * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. * * Note that a new waiter is accounted for in (a) even when it is possible that * the wait call can return error, in which case we backtrack from it in (b). * Refer to the comment in futex_q_lock(). * * Similarly, in order to account for waiters being requeued on another * address we always increment the waiters for the destination bucket before * acquiring the lock. It then decrements them again after releasing it - * the code that actually moves the futex(es) between hash buckets (requeue_futex) * will do the additional required waiter count housekeeping. This is done for * double_lock_hb() and double_unlock_hb(), respectively. */ bool __futex_wake_mark(struct futex_q *q) { if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) return false; __futex_unqueue(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL * is written, without taking any locks. This is possible in the event * of a spurious wakeup, for example. A memory barrier is required here * to prevent the following store to lock_ptr from getting ahead of the * plist_del in __futex_unqueue(). */ smp_store_release(&q->lock_ptr, NULL); return true; } /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. Callers * must ensure to later call wake_up_q() for the actual * wakeups to occur. */ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) { struct task_struct *p = q->task; get_task_struct(p); if (!__futex_wake_mark(q)) { put_task_struct(p); return; } /* * Queue the task for later wakeup for after we've released * the hb->lock. */ wake_q_add_safe(wake_q, p); } /* * Wake up waiters matching bitset queued on this futex (uaddr). */ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; DEFINE_WAKE_Q(wake_q); int ret; if (!bitset) return -EINVAL; ret = get_futex_key(uaddr, flags, &key, FUTEX_READ); if (unlikely(ret != 0)) return ret; if ((flags & FLAGS_STRICT) && !nr_wake) return 0; hb = futex_hash(&key); /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) return ret; spin_lock(&hb->lock); plist_for_each_entry_safe(this, next, &hb->chain, list) { if (futex_match (&this->key, &key)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } /* Check if one of the bits is set in both bitsets */ if (!(this->bitset & bitset)) continue; this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } spin_unlock(&hb->lock); wake_up_q(&wake_q); return ret; } static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { unsigned int op = (encoded_op & 0x70000000) >> 28; unsigned int cmp = (encoded_op & 0x0f000000) >> 24; int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11); int cmparg = sign_extend32(encoded_op & 0x00000fff, 11); int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { char comm[sizeof(current->comm)]; /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", get_task_comm(comm, current), oparg); oparg &= 31; } oparg = 1 << oparg; } pagefault_disable(); ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); pagefault_enable(); if (ret) return ret; switch (cmp) { case FUTEX_OP_CMP_EQ: return oldval == cmparg; case FUTEX_OP_CMP_NE: return oldval != cmparg; case FUTEX_OP_CMP_LT: return oldval < cmparg; case FUTEX_OP_CMP_GE: return oldval >= cmparg; case FUTEX_OP_CMP_LE: return oldval <= cmparg; case FUTEX_OP_CMP_GT: return oldval > cmparg; default: return -ENOSYS; } } /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; int ret, op_ret; DEFINE_WAKE_Q(wake_q); retry: ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) return ret; hb1 = futex_hash(&key1); hb2 = futex_hash(&key2); retry_private: double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { double_unlock_hb(hb1, hb2); if (!IS_ENABLED(CONFIG_MMU) || unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { /* * we don't get EFAULT from MMU faults if we don't have * an MMU, but we might get them from range checking */ ret = op_ret; return ret; } if (op_ret == -EFAULT) { ret = fault_in_user_writeable(uaddr2); if (ret) return ret; } cond_resched(); if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (futex_match (&this->key, &key1)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } if (op_ret > 0) { op_ret = 0; plist_for_each_entry_safe(this, next, &hb2->chain, list) { if (futex_match (&this->key, &key2)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++op_ret >= nr_wake2) break; } } ret += op_ret; } out_unlock: double_unlock_hb(hb1, hb2); wake_up_q(&wake_q); return ret; } static long futex_wait_restart(struct restart_block *restart); /** * futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal * @hb: the futex hash bucket, must be locked by the caller * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout) { /* * The task state is guaranteed to be set before another task can * wake it. set_current_state() is implemented using smp_store_mb() and * futex_queue() calls spin_unlock() upon completion, both serializing * access to the hash list and forcing another memory barrier. */ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); futex_queue(q, hb); /* Arm the timer */ if (timeout) hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); /* * If we have been removed from the hash list, then another task * has tried to wake us, and we can skip the call to schedule(). */ if (likely(!plist_node_empty(&q->list))) { /* * If the timer has already expired, current will already be * flagged for rescheduling. Only call schedule if there * is no timeout, or if it has yet to expire. */ if (!timeout || timeout->task) schedule(); } __set_current_state(TASK_RUNNING); } /** * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * * Helper to unqueue a list of futexes. This can't fail. * * Return: * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ int futex_unqueue_multiple(struct futex_vector *v, int count) { int ret = -1, i; for (i = 0; i < count; i++) { if (!futex_unqueue(&v[i].q)) ret = i; } return ret; } /** * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes * @vs: The futex list to wait on * @count: The size of the list * @woken: Index of the last woken futex, if any. Used to notify the * caller that it can return this index to userspace (return parameter) * * Prepare multiple futexes in a single step and enqueue them. This may fail if * the futex list is invalid or if any futex was already awoken. On success the * task is ready to interruptible sleep. * * Return: * - 1 - One of the futexes was woken by another thread * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { struct futex_hash_bucket *hb; bool retry = false; int ret, i; u32 uval; /* * Enqueuing multiple futexes is tricky, because we need to enqueue * each futex on the list before dealing with the next one to avoid * deadlocking on the hash bucket. But, before enqueuing, we need to * make sure that current->state is TASK_INTERRUPTIBLE, so we don't * lose any wake events, which cannot be done before the get_futex_key * of the next key, because it calls get_user_pages, which can sleep. * Thus, we fetch the list of futexes keys in two steps, by first * pinning all the memory keys in the futex key, and only then we read * each key and queue the corresponding futex. * * Private futexes doesn't need to recalculate hash in retry, so skip * get_futex_key() when retrying. */ retry: for (i = 0; i < count; i++) { if (!(vs[i].w.flags & FLAGS_SHARED) && retry) continue; ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), vs[i].w.flags, &vs[i].q.key, FUTEX_READ); if (unlikely(ret)) return ret; } set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); for (i = 0; i < count; i++) { u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; struct futex_q *q = &vs[i].q; u32 val = vs[i].w.val; hb = futex_q_lock(q); ret = futex_get_value_locked(&uval, uaddr); if (!ret && uval == val) { /* * The bucket lock can't be held while dealing with the * next futex. Queue each futex at this moment so hb can * be unlocked. */ futex_queue(q, hb); continue; } futex_q_unlock(hb); __set_current_state(TASK_RUNNING); /* * Even if something went wrong, if we find out that a futex * was woken, we don't return error and return this index to * userspace */ *woken = futex_unqueue_multiple(vs, i); if (*woken >= 0) return 1; if (ret) { /* * If we need to handle a page fault, we need to do so * without any lock and any enqueued futex (otherwise * we could lose some wakeup). So we do it here, after * undoing all the work done so far. In success, we * retry all the work. */ if (get_user(uval, uaddr)) return -EFAULT; retry = true; goto retry; } if (uval != val) return -EWOULDBLOCK; } return 0; } /** * futex_sleep_multiple - Check sleeping conditions and sleep * @vs: List of futexes to wait for * @count: Length of vs * @to: Timeout * * Sleep if and only if the timeout hasn't expired and no futex on the list has * been woken up. */ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { if (to && !to->task) return; for (; count; count--, vs++) { if (!READ_ONCE(vs->q.lock_ptr)) return; } schedule(); } /** * futex_wait_multiple - Prepare to wait on and enqueue several futexes * @vs: The list of futexes to wait on * @count: The number of objects * @to: Timeout before giving up and returning to userspace * * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function * sleeps on a group of futexes and returns on the first futex that is * wake, or after the timeout has elapsed. * * Return: * - >=0 - Hint to the futex that was awoken * - <0 - On error */ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { int ret, hint = 0; if (to) hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); while (1) { ret = futex_wait_multiple_setup(vs, count, &hint); if (ret) { if (ret > 0) { /* A futex was woken during setup */ ret = hint; } return ret; } futex_sleep_multiple(vs, count, to); __set_current_state(TASK_RUNNING); ret = futex_unqueue_multiple(vs, count); if (ret >= 0) return ret; if (to && !to->task) return -ETIMEDOUT; else if (signal_pending(current)) return -ERESTARTSYS; /* * The final case is a spurious wakeup, for * which just retry. */ } } /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q * @hb: storage for hash_bucket pointer to be returned to caller * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; * - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb) { u32 uval; int ret; /* * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for * any cond. If we locked the hash-bucket after testing *uaddr, that * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * * On the other hand, we insert q and release the hash-bucket only * after testing *uaddr. This guarantees that futex_wait() will NOT * absorb a wakeup if *uaddr does not match the desired values * while the syscall executes. */ retry: ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; retry_private: *hb = futex_q_lock(q); ret = futex_get_value_locked(&uval, uaddr); if (ret) { futex_q_unlock(*hb); ret = get_user(uval, uaddr); if (ret) return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } if (uval != val) { futex_q_unlock(*hb); ret = -EWOULDBLOCK; } return ret; } int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset) { struct futex_q q = futex_q_init; struct futex_hash_bucket *hb; int ret; if (!bitset) return -EINVAL; q.bitset = bitset; retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ ret = futex_wait_setup(uaddr, val, flags, &q, &hb); if (ret) return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ futex_wait_queue(hb, &q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ if (!futex_unqueue(&q)) return 0; if (to && !to->task) return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the * victim of a spurious wakeup as well. */ if (!signal_pending(current)) goto retry; return -ERESTARTSYS; } int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { struct hrtimer_sleeper timeout, *to; struct restart_block *restart; int ret; to = futex_setup_timer(abs_time, &timeout, flags, current->timer_slack_ns); ret = __futex_wait(uaddr, flags, val, to, bitset); /* No timeout, nothing to clean up. */ if (!to) return ret; hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); if (ret == -ERESTARTSYS) { restart = ¤t->restart_block; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; return set_restart_fn(restart, futex_wait_restart); } return ret; } static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = restart->futex.uaddr; ktime_t t, *tp = NULL; if (restart->futex.flags & FLAGS_HAS_TIMEOUT) { t = restart->futex.time; tp = &t; } restart->fn = do_no_restart_syscall; return (long)futex_wait(uaddr, restart->futex.flags, restart->futex.val, tp, restart->futex.bitset); } |
| 225 225 225 225 225 224 225 224 6 6 6 6 6 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to generic helpers functions */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/scatterlist.h> #include "blk.h" static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector) { unsigned int discard_granularity = bdev_discard_granularity(bdev); sector_t granularity_aligned_sector; if (bdev_is_partition(bdev)) sector += bdev->bd_start_sect; granularity_aligned_sector = round_up(sector, discard_granularity >> SECTOR_SHIFT); /* * Make sure subsequent bios start aligned to the discard granularity if * it needs to be split. */ if (granularity_aligned_sector != sector) return granularity_aligned_sector - sector; /* * Align the bio size to the discard granularity to make splitting the bio * at discard granularity boundaries easier in the driver if needed. */ return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT; } int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { struct bio *bio = *biop; sector_t bs_mask; if (bdev_read_only(bdev)) return -EPERM; if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; /* In case the discard granularity isn't set by buggy device driver */ if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) { pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n", bdev); return -EOPNOTSUPP; } bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; if (!nr_sects) return -EINVAL; while (nr_sects) { sector_t req_sects = min(nr_sects, bio_discard_limit(bdev, sector)); bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask); bio->bi_iter.bi_sector = sector; bio->bi_iter.bi_size = req_sects << 9; sector += req_sects; nr_sects -= req_sects; /* * We can loop for a long time in here, if someone does * full device discards (like mkfs). Be nice and allow * us to schedule out to avoid softlocking if preempt * is disabled. */ cond_resched(); } *biop = bio; return 0; } EXPORT_SYMBOL(__blkdev_issue_discard); /** * blkdev_issue_discard - queue a discard * @bdev: blockdev to issue discard for * @sector: start sector * @nr_sects: number of sectors to discard * @gfp_mask: memory allocation flags (for bio_alloc) * * Description: * Issue a discard request for the sectors in question. */ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask) { struct bio *bio = NULL; struct blk_plug plug; int ret; blk_start_plug(&plug); ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio); if (!ret && bio) { ret = submit_bio_wait(bio); if (ret == -EOPNOTSUPP) ret = 0; bio_put(bio); } blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(blkdev_issue_discard); static int __blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { struct bio *bio = *biop; unsigned int max_write_zeroes_sectors; if (bdev_read_only(bdev)) return -EPERM; /* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */ max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev); if (max_write_zeroes_sectors == 0) return -EOPNOTSUPP; while (nr_sects) { bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask); bio->bi_iter.bi_sector = sector; if (flags & BLKDEV_ZERO_NOUNMAP) bio->bi_opf |= REQ_NOUNMAP; if (nr_sects > max_write_zeroes_sectors) { bio->bi_iter.bi_size = max_write_zeroes_sectors << 9; nr_sects -= max_write_zeroes_sectors; sector += max_write_zeroes_sectors; } else { bio->bi_iter.bi_size = nr_sects << 9; nr_sects = 0; } cond_resched(); } *biop = bio; return 0; } /* * Convert a number of 512B sectors to a number of pages. * The result is limited to a number of pages that can fit into a BIO. * Also make sure that the result is always at least 1 (page) for the cases * where nr_sects is lower than the number of sectors in a page. */ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) { sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512); return min(pages, (sector_t)BIO_MAX_VECS); } static int __blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { struct bio *bio = *biop; int bi_size = 0; unsigned int sz; if (bdev_read_only(bdev)) return -EPERM; while (nr_sects != 0) { bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects), REQ_OP_WRITE, gfp_mask); bio->bi_iter.bi_sector = sector; while (nr_sects != 0) { sz = min((sector_t) PAGE_SIZE, nr_sects << 9); bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0); nr_sects -= bi_size >> 9; sector += bi_size >> 9; if (bi_size < sz) break; } cond_resched(); } *biop = bio; return 0; } /** * __blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue * @sector: start sector * @nr_sects: number of sectors to write * @gfp_mask: memory allocation flags (for bio_alloc) * @biop: pointer to anchor bio * @flags: controls detailed behavior * * Description: * Zero-fill a block range, either using hardware offload or by explicitly * writing zeroes to the device. * * If a device is using logical block provisioning, the underlying space will * not be released if %flags contains BLKDEV_ZERO_NOUNMAP. * * If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return * -EOPNOTSUPP if no explicit hardware offload for zeroing is provided. */ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { int ret; sector_t bs_mask; bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, biop, flags); if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK)) return ret; return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, biop); } EXPORT_SYMBOL(__blkdev_issue_zeroout); /** * blkdev_issue_zeroout - zero-fill a block range * @bdev: blockdev to write * @sector: start sector * @nr_sects: number of sectors to write * @gfp_mask: memory allocation flags (for bio_alloc) * @flags: controls detailed behavior * * Description: * Zero-fill a block range, either using hardware offload or by explicitly * writing zeroes to the device. See __blkdev_issue_zeroout() for the * valid values for %flags. */ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags) { int ret = 0; sector_t bs_mask; struct bio *bio; struct blk_plug plug; bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev); bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; retry: bio = NULL; blk_start_plug(&plug); if (try_write_zeroes) { ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, &bio, flags); } else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, &bio); } else { /* No zeroing offload support */ ret = -EOPNOTSUPP; } if (ret == 0 && bio) { ret = submit_bio_wait(bio); bio_put(bio); } blk_finish_plug(&plug); if (ret && try_write_zeroes) { if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { try_write_zeroes = false; goto retry; } if (!bdev_write_zeroes_sectors(bdev)) { /* * Zeroing offload support was indicated, but the * device reported ILLEGAL REQUEST (for some devices * there is no non-destructive way to verify whether * WRITE ZEROES is actually supported). */ ret = -EOPNOTSUPP; } } return ret; } EXPORT_SYMBOL(blkdev_issue_zeroout); int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp) { sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev); struct bio *bio = NULL; struct blk_plug plug; int ret = 0; /* make sure that "len << SECTOR_SHIFT" doesn't overflow */ if (max_sectors > UINT_MAX >> SECTOR_SHIFT) max_sectors = UINT_MAX >> SECTOR_SHIFT; max_sectors &= ~bs_mask; if (max_sectors == 0) return -EOPNOTSUPP; if ((sector | nr_sects) & bs_mask) return -EINVAL; if (bdev_read_only(bdev)) return -EPERM; blk_start_plug(&plug); for (;;) { unsigned int len = min_t(sector_t, nr_sects, max_sectors); bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp); bio->bi_iter.bi_sector = sector; bio->bi_iter.bi_size = len << SECTOR_SHIFT; sector += len; nr_sects -= len; if (!nr_sects) { ret = submit_bio_wait(bio); bio_put(bio); break; } cond_resched(); } blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(blkdev_issue_secure_erase); |
| 12 246 274 10 10 16 9 10 10 10 10 25 25 25 25 19 16 21 9 25 25 2 25 25 6 10 10 10 10 10 2 10 10 10 10 10 10 10 10 10 10 10 10 2 10 10 10 6 10 1 1 2 2 2 2 2 12 12 12 12 12 235 235 235 235 246 239 242 235 12 242 242 246 246 246 246 246 246 10 10 246 10 242 242 12 242 3 3 1 12 1 264 263 19 261 261 260 273 8 271 2 18 12 8 6 6 6 12 12 12 218 12 209 210 209 209 1 210 1 2 338 3 335 83 215 28 209 215 7 209 209 2 210 11 209 217 941 941 941 1158 1158 75 1154 1158 789 1156 1156 296 301 268 403 242 277 9 9 149 980 941 940 941 941 939 938 6 6 3 3 6 6 1 1 235 16 11 10 7 6 6 6 6 6 6 6 6 1 6 18 18 18 18 18 15 18 18 18 18 18 18 7 7 1 1 1 1 1 233 234 234 234 234 234 233 234 234 234 234 234 83 234 234 234 234 10 233 17 17 2 14 17 17 17 17 15 17 4 4 606 605 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Robert Olsson <robert.olsson@its.uu.se> Uppsala Universitet * & Swedish University of Agricultural Sciences. * * Jens Laas <jens.laas@data.slu.se> Swedish University of * Agricultural Sciences. * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. * https://www.csc.kth.se/~snilsson/software/dyntrie2/ * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson * IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 * * Code from fib_hash has been reused which includes the following header: * * 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. * * IPv4 FIB: lookup engine and maintenance routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Substantial contributions to this work comes from: * * David S. Miller, <davem@davemloft.net> * Stephen Hemminger <shemminger@osdl.org> * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/rcupdate_wait.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define KEY_MAX ((t_key)~0) typedef unsigned int t_key; #define IS_TRIE(n) ((n)->pos >= KEYLENGTH) #define IS_TNODE(n) ((n)->bits) #define IS_LEAF(n) (!(n)->bits) struct key_vector { t_key key; unsigned char pos; /* 2log(KEYLENGTH) bits needed */ unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; union { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; struct tnode { struct rcu_head rcu; t_key empty_children; /* KEYLENGTH bits needed */ t_key full_children; /* KEYLENGTH bits needed */ struct key_vector __rcu *parent; struct key_vector kv[1]; #define tn_bits kv[0].bits }; #define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) #define LEAF_SIZE TNODE_SIZE(1) #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; unsigned int backtrack; unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; unsigned int resize_node_skipped; }; #endif struct trie_stat { unsigned int totdepth; unsigned int maxdepth; unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; unsigned int prefixes; unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); static unsigned int tnode_free_size; /* * synchronize_rcu after call_rcu for outstanding dirty memory; it should be * especially useful before resizing the root node with PREEMPT_NONE configs; * the value was obtained experimentally, aiming to avoid visible slowdown. */ unsigned int sysctl_fib_sync_mem = 512 * 1024; unsigned int sysctl_fib_sync_mem_min = 64 * 1024; unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { return container_of(kv, struct tnode, kv[0]); } /* caller must hold RTNL */ #define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) #define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ #define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) #define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) rcu_assign_pointer(tn_info(n)->parent, tp); } #define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } #define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) static inline unsigned long get_index(t_key key, struct key_vector *kv) { unsigned long index = key ^ kv->key; if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) return 0; return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is * necessary. Every node in the trie has a key associated with it, but not * all of the bits in that key are significant. * * Consider a node 'n' and its parent 'tp'. * * If n is a leaf, every bit in its key is significant. Its presence is * necessitated by path compression, since during a tree traversal (when * searching for a leaf - unless we are doing an insertion) we will completely * ignore all skipped bits we encounter. Thus we need to verify, at the end of * a potentially successful search, that we have indeed been walking the * correct key path. * * Note that we can never "miss" the correct key in the tree if present by * following the wrong path. Path compression ensures that segments of the key * that are the same for all keys with a given prefix are skipped, but the * skipped part *is* identical for each node in the subtrie below the skipped * bit! trie_insert() in this implementation takes care of that. * * if n is an internal node - a 'tnode' here, the various parts of its key * have many different meanings. * * Example: * _________________________________________________________________ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C | * ----------------------------------------------------------------- * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 * * _________________________________________________________________ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u | * ----------------------------------------------------------------- * 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 * * tp->pos = 22 * tp->bits = 3 * n->pos = 13 * n->bits = 4 * * First, let's just ignore the bits that come before the parent tp, that is * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this * point we do not use them for anything. * * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest * of the bits are really not needed or indeed known in n->key. * * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; static const int inflate_threshold_root = 30; static void __alias_free_mem(struct rcu_head *head) { struct fib_alias *fa = container_of(head, struct fib_alias, rcu); kmem_cache_free(fn_alias_kmem, fa); } static inline void alias_free_mem_rcu(struct fib_alias *fa) { call_rcu(&fa->rcu, __alias_free_mem); } #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); else kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) static struct tnode *tnode_alloc(int bits) { size_t size; /* verify bits is within bounds */ if (bits > TNODE_VMALLOC_MAX) return NULL; /* determine size and verify it is non-zero and didn't overflow */ size = TNODE_SIZE(1ul << bits); if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } static inline void empty_child_inc(struct key_vector *n) { tn_info(n)->empty_children++; if (!tn_info(n)->empty_children) tn_info(n)->full_children++; } static inline void empty_child_dec(struct key_vector *n) { if (!tn_info(n)->empty_children) tn_info(n)->full_children--; tn_info(n)->empty_children--; } static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { struct key_vector *l; struct tnode *kv; kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; l->slen = fa->fa_slen; /* link leaf to fib alias */ INIT_HLIST_HEAD(&l->leaf); hlist_add_head(&fa->fa_list, &l->leaf); return l; } static struct key_vector *tnode_new(t_key key, int pos, int bits) { unsigned int shift = pos + bits; struct key_vector *tn; struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); tnode = tnode_alloc(bits); if (!tnode) return NULL; pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), sizeof(struct key_vector *) << bits); if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; tn->slen = pos; return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ static void put_child(struct key_vector *tn, unsigned long i, struct key_vector *n) { struct key_vector *chi = get_child(tn, i); int isfull, wasfull; BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ if (!n && chi) empty_child_inc(tn); if (n && !chi) empty_child_dec(tn); /* update fullChildren */ wasfull = tnode_full(tn, chi); isfull = tnode_full(tn, n); if (wasfull && !isfull) tn_info(tn)->full_children--; else if (!wasfull && isfull) tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; rcu_assign_pointer(tn->tnode[i], n); } static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); if (!inode) continue; /* Either update the children of a tnode that * already belongs to us or update the child * to point to ourselves. */ if (node_parent(inode) == tn) update_children(inode); else node_set_parent(inode, tn); } } static inline void put_child_root(struct key_vector *tp, t_key key, struct key_vector *n) { if (IS_TRIE(tp)) rcu_assign_pointer(tp->tnode[0], n); else put_child(tp, get_index(key, tp), n); } static inline void tnode_free_init(struct key_vector *tn) { tn_info(tn)->rcu.next = NULL; } static inline void tnode_free_append(struct key_vector *tn, struct key_vector *n) { tn_info(n)->rcu.next = tn_info(tn)->rcu.next; tn_info(tn)->rcu.next = &tn_info(n)->rcu; } static void tnode_free(struct key_vector *tn) { struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_rcu(); } } static struct key_vector *replace(struct trie *t, struct key_vector *oldtnode, struct key_vector *tn) { struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); /* all pointers should be clean so we are done */ tnode_free(oldtnode); /* resize children now that oldtnode is freed */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) tn = resize(t, inode); } return tp; } static struct key_vector *inflate(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; t_key m; pr_debug("In inflate\n"); tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { struct key_vector *inode = get_child(oldtnode, --i); struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ if (!inode) continue; /* A leaf or an internal node with skipped bits */ if (!tnode_full(oldtnode, inode)) { put_child(tn, get_index(inode->key, tn), inode); continue; } /* drop the node in the old tnode free list */ tnode_free_append(oldtnode, inode); /* An internal node with two children */ if (inode->bits == 1) { put_child(tn, 2 * i + 1, get_child(inode, 1)); put_child(tn, 2 * i, get_child(inode, 0)); continue; } /* We will replace this node 'inode' with two new * ones, 'node0' and 'node1', each with half of the * original children. The two new nodes will have * a position one bit further down the key and this * means that the "significant" part of their keys * (see the discussion near the top of this file) * will differ by one bit, which will be "0" in * node0's key and "1" in node1's key. Since we are * moving the key position by one step, the bit that * we are moving away from - the bit at position * (tn->pos) - is the one that will differ between * node0 and node1. So... we synthesize that bit in the * two new keys. */ node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1); if (!node1) goto nomem; node0 = tnode_new(inode->key, inode->pos, inode->bits - 1); tnode_free_append(tn, node1); if (!node0) goto nomem; tnode_free_append(tn, node0); /* populate child pointers in new nodes */ for (k = child_length(inode), j = k / 2; j;) { put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ NODE_INIT_PARENT(node1, tn); NODE_INIT_PARENT(node0, tn); /* link parent to nodes */ put_child(tn, 2 * i + 1, node1); put_child(tn, 2 * i, node0); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *halve(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode); i;) { struct key_vector *node1 = get_child(oldtnode, --i); struct key_vector *node0 = get_child(oldtnode, --i); struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { put_child(tn, i / 2, node1 ? : node0); continue; } /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); if (!inode) goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ put_child(inode, 1, node1); put_child(inode, 0, node0); NODE_INIT_PARENT(inode, tn); /* link parent to node */ put_child(tn, i / 2, inode); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *collapse(struct trie *t, struct key_vector *oldtnode) { struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ for (n = NULL, i = child_length(oldtnode); !n && i;) n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); return tp; } static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; unsigned char slen_max; /* only vector 0 can have a suffix length greater than or equal to * tn->pos + tn->bits, the second highest node will have a suffix * length at most of tn->pos + tn->bits - 1 */ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; /* update stride and slen based on new value */ stride <<= (n->slen - slen); slen = n->slen; i &= ~(stride - 1); /* stop searching if we have hit the maximum possible value */ if (slen >= slen_max) break; } tn->slen = slen; return slen; } /* From "Implementing a dynamic compressed trie" by Stefan Nilsson of * the Helsinki University of Technology and Matti Tikkanen of Nokia * Telecommunications, page 6: * "A node is doubled if the ratio of non-empty children to all * children in the *doubled* node is at least 'high'." * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. * All of those will be doubled in the resulting inflated tnode, so * we just count them one extra time here. * * A clearer way to write this would be: * * to_be_doubled = tn->full_children; * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; * if (new_fill_factor >= inflate_threshold) * * ...and so on, tho it would mess up the while () loop. * * anyway, * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >= * inflate_threshold * * avoid a division: * 100 * (not_to_be_doubled + 2*to_be_doubled) >= * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= * inflate_threshold * child_length(tn) * 2 * * shorten again: * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * * child_length(tn) * */ static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; used -= tn_info(tn)->empty_children; used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } static inline bool should_collapse(struct key_vector *tn) { unsigned long used = child_length(tn); used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ return used < 2; } #define MAX_WORK 10 static struct key_vector *resize(struct trie *t, struct key_vector *tn) { #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif struct key_vector *tp = node_parent(tn); unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", tn, inflate_threshold, halve_threshold); /* track the tnode via the pointer from the parent instead of * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* update parent in case inflate failed */ tp = node_parent(tn); /* Return if at least one inflate is run */ if (max_work != MAX_WORK) return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* Only one child remains */ if (should_collapse(tn)) return collapse(t, tn); /* update parent in case halve failed */ return node_parent(tn); } static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { unsigned char node_slen = tn->slen; while ((node_slen > tn->pos) && (node_slen > slen)) { slen = update_suffix(tn); if (node_slen == slen) break; tn = node_parent(tn); node_slen = tn->slen; } } static void node_push_suffix(struct key_vector *tn, unsigned char slen) { while (tn->slen < slen) { tn->slen = slen; tn = node_parent(tn); } } /* rcu_read_lock needs to be hold by caller from readside */ static struct key_vector *fib_find_node(struct trie *t, struct key_vector **tp, u32 key) { struct key_vector *pn, *n = t->kv; unsigned long index = 0; do { pn = n; n = get_child_rcu(n, index); if (!n) break; index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) { n = NULL; break; } /* keep searching until we find a perfect match leaf or NULL */ } while (IS_TNODE(n)); *tp = pn; return n; } /* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; if (!fah) return NULL; hlist_for_each_entry(fa, fah, fa_list) { /* Avoid Sparse warning when using dscp_t in inequalities */ u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); u8 __dscp = inet_dscp_to_dsfield(dscp); if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) break; if (fa->tb_id > tb_id) continue; if (fa->tb_id != tb_id) break; if (find_first) return fa; if (__fa_dscp > __dscp) continue; if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } return NULL; } static struct fib_alias * fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) { u8 slen = KEYLENGTH - fri->dst_len; struct key_vector *l, *tp; struct fib_table *tb; struct fib_alias *fa; struct trie *t; tb = fib_get_table(net, fri->tb_id); if (!tb) return NULL; t = (struct trie *)tb->tb_data; l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); if (!l) return NULL; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && fa->fa_dscp == fri->dscp && fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } return NULL; } void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; rcu_read_lock(); fa_match = fib_find_matching_alias(net, fri); if (!fa_match) goto out; /* These are paired with the WRITE_ONCE() happening in this function. * The reason is that we are only protected by RCU at this point. */ if (READ_ONCE(fa_match->offload) == fri->offload && READ_ONCE(fa_match->trap) == fri->trap && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap); fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); /* 2 means send notifications only if offload_failed was changed. */ if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload_failed, fri->offload_failed); if (!fib_notify_on_flag_change) goto out; skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); goto out; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) tn = resize(t, tn); } static int fib_insert_node(struct trie *t, struct key_vector *tp, struct fib_alias *new, t_key key) { struct key_vector *n, *l; l = leaf_new(key, new); if (!l) goto noleaf; /* retrieve child from parent node */ n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * * Add a new tnode here * first tnode need some special handling * leaves us in position for handling as case 3 */ if (n) { struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); if (!tn) goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ tp = tn; } /* Case 3: n is NULL, and will just insert a new leaf */ node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); return 0; notnode: node_free(l); noleaf: return -ENOMEM; } static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) { if (!l) return fib_insert_node(t, tp, new, key); if (fa) { hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { struct fib_alias *last; hlist_for_each_entry(last, &l->leaf, fa_list) { if (new->fa_slen < last->fa_slen) break; if ((new->fa_slen == last->fa_slen) && (new->tb_id > last->tb_id)) break; fa = last; } if (fa) hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); else hlist_add_head_rcu(&new->fa_list, &l->leaf); } /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; node_push_suffix(tp, new->fa_slen); } return 0; } static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { if (plen > KEYLENGTH) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; } if ((plen < KEYLENGTH) && (key << plen)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); return false; } return true; } static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; int err; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and * insert to the tail of the section matching the suffix length * of the new alias. */ if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; err = -EEXIST; if (cfg->fc_nlflags & NLM_F_EXCL) goto out; nlflags &= ~NLM_F_EXCL; /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it */ fa_match = NULL; fa_first = fa; hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && fa->fa_info == fi) { fa_match = fa; break; } } if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) err = 0; goto out; } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; fi_drop = fa->fa_info; new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) { hlist_replace_rcu(&new_fa->fa_list, &fa->fa_list); goto out_free_new_fa; } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); alias_free_mem_rcu(fa); fib_release_info(fi_drop); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); goto succeeded; } /* Error if we find a perfect match which * uses the same scope, type, and nexthop * information. */ if (fa_match) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; else fa = fa_first; } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) goto out_free_new_fa; /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); if (WARN_ON_ONCE(!l)) { err = -ENOENT; goto out_free_new_fa; } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) goto out_remove_new_fa; } if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: fib_release_info(fi); err: return err; } static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; return (key ^ prefix) & (prefix | -prefix); } bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp) { if (nhc->nhc_flags & RTNH_F_DEAD) return false; if (ip_ignore_linkdown(nhc->nhc_dev) && nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (flp->flowi4_oif && flp->flowi4_oif != nhc->nhc_oif) return false; return true; } /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); struct key_vector *n, *pn; struct fib_alias *fa; unsigned long index; t_key cindex; pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); if (!n) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); #endif /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ if (IS_LEAF(n)) goto found; /* only record pn and cindex if we are going to be chopping * bits later. Otherwise we are just wasting cycles. */ if (n->slen > n->pos) { pn = n; cindex = index; } n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of * the lsb and higher in the prefix. */ if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos)) goto backtrace; /* exit out and process leaf */ if (unlikely(IS_LEAF(n))) break; /* Don't bother recording parent info. Since we are in * prefix match mode we will have to come back to wherever * we started this traversal anyway */ while ((n = rcu_dereference(*cptr)) == NULL) { backtrace: #ifdef CONFIG_IP_FIB_TRIE_STATS if (!n) this_cpu_inc(stats->null_node_hit); #endif /* If we are at cindex 0 there are no more bits for * us to strip at this level so we must ascend back * up one level to see if there are any more bits to * be stripped there. */ while (!cindex) { t_key pkey = pn->key; /* If we don't have a parent then there is * nothing for us to do as we do not have any * further nodes to parse. */ if (IS_TRIE(pn)) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } /* strip the least significant bit from the cindex */ cindex &= cindex - 1; /* grab pointer for next child node */ cptr = &pn->tnode[cindex]; } } found: /* this line carries forward the xor from earlier in the function */ index = key ^ n->key; /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { if (index >= (1ul << fa->fa_slen)) continue; } if (fa->fa_dscp && inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; if (unlikely(fi->nh)) { if (nexthop_is_blackhole(fi->nh)) { err = fib_props[RTN_BLACKHOLE].error; goto out_reject; } nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, &nhsel); if (nhc) goto set_result; goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { nhc = fib_info_nhc(fi, nhsel); if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } } miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old) { /* record the location of the previous list_info entry */ struct hlist_node **pprev = old->fa_list.pprev; struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); /* remove the fib_alias from the list */ hlist_del_rcu(&old->fa_list); /* if we emptied the list this leaf will be freed and we can sort * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { if (tp->slen == l->slen) node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); return; } /* only access fa if it is pointing at the last valid hlist_node */ if (*pprev) return; /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; node_pull_suffix(tp, fa->fa_slen); } static void fib_notify_alias_delete(struct net *net, u32 key, struct hlist_head *fah, struct fib_alias *fa_to_delete, struct netlink_ext_ack *extack) { struct fib_alias *fa_next, *fa_to_notify; u32 tb_id = fa_to_delete->tb_id; u8 slen = fa_to_delete->fa_slen; enum fib_event_type fib_event; /* Do not notify if we do not care about the route. */ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) return; /* Determine if the route should be replaced by the next route in the * list. */ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, struct fib_alias, fa_list); if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { fib_event = FIB_EVENT_ENTRY_REPLACE; fa_to_notify = fa_next; } else { fib_event = FIB_EVENT_ENTRY_DEL; fa_to_notify = fa_to_delete; } call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, fa_to_notify, extack); } /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; dscp = cfg->fc_dscp; fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || fa->fa_info->fib_scope == cfg->fc_scope) && (!cfg->fc_prefsrc || fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; } } if (!fa_to_delete) return -ESRCH; fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; fib_remove_alias(t, tp, l, fa_to_delete); if (fa_to_delete->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa_to_delete->fa_info); alias_free_mem_rcu(fa_to_delete); return 0; } /* Scan for the next leaf starting at the provided key value */ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { struct key_vector *pn, *n = *tn; unsigned long cindex; /* this loop is meant to try and find the key in the trie */ do { /* record parent and next child index */ pn = n; cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; /* descend into the next child */ n = get_child_rcu(pn, cindex++); if (!n) break; /* guarantee forward progress on the keys */ if (IS_LEAF(n) && (n->key >= key)) goto found; } while (IS_TNODE(n)); /* this loop will search for the next leaf with a greater key */ while (!IS_TRIE(pn)) { /* if we exhausted the parent node we will need to climb */ if (cindex >= (1ul << pn->bits)) { t_key pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; continue; } /* grab the next available node */ n = get_child_rcu(pn, cindex++); if (!n) continue; /* no need to compare keys since we bumped the index */ if (IS_LEAF(n)) goto found; /* Rescan start scanning in new node */ pn = n; cindex = 0; } *tn = pn; return NULL; /* Root of trie */ found: /* if we are at the limit for keys just return NULL for the tnode */ *tn = pn; return n; } static void fib_trie_free(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order and free everything */ for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; n = pn; pn = node_parent(pn); /* drop emptied tnode */ put_child_root(pn, n->key, NULL); node_free(n); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); } put_child_root(pn, n->key, NULL); node_free(n); } #ifdef CONFIG_IP_FIB_TRIE_STATS free_percpu(t->stats); #endif kfree(tb); } struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { struct trie *ot = (struct trie *)oldtb->tb_data; struct key_vector *l, *tp = ot->kv; struct fib_table *local_tb; struct fib_alias *fa; struct trie *lt; t_key key = 0; if (oldtb->tb_data == oldtb->__data) return oldtb; local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); if (!local_tb) return NULL; lt = (struct trie *)local_tb->tb_data; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) continue; /* clone fa for new local table */ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; memcpy(new_fa, fa, sizeof(*fa)); /* insert clone into table */ if (!local_l) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, NULL, l->key)) { kmem_cache_free(fn_alias_kmem, new_fa); goto out; } } /* stop loop if key wrapped back to 0 */ key = l->key + 1; if (key < l->key) break; } return local_tb; out: fib_trie_free(local_tb); return NULL; } /* Caller must hold RTNL */ void fib_table_flush_external(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { /* if alias was cloned to local then we just * need to remove the local copy from main */ if (tb->tb_id != fa->tb_id) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); continue; } /* record local slen */ slen = fa->fa_slen; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } } /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; int found = 0; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || tb->tb_id != fa->tb_id || (!(fi->fib_flags & RTNH_F_DEAD) && !fib_props[fa->fa_type].error)) { slen = fa->fa_slen; continue; } /* Do not flush error routes if network namespace is * not being dismantled */ if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); if (fi->pfsrc_removed) rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); found++; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } pr_debug("trie_flush found=%d\n", found); return found; } /* derived from fib_trie_free */ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, struct nl_info *info) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct fib_alias *fa; for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; pn = node_parent(pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) continue; rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); } } } void fib_info_notify_update(struct net *net, struct nl_info *info) { unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_alias *fa; int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi) continue; /* local and main table can share the same trie, * so don't notify twice for the same entry. */ if (tb->tb_id != fa->tb_id) continue; if (fa->fa_slen == last_slen) continue; last_slen = fa->fa_slen; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; } return 0; } static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } return 0; } int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { unsigned int h; int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { err = fib_table_notify(tb, nb, extack); if (err) return err; } } return 0; } static void __trie_free_rcu(struct rcu_head *head) { struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; if (tb->tb_data == tb->__data) free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } void fib_free_table(struct fib_table *tb) { call_rcu(&tb->rcu, __trie_free_rcu); } static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { unsigned int flags = NLM_F_MULTI; __be32 xkey = htonl(l->key); int i, s_i, i_fa, s_fa, err; struct fib_alias *fa; if (filter->filter_set || !filter->dump_exceptions || !filter->dump_routes) flags |= NLM_F_DUMP_FILTERED; s_i = cb->args[4]; s_fa = cb->args[5]; i = 0; /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (i < s_i) goto next; i_fa = 0; if (tb->tb_id != fa->tb_id) goto next; if (filter->filter_set) { if (filter->rt_type && fa->fa_type != filter->rt_type) goto next; if ((filter->protocol && fi->fib_protocol != filter->protocol)) goto next; if (filter->dev && !fib_info_nh_uses_dev(fi, filter->dev)) goto next; } if (filter->dump_routes) { if (!s_fa) { struct fib_rt_info fri; fri.fi = fi; fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; fri.dscp = fa->fa_dscp; fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } i_fa++; } if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, &i_fa, s_fa, flags); if (err < 0) goto stop; } next: i++; } cb->args[4] = i; return skb->len; stop: cb->args[4] = i; cb->args[5] = i_fa; return err; } /* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ int count = cb->args[2]; t_key key = cb->args[3]; /* First time here, count and key are both always 0. Count > 0 * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) return skb->len; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; err = fn_trie_dump_leaf(l, tb, skb, cb, filter); if (err < 0) { cb->args[3] = key; cb->args[2] = count; return err; } ++count; key = l->key + 1; memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); /* stop loop if key wrapped back to 0 */ if (key < l->key) break; } cb->args[3] = key; cb->args[2] = count; return skb->len; } void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; size_t sz = sizeof(*tb); if (!alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); if (!tb) return NULL; tb->tb_id = id; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); if (alias) return tb; t = (struct trie *) tb->tb_data; t->kv[0].pos = KEYLENGTH; t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { kfree(tb); tb = NULL; } #endif return tb; } #ifdef CONFIG_PROC_FS /* Depth first Trie walk iterator */ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct key_vector *tnode; unsigned int index; unsigned int depth; }; static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; struct key_vector *pn = iter->tnode; t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); while (!IS_TRIE(pn)) { while (cindex < child_length(pn)) { struct key_vector *n = get_child_rcu(pn, cindex++); if (!n) continue; if (IS_LEAF(n)) { iter->tnode = pn; iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } return n; } /* Current node exhausted, pop back up */ pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; --iter->depth; } /* record root node so further searches know we are done */ iter->tnode = pn; iter->index = 0; return NULL; } static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { struct key_vector *n, *pn; if (!t) return NULL; pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; if (IS_TNODE(n)) { iter->tnode = n; iter->index = 0; iter->depth = 1; } else { iter->tnode = pn; iter->index = 0; iter->depth = 0; } return n; } static void trie_collect_stats(struct trie *t, struct trie_stat *s) { struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); } /* * This outputs /proc/net/fib_triestats */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; else avdepth = 0; seq_printf(seq, "\tAver depth: %u.%02d\n", avdepth / 100, avdepth % 100); seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; } seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } #ifdef CONFIG_IP_FIB_TRIE_STATS static void trie_show_usage(struct seq_file *seq, const struct trie_use_stats __percpu *stats) { struct trie_use_stats s = { 0 }; int cpu; /* loop through all of the CPUs and gather up the stats */ for_each_possible_cpu(cpu) { const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu); s.gets += pcpu->gets; s.backtrack += pcpu->backtrack; s.semantic_match_passed += pcpu->semantic_match_passed; s.semantic_match_miss += pcpu->semantic_match_miss; s.null_node_hit += pcpu->null_node_hit; s.resize_node_skipped += pcpu->resize_node_skipped; } seq_printf(seq, "\nCounters:\n---------\n"); seq_printf(seq, "gets = %u\n", s.gets); seq_printf(seq, "backtracks = %u\n", s.backtrack); seq_printf(seq, "semantic match passed = %u\n", s.semantic_match_passed); seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss); seq_printf(seq, "null node hit= %u\n", s.null_node_hit); seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped); } #endif /* CONFIG_IP_FIB_TRIE_STATS */ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) { if (tb->tb_id == RT_TABLE_LOCAL) seq_puts(seq, "Local:\n"); else if (tb->tb_id == RT_TABLE_MAIN) seq_puts(seq, "Main:\n"); else seq_printf(seq, "Id %d:\n", tb->tb_id); } static int fib_triestat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; unsigned int h; seq_printf(seq, "Basic info: size of leaf:" " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; if (!t) continue; fib_table_print(seq, tb); trie_collect_stats(t, &stat); trie_show_stats(seq, &stat); #ifdef CONFIG_IP_FIB_TRIE_STATS trie_show_usage(seq, t->stats); #endif } cond_resched_rcu(); } rcu_read_unlock(); return 0; } static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); loff_t idx = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); n; n = fib_trie_get_next(iter)) if (pos == idx++) { iter->tb = tb; return n; } } } return NULL; } static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return fib_trie_get_idx(seq, *pos); } static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; struct key_vector *n; ++*pos; /* next node in same table */ n = fib_trie_get_next(iter); if (n) return n; /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } } return NULL; found: iter->tb = tb; return n; } static void fib_trie_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void seq_indent(struct seq_file *seq, int n) { while (n-- > 0) seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) { switch (s) { case RT_SCOPE_UNIVERSE: return "universe"; case RT_SCOPE_SITE: return "site"; case RT_SCOPE_LINK: return "link"; case RT_SCOPE_HOST: return "host"; case RT_SCOPE_NOWHERE: return "nowhere"; default: snprintf(buf, len, "scope=%d", s); return buf; } } static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", [RTN_BROADCAST] = "BROADCAST", [RTN_ANYCAST] = "ANYCAST", [RTN_MULTICAST] = "MULTICAST", [RTN_BLACKHOLE] = "BLACKHOLE", [RTN_UNREACHABLE] = "UNREACHABLE", [RTN_PROHIBIT] = "PROHIBIT", [RTN_THROW] = "THROW", [RTN_NAT] = "NAT", [RTN_XRESOLVE] = "XRESOLVE", }; static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; snprintf(buf, len, "type %u", t); return buf; } /* Pretty print the trie */ static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; struct key_vector *n = v; if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { __be32 prf = htonl(n->key); seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, tn_info(n)->full_children, tn_info(n)->empty_children); } else { __be32 val = htonl(n->key); struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { char buf1[32], buf2[32]; seq_indent(seq, iter->depth + 1); seq_printf(seq, " /%zu %s %s", KEYLENGTH - fa->fa_slen, rtn_scope(buf1, sizeof(buf1), fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_dscp) seq_printf(seq, " tos=%d", inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } return 0; } static const struct seq_operations fib_trie_seq_ops = { .start = fib_trie_seq_start, .next = fib_trie_seq_next, .stop = fib_trie_seq_stop, .show = fib_trie_seq_show, }; struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; struct key_vector *tnode; loff_t pos; t_key key; }; static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { struct key_vector *l, **tp = &iter->tnode; t_key key; /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { key = iter->key; } else { iter->pos = 1; key = 0; } pos -= iter->pos; while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; l = NULL; /* handle unlikely case of a key wrap */ if (!key) break; } if (l) iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ return l; } static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; struct trie *t; rcu_read_lock(); tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; iter->main_tb = tb; t = (struct trie *)tb->tb_data; iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); iter->pos = 0; iter->key = KEY_MAX; return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; t_key key = iter->key + 1; ++*pos; /* only allow key of 0 for start of sequence */ if ((v == SEQ_START_TOKEN) || key) l = leaf_walk_rcu(&iter->tnode, key); if (l) { iter->key = l->key; iter->pos++; } else { iter->pos = 0; } return l; } static void fib_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; if (fi) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); if (nhc->nhc_gw.ipv4) flags |= RTF_GATEWAY; } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; } /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct fib_route_iter *iter = seq->private; struct fib_table *tb = iter->main_tb; struct fib_alias *fa; struct key_vector *l = v; __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" "\tWindow\tIRTT"); return 0; } prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); if ((fa->fa_type == RTN_BROADCAST) || (fa->fa_type == RTN_MULTICAST)) continue; if (fa->tb_id != tb->tb_id) continue; seq_setwidth(seq, 127); if (fi) { struct fib_nh_common *nhc = fib_info_nhc(fi, 0); __be32 gw = 0; if (nhc->nhc_gw_family == AF_INET) gw = nhc->nhc_gw.ipv4; seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } seq_pad(seq, '\n'); } return 0; } static const struct seq_operations fib_route_seq_ops = { .start = fib_route_seq_start, .next = fib_route_seq_next, .stop = fib_route_seq_stop, .show = fib_route_seq_show, }; int __net_init fib_proc_init(struct net *net) { if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, sizeof(struct fib_trie_iter))) goto out1; if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, fib_triestat_seq_show, NULL)) goto out2; if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, sizeof(struct fib_route_iter))) goto out3; return 0; out3: remove_proc_entry("fib_triestat", net->proc_net); out2: remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { remove_proc_entry("fib_trie", net->proc_net); remove_proc_entry("fib_triestat", net->proc_net); remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ |
| 1253 1253 1254 1252 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2019 Facebook * Copyright 2020 Google LLC. */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(inode_cache); static struct bpf_local_storage __rcu ** inode_storage_ptr(void *owner) { struct inode *inode = owner; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return NULL; return &bsb->storage; } static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *inode_storage; struct bpf_local_storage_map *smap; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return NULL; inode_storage = rcu_dereference_check(bsb->storage, bpf_rcu_lock_held()); if (!inode_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit); } void bpf_inode_storage_free(struct inode *inode) { struct bpf_local_storage *local_storage; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return; rcu_read_lock(); local_storage = rcu_dereference(bsb->storage); if (!local_storage) { rcu_read_unlock(); return; } bpf_local_storage_destroy(local_storage); rcu_read_unlock(); } static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct fd f = fdget_raw(*(int *)key); if (!f.file) return ERR_PTR(-EBADF); sdata = inode_storage_lookup(file_inode(f.file), map, true); fdput(f); return sdata ? sdata->data : NULL; } static long bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct fd f = fdget_raw(*(int *)key); if (!f.file) return -EBADF; if (!inode_storage_ptr(file_inode(f.file))) { fdput(f); return -EBADF; } sdata = bpf_local_storage_update(file_inode(f.file), (struct bpf_local_storage_map *)map, value, map_flags, GFP_ATOMIC); fdput(f); return PTR_ERR_OR_ZERO(sdata); } static int inode_storage_delete(struct inode *inode, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = inode_storage_lookup(inode, map, false); if (!sdata) return -ENOENT; bpf_selem_unlink(SELEM(sdata), false); return 0; } static long bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) { struct fd f = fdget_raw(*(int *)key); int err; if (!f.file) return -EBADF; err = inode_storage_delete(file_inode(f.file), map); fdput(f); return err; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; /* explicitly check that the inode_storage_ptr is not * NULL as inode_storage_lookup returns NULL in this case and * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ if (!inode || !inode_storage_ptr(inode)) return (unsigned long)NULL; sdata = inode_storage_lookup(inode, map, true); if (sdata) return (unsigned long)sdata->data; /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { sdata = bpf_local_storage_update( inode, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, gfp_flags); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!inode) return -EINVAL; /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ return inode_storage_delete(inode, map); } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &inode_cache, false); } static void inode_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &inode_cache, NULL); } const struct bpf_map_ops inode_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = inode_storage_map_alloc, .map_free = inode_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_inode_storage_lookup_elem, .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = inode_storage_ptr, }; BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode) const struct bpf_func_proto bpf_inode_storage_get_proto = { .func = bpf_inode_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_inode_storage_delete_proto = { .func = bpf_inode_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], }; |
| 2 2 2 11 11 11 1 11 11 11 1 11 2 1 1 1 1 2 2 2 2 2 10 10 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/igmp.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/if_ether.h> #include <net/ip.h> #include <net/netlink.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/addrconf.h> #endif #include "br_private.h" static bool br_ip4_rports_get_timer(struct net_bridge_mcast_port *pmctx, unsigned long *timer) { *timer = br_timer_value(&pmctx->ip4_mc_router_timer); return !hlist_unhashed(&pmctx->ip4_rlist); } static bool br_ip6_rports_get_timer(struct net_bridge_mcast_port *pmctx, unsigned long *timer) { #if IS_ENABLED(CONFIG_IPV6) *timer = br_timer_value(&pmctx->ip6_mc_router_timer); return !hlist_unhashed(&pmctx->ip6_rlist); #else *timer = 0; return false; #endif } static size_t __br_rports_one_size(void) { return nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PORT */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_TIMER */ nla_total_size(sizeof(u8)) + /* MDBA_ROUTER_PATTR_TYPE */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET_TIMER */ nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET6_TIMER */ nla_total_size(sizeof(u32)); /* MDBA_ROUTER_PATTR_VID */ } size_t br_rports_size(const struct net_bridge_mcast *brmctx) { struct net_bridge_mcast_port *pmctx; size_t size = nla_total_size(0); /* MDBA_ROUTER */ rcu_read_lock(); hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, ip4_rlist) size += __br_rports_one_size(); #if IS_ENABLED(CONFIG_IPV6) hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, ip6_rlist) size += __br_rports_one_size(); #endif rcu_read_unlock(); return size; } int br_rports_fill_info(struct sk_buff *skb, const struct net_bridge_mcast *brmctx) { u16 vid = brmctx->vlan ? brmctx->vlan->vid : 0; bool have_ip4_mc_rtr, have_ip6_mc_rtr; unsigned long ip4_timer, ip6_timer; struct nlattr *nest, *port_nest; struct net_bridge_port *p; if (!brmctx->multicast_router || !br_rports_have_mc_router(brmctx)) return 0; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; list_for_each_entry_rcu(p, &brmctx->br->port_list, list) { struct net_bridge_mcast_port *pmctx; if (vid) { struct net_bridge_vlan *v; v = br_vlan_find(nbp_vlan_group(p), vid); if (!v) continue; pmctx = &v->port_mcast_ctx; } else { pmctx = &p->multicast_ctx; } have_ip4_mc_rtr = br_ip4_rports_get_timer(pmctx, &ip4_timer); have_ip6_mc_rtr = br_ip6_rports_get_timer(pmctx, &ip6_timer); if (!have_ip4_mc_rtr && !have_ip6_mc_rtr) continue; port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto fail; if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, max(ip4_timer, ip6_timer)) || nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, p->multicast_ctx.multicast_router) || (have_ip4_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER, ip4_timer)) || (have_ip6_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER, ip6_timer)) || (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid))) { nla_nest_cancel(skb, port_nest); goto fail; } nla_nest_end(skb, port_nest); } nla_nest_end(skb, nest); return 0; fail: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) { e->state = flags & MDB_PG_FLAGS_PERMANENT; e->flags = 0; if (flags & MDB_PG_FLAGS_OFFLOAD) e->flags |= MDB_FLAGS_OFFLOAD; if (flags & MDB_PG_FLAGS_FAST_LEAVE) e->flags |= MDB_FLAGS_FAST_LEAVE; if (flags & MDB_PG_FLAGS_STAR_EXCL) e->flags |= MDB_FLAGS_STAR_EXCL; if (flags & MDB_PG_FLAGS_BLOCKED) e->flags |= MDB_FLAGS_BLOCKED; } static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, struct nlattr **mdb_attrs) { memset(ip, 0, sizeof(struct br_ip)); ip->vid = entry->vid; ip->proto = entry->addr.proto; switch (ip->proto) { case htons(ETH_P_IP): ip->dst.ip4 = entry->addr.u.ip4; if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip->dst.ip6 = entry->addr.u.ip6; if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #endif default: ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr); } } static int __mdb_fill_srcs(struct sk_buff *skb, struct net_bridge_port_group *p) { struct net_bridge_group_src *ent; struct nlattr *nest, *nest_ent; if (hlist_empty(&p->src_list)) return 0; nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); if (!nest) return -EMSGSIZE; hlist_for_each_entry_rcu(ent, &p->src_list, node, lockdep_is_held(&p->key.port->br->multicast_lock)) { nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); if (!nest_ent) goto out_cancel_err; switch (ent->addr.proto) { case htons(ETH_P_IP): if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, ent->addr.src.ip4)) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, &ent->addr.src.ip6)) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } break; #endif default: nla_nest_cancel(skb, nest_ent); continue; } if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, br_timer_value(&ent->timer))) { nla_nest_cancel(skb, nest_ent); goto out_cancel_err; } nla_nest_end(skb, nest_ent); } nla_nest_end(skb, nest); return 0; out_cancel_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int __mdb_fill_info(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *p) { bool dump_srcs_mode = false; struct timer_list *mtimer; struct nlattr *nest_ent; struct br_mdb_entry e; u8 flags = 0; int ifindex; memset(&e, 0, sizeof(e)); if (p) { ifindex = p->key.port->dev->ifindex; mtimer = &p->timer; flags = p->flags; } else { ifindex = mp->br->dev->ifindex; mtimer = &mp->timer; } __mdb_entry_fill_flags(&e, flags); e.ifindex = ifindex; e.vid = mp->addr.vid; if (mp->addr.proto == htons(ETH_P_IP)) { e.addr.u.ip4 = mp->addr.dst.ip4; #if IS_ENABLED(CONFIG_IPV6) } else if (mp->addr.proto == htons(ETH_P_IPV6)) { e.addr.u.ip6 = mp->addr.dst.ip6; #endif } else { ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); e.state = MDB_PERMANENT; } e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); if (!nest_ent) return -EMSGSIZE; if (nla_put_nohdr(skb, sizeof(e), &e) || nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, br_timer_value(mtimer))) goto nest_err; switch (mp->addr.proto) { case htons(ETH_P_IP): dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_igmp_version == 3); if (mp->addr.src.ip4) { if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE, mp->addr.src.ip4)) goto nest_err; break; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_mld_version == 2); if (!ipv6_addr_any(&mp->addr.src.ip6)) { if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE, &mp->addr.src.ip6)) goto nest_err; break; } break; #endif default: ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); } if (p) { if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol)) goto nest_err; if (dump_srcs_mode && (__mdb_fill_srcs(skb, p) || nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) goto nest_err; } nla_nest_end(skb, nest_ent); return 0; nest_err: nla_nest_cancel(skb, nest_ent); return -EMSGSIZE; } static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2]; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct nlattr *nest, *nest2; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) return -EMSGSIZE; hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; if (idx < s_idx) goto skip; nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!nest2) { err = -EMSGSIZE; break; } if (!s_pidx && mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) { nla_nest_cancel(skb, nest2); break; } } for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; pp = &p->next) { if (!p->key.port) continue; if (pidx < s_pidx) goto skip_pg; err = __mdb_fill_info(skb, mp, p); if (err) { nla_nest_end(skb, nest2); goto out; } skip_pg: pidx++; } pidx = 0; s_pidx = 0; nla_nest_end(skb, nest2); skip: idx++; } out: cb->args[1] = idx; cb->args[2] = pidx; nla_nest_end(skb, nest); return err; } int br_mdb_dump(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct net_bridge *br = netdev_priv(dev); struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETMDB, sizeof(*bpm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->ifindex = dev->ifindex; rcu_read_lock(); err = br_mdb_fill_info(skb, cb, dev); if (err) goto out; err = br_rports_fill_info(skb, &br->multicast_ctx); if (err) goto out; out: rcu_read_unlock(); nlmsg_end(skb, nlh); return err; } static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { struct nlmsghdr *nlh; struct br_port_msg *bpm; struct nlattr *nest, *nest2; nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) goto cancel; nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (nest2 == NULL) goto end; if (__mdb_fill_info(skb, mp, pg)) goto end; nla_nest_end(skb, nest2); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; end: nla_nest_end(skb, nest); cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t rtnl_mdb_nlmsg_pg_size(const struct net_bridge_port_group *pg) { struct net_bridge_group_src *ent; size_t nlmsg_size, addr_size = 0; /* MDBA_MDB_ENTRY_INFO */ nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) + /* MDBA_MDB_EATTR_TIMER */ nla_total_size(sizeof(u32)); if (!pg) goto out; /* MDBA_MDB_EATTR_RTPROT */ nlmsg_size += nla_total_size(sizeof(u8)); switch (pg->key.addr.proto) { case htons(ETH_P_IP): /* MDBA_MDB_EATTR_SOURCE */ if (pg->key.addr.src.ip4) nlmsg_size += nla_total_size(sizeof(__be32)); if (pg->key.port->br->multicast_ctx.multicast_igmp_version == 2) goto out; addr_size = sizeof(__be32); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): /* MDBA_MDB_EATTR_SOURCE */ if (!ipv6_addr_any(&pg->key.addr.src.ip6)) nlmsg_size += nla_total_size(sizeof(struct in6_addr)); if (pg->key.port->br->multicast_ctx.multicast_mld_version == 1) goto out; addr_size = sizeof(struct in6_addr); break; #endif } /* MDBA_MDB_EATTR_GROUP_MODE */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_SRC_LIST nested attr */ if (!hlist_empty(&pg->src_list)) nlmsg_size += nla_total_size(0); hlist_for_each_entry(ent, &pg->src_list, node) { /* MDBA_MDB_SRCLIST_ENTRY nested attr + * MDBA_MDB_SRCATTR_ADDRESS + MDBA_MDB_SRCATTR_TIMER */ nlmsg_size += nla_total_size(0) + nla_total_size(addr_size) + nla_total_size(sizeof(u32)); } out: return nlmsg_size; } static size_t rtnl_mdb_nlmsg_size(const struct net_bridge_port_group *pg) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0) + /* Port group entry */ rtnl_mdb_nlmsg_pg_size(pg); } void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; br_switchdev_mdb_notify(dev, mp, pg, type); skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC); if (!skb) goto errout; err = nlmsg_populate_mdb_fill(skb, dev, mp, pg, type); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static int nlmsg_populate_rtr_fill(struct sk_buff *skb, struct net_device *dev, int ifindex, u16 vid, u32 pid, u32 seq, int type, unsigned int flags) { struct nlattr *nest, *port_nest; struct br_port_msg *bpm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (!nest) goto cancel; port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto end; if (nla_put_nohdr(skb, sizeof(u32), &ifindex)) { nla_nest_cancel(skb, port_nest); goto end; } if (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid)) { nla_nest_cancel(skb, port_nest); goto end; } nla_nest_end(skb, port_nest); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; end: nla_nest_end(skb, nest); cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t rtnl_rtr_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + nla_total_size(sizeof(__u32)) + nla_total_size(sizeof(u16)); } void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; int ifindex; u16 vid; ifindex = pmctx ? pmctx->port->dev->ifindex : 0; vid = pmctx && br_multicast_port_ctx_is_vlan(pmctx) ? pmctx->vlan->vid : 0; skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = nlmsg_populate_rtr_fill(skb, dev, ifindex, vid, 0, 0, type, NTF_SELF); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static const struct nla_policy br_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static const struct nla_policy br_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(br_mdbe_src_list_entry_pol), }; static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto, struct netlink_ext_ack *extack) { switch (proto) { case htons(ETH_P_IP): if (nla_len(attr) != sizeof(struct in_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); return false; } if (ipv4_is_multicast(nla_get_in_addr(attr))) { NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr src; if (nla_len(attr) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); return false; } src = nla_get_in6_addr(attr); if (ipv6_addr_is_multicast(&src)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } break; } #endif default: NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); return false; } return true; } static struct net_bridge_mcast * __br_mdb_choose_context(struct net_bridge *br, const struct br_mdb_entry *entry, struct netlink_ext_ack *extack) { struct net_bridge_mcast *brmctx = NULL; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { brmctx = &br->multicast_ctx; goto out; } if (!entry->vid) { NL_SET_ERR_MSG_MOD(extack, "Cannot add an entry without a vlan when vlan snooping is enabled"); goto out; } v = br_vlan_find(br_vlan_group(br), entry->vid); if (!v) { NL_SET_ERR_MSG_MOD(extack, "Vlan is not configured"); goto out; } if (br_multicast_ctx_vlan_global_disabled(&v->br_mcast_ctx)) { NL_SET_ERR_MSG_MOD(extack, "Vlan's multicast processing is disabled"); goto out; } brmctx = &v->br_mcast_ctx; out: return brmctx; } static int br_mdb_replace_group_sg(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, unsigned char flags) { unsigned long now = jiffies; pg->flags = flags; pg->rt_protocol = cfg->rt_protocol; if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&pg->timer, now + brmctx->multicast_membership_interval); else del_timer(&pg->timer); br_mdb_notify(cfg->br->dev, mp, pg, RTM_NEWMDB); return 0; } static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; unsigned long now = jiffies; for (pp = &mp->ports; (p = mlock_dereference(*pp, cfg->br)) != NULL; pp = &p->next) { if (p->key.port == cfg->p) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "(S, G) group is already joined by port"); return -EEXIST; } return br_mdb_replace_group_sg(cfg, mp, p, brmctx, flags); } if ((unsigned long)p->key.port < (unsigned long)cfg->p) break; } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, MCAST_INCLUDE, cfg->rt_protocol, extack); if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); br_mdb_notify(cfg->br->dev, mp, p, RTM_NEWMDB); /* All of (*, G) EXCLUDE ports need to be added to the new (S, G) for * proper replication. */ if (br_multicast_should_handle_mode(brmctx, cfg->group.proto)) { struct net_bridge_mdb_entry *star_mp; struct br_ip star_group; star_group = p->key.addr; memset(&star_group.src, 0, sizeof(star_group.src)); star_mp = br_mdb_ip_get(cfg->br, &star_group); if (star_mp) br_multicast_sg_add_exclude_ports(star_mp, p); } return 0; } static int br_mdb_add_group_src_fwd(const struct br_mdb_config *cfg, struct br_ip *src_ip, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { struct net_bridge_mdb_entry *sgmp; struct br_mdb_config sg_cfg; struct br_ip sg_ip; u8 flags = 0; sg_ip = cfg->group; sg_ip.src = src_ip->src; sgmp = br_multicast_new_group(cfg->br, &sg_ip); if (IS_ERR(sgmp)) { NL_SET_ERR_MSG_MOD(extack, "Failed to add (S, G) MDB entry"); return PTR_ERR(sgmp); } if (cfg->entry->state == MDB_PERMANENT) flags |= MDB_PG_FLAGS_PERMANENT; if (cfg->filter_mode == MCAST_EXCLUDE) flags |= MDB_PG_FLAGS_BLOCKED; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.br = cfg->br; sg_cfg.p = cfg->p; sg_cfg.entry = cfg->entry; sg_cfg.group = sg_ip; sg_cfg.src_entry = true; sg_cfg.filter_mode = MCAST_INCLUDE; sg_cfg.rt_protocol = cfg->rt_protocol; sg_cfg.nlflags = cfg->nlflags; return br_mdb_add_group_sg(&sg_cfg, sgmp, brmctx, flags, extack); } static int br_mdb_add_group_src(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct br_mdb_src_entry *src, struct netlink_ext_ack *extack) { struct net_bridge_group_src *ent; unsigned long now = jiffies; int err; ent = br_multicast_find_group_src(pg, &src->addr); if (!ent) { ent = br_multicast_new_group_src(pg, &src->addr); if (!ent) { NL_SET_ERR_MSG_MOD(extack, "Failed to add new source entry"); return -ENOSPC; } } else if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); return -EEXIST; } if (cfg->filter_mode == MCAST_INCLUDE && cfg->entry->state == MDB_TEMPORARY) mod_timer(&ent->timer, now + br_multicast_gmi(brmctx)); else del_timer(&ent->timer); /* Install a (S, G) forwarding entry for the source. */ err = br_mdb_add_group_src_fwd(cfg, &src->addr, brmctx, extack); if (err) goto err_del_sg; ent->flags = BR_SGRP_F_INSTALLED | BR_SGRP_F_USER_ADDED; return 0; err_del_sg: __br_multicast_del_group_src(ent); return err; } static void br_mdb_del_group_src(struct net_bridge_port_group *pg, struct br_mdb_src_entry *src) { struct net_bridge_group_src *ent; ent = br_multicast_find_group_src(pg, &src->addr); if (WARN_ON_ONCE(!ent)) return; br_multicast_del_group_src(ent, false); } static int br_mdb_add_group_srcs(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { int i, err; for (i = 0; i < cfg->num_src_entries; i++) { err = br_mdb_add_group_src(cfg, pg, brmctx, &cfg->src_entries[i], extack); if (err) goto err_del_group_srcs; } return 0; err_del_group_srcs: for (i--; i >= 0; i--) br_mdb_del_group_src(pg, &cfg->src_entries[i]); return err; } static int br_mdb_replace_group_srcs(const struct br_mdb_config *cfg, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, struct netlink_ext_ack *extack) { struct net_bridge_group_src *ent; struct hlist_node *tmp; int err; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; err = br_mdb_add_group_srcs(cfg, pg, brmctx, extack); if (err) goto err_clear_delete; hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) { if (ent->flags & BR_SGRP_F_DELETE) br_multicast_del_group_src(ent, false); } return 0; err_clear_delete: hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_DELETE; return err; } static int br_mdb_replace_group_star_g(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { unsigned long now = jiffies; int err; err = br_mdb_replace_group_srcs(cfg, pg, brmctx, extack); if (err) return err; pg->flags = flags; pg->filter_mode = cfg->filter_mode; pg->rt_protocol = cfg->rt_protocol; if (!(flags & MDB_PG_FLAGS_PERMANENT) && cfg->filter_mode == MCAST_EXCLUDE) mod_timer(&pg->timer, now + brmctx->multicast_membership_interval); else del_timer(&pg->timer); br_mdb_notify(cfg->br->dev, mp, pg, RTM_NEWMDB); if (br_multicast_should_handle_mode(brmctx, cfg->group.proto)) br_multicast_star_g_handle_mode(pg, cfg->filter_mode); return 0; } static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, struct net_bridge_mdb_entry *mp, struct net_bridge_mcast *brmctx, unsigned char flags, struct netlink_ext_ack *extack) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; unsigned long now = jiffies; int err; for (pp = &mp->ports; (p = mlock_dereference(*pp, cfg->br)) != NULL; pp = &p->next) { if (p->key.port == cfg->p) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "(*, G) group is already joined by port"); return -EEXIST; } return br_mdb_replace_group_star_g(cfg, mp, p, brmctx, flags, extack); } if ((unsigned long)p->key.port < (unsigned long)cfg->p) break; } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, cfg->filter_mode, cfg->rt_protocol, extack); if (unlikely(!p)) return -ENOMEM; err = br_mdb_add_group_srcs(cfg, p, brmctx, extack); if (err) goto err_del_port_group; rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && cfg->filter_mode == MCAST_EXCLUDE) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); br_mdb_notify(cfg->br->dev, mp, p, RTM_NEWMDB); /* If we are adding a new EXCLUDE port group (*, G), it needs to be * also added to all (S, G) entries for proper replication. */ if (br_multicast_should_handle_mode(brmctx, cfg->group.proto) && cfg->filter_mode == MCAST_EXCLUDE) br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE); return 0; err_del_port_group: br_multicast_del_port_group(p); return err; } static int br_mdb_add_group(const struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = cfg->entry; struct net_bridge_port *port = cfg->p; struct net_bridge_mdb_entry *mp; struct net_bridge *br = cfg->br; struct net_bridge_mcast *brmctx; struct br_ip group = cfg->group; unsigned char flags = 0; brmctx = __br_mdb_choose_context(br, entry, extack); if (!brmctx) return -EINVAL; mp = br_multicast_new_group(br, &group); if (IS_ERR(mp)) return PTR_ERR(mp); /* host join */ if (!port) { if (mp->host_joined) { NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; } br_multicast_host_join(brmctx, mp, false); br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB); return 0; } if (entry->state == MDB_PERMANENT) flags |= MDB_PG_FLAGS_PERMANENT; if (br_multicast_is_star_g(&group)) return br_mdb_add_group_star_g(cfg, mp, brmctx, flags, extack); else return br_mdb_add_group_sg(cfg, mp, brmctx, flags, extack); } static int __br_mdb_add(const struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { int ret; spin_lock_bh(&cfg->br->multicast_lock); ret = br_mdb_add_group(cfg, extack); spin_unlock_bh(&cfg->br->multicast_lock); return ret; } static int br_mdb_config_src_entry_init(struct nlattr *src_entry, struct br_mdb_src_entry *src, __be16 proto, struct netlink_ext_ack *extack) { struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; int err; err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, br_mdbe_src_list_entry_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) return -EINVAL; if (!is_valid_mdb_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) return -EINVAL; src->addr.proto = proto; nla_memcpy(&src->addr.src, tb[MDBE_SRCATTR_ADDRESS], nla_len(tb[MDBE_SRCATTR_ADDRESS])); return 0; } static int br_mdb_config_src_list_init(struct nlattr *src_list, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *src_entry; int rem, err; int i = 0; nla_for_each_nested(src_entry, src_list, rem) cfg->num_src_entries++; if (cfg->num_src_entries >= PG_SRC_ENT_LIMIT) { NL_SET_ERR_MSG_FMT_MOD(extack, "Exceeded maximum number of source entries (%u)", PG_SRC_ENT_LIMIT - 1); return -EINVAL; } cfg->src_entries = kcalloc(cfg->num_src_entries, sizeof(struct br_mdb_src_entry), GFP_KERNEL); if (!cfg->src_entries) return -ENOMEM; nla_for_each_nested(src_entry, src_list, rem) { err = br_mdb_config_src_entry_init(src_entry, &cfg->src_entries[i], cfg->entry->addr.proto, extack); if (err) goto err_src_entry_init; i++; } return 0; err_src_entry_init: kfree(cfg->src_entries); return err; } static void br_mdb_config_src_list_fini(struct br_mdb_config *cfg) { kfree(cfg->src_entries); } static int br_mdb_config_attrs_init(struct nlattr *set_attrs, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1]; int err; err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX, set_attrs, br_mdbe_attrs_pol, extack); if (err) return err; if (mdb_attrs[MDBE_ATTR_SOURCE] && !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE], cfg->entry->addr.proto, extack)) return -EINVAL; __mdb_entry_to_br_ip(cfg->entry, &cfg->group, mdb_attrs); if (mdb_attrs[MDBE_ATTR_GROUP_MODE]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Filter mode cannot be set for host groups"); return -EINVAL; } if (!br_multicast_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); return -EINVAL; } cfg->filter_mode = nla_get_u8(mdb_attrs[MDBE_ATTR_GROUP_MODE]); } else { cfg->filter_mode = MCAST_EXCLUDE; } if (mdb_attrs[MDBE_ATTR_SRC_LIST]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set for host groups"); return -EINVAL; } if (!br_multicast_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); return -EINVAL; } if (!mdb_attrs[MDBE_ATTR_GROUP_MODE]) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); return -EINVAL; } err = br_mdb_config_src_list_init(mdb_attrs[MDBE_ATTR_SRC_LIST], cfg, extack); if (err) return err; } if (!cfg->num_src_entries && cfg->filter_mode == MCAST_INCLUDE) { NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); return -EINVAL; } if (mdb_attrs[MDBE_ATTR_RTPROT]) { if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be set for host groups"); return -EINVAL; } cfg->rt_protocol = nla_get_u8(mdb_attrs[MDBE_ATTR_RTPROT]); } return 0; } static int br_mdb_config_init(struct br_mdb_config *cfg, struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); memset(cfg, 0, sizeof(*cfg)); cfg->filter_mode = MCAST_EXCLUDE; cfg->rt_protocol = RTPROT_STATIC; cfg->nlflags = nlmsg_flags; cfg->br = netdev_priv(dev); if (!netif_running(cfg->br->dev)) { NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running"); return -EINVAL; } if (!br_opt_get(cfg->br, BROPT_MULTICAST_ENABLED)) { NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled"); return -EINVAL; } cfg->entry = nla_data(tb[MDBA_SET_ENTRY]); if (cfg->entry->ifindex != cfg->br->dev->ifindex) { struct net_device *pdev; pdev = __dev_get_by_index(net, cfg->entry->ifindex); if (!pdev) { NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist"); return -ENODEV; } cfg->p = br_port_get_rtnl(pdev); if (!cfg->p) { NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port"); return -EINVAL; } if (cfg->p->br != cfg->br) { NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; } } if (cfg->entry->addr.proto == htons(ETH_P_IP) && ipv4_is_zeronet(cfg->entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address 0.0.0.0 is not allowed"); return -EINVAL; } if (tb[MDBA_SET_ENTRY_ATTRS]) return br_mdb_config_attrs_init(tb[MDBA_SET_ENTRY_ATTRS], cfg, extack); else __mdb_entry_to_br_ip(cfg->entry, &cfg->group, NULL); return 0; } static void br_mdb_config_fini(struct br_mdb_config *cfg) { br_mdb_config_src_list_fini(cfg); } int br_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct br_mdb_config cfg; int err; err = br_mdb_config_init(&cfg, dev, tb, nlmsg_flags, extack); if (err) return err; err = -EINVAL; /* host join errors which can happen before creating the group */ if (!cfg.p && !br_group_is_l2(&cfg.group)) { /* don't allow any flags for host-joined IP groups */ if (cfg.entry->state) { NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups"); goto out; } if (!br_multicast_is_star_g(&cfg.group)) { NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined"); goto out; } } if (br_group_is_l2(&cfg.group) && cfg.entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed"); goto out; } if (cfg.p) { if (cfg.p->state == BR_STATE_DISABLED && cfg.entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state and entry is not permanent"); goto out; } vg = nbp_vlan_group(cfg.p); } else { vg = br_vlan_group(cfg.br); } /* If vlan filtering is enabled and VLAN is not specified * install mdb entry on all vlans configured on the port. */ if (br_vlan_enabled(cfg.br->dev) && vg && cfg.entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { cfg.entry->vid = v->vid; cfg.group.vid = v->vid; err = __br_mdb_add(&cfg, extack); if (err) break; } } else { err = __br_mdb_add(&cfg, extack); } out: br_mdb_config_fini(&cfg); return err; } static int __br_mdb_del(const struct br_mdb_config *cfg) { struct br_mdb_entry *entry = cfg->entry; struct net_bridge *br = cfg->br; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip ip = cfg->group; int err = -EINVAL; spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &ip); if (!mp) goto unlock; /* host leave */ if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) { br_multicast_host_leave(mp, false); err = 0; br_mdb_notify(br->dev, mp, NULL, RTM_DELMDB); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); goto unlock; } for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex) continue; br_multicast_del_pg(mp, p, pp); err = 0; break; } unlock: spin_unlock_bh(&br->multicast_lock); return err; } int br_mdb_del(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct br_mdb_config cfg; int err; err = br_mdb_config_init(&cfg, dev, tb, 0, extack); if (err) return err; if (cfg.p) vg = nbp_vlan_group(cfg.p); else vg = br_vlan_group(cfg.br); /* If vlan filtering is enabled and VLAN is not specified * delete mdb entry on all vlans configured on the port. */ if (br_vlan_enabled(cfg.br->dev) && vg && cfg.entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { cfg.entry->vid = v->vid; cfg.group.vid = v->vid; err = __br_mdb_del(&cfg); } } else { err = __br_mdb_del(&cfg); } br_mdb_config_fini(&cfg); return err; } struct br_mdb_flush_desc { u32 port_ifindex; u16 vid; u8 rt_protocol; u8 state; u8 state_mask; }; static const struct nla_policy br_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT), }; static int br_mdb_flush_desc_init(struct br_mdb_flush_desc *desc, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; desc->port_ifindex = entry->ifindex; desc->vid = entry->vid; desc->state = entry->state; if (!tb[MDBA_SET_ENTRY_ATTRS]) return 0; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_SET_ENTRY_ATTRS], br_mdbe_attrs_del_bulk_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) desc->state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]); if (mdbe_attrs[MDBE_ATTR_RTPROT]) desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); return 0; } static void br_mdb_flush_host(struct net_bridge *br, struct net_bridge_mdb_entry *mp, const struct br_mdb_flush_desc *desc) { u8 state; if (desc->port_ifindex && desc->port_ifindex != br->dev->ifindex) return; if (desc->rt_protocol) return; state = br_group_is_l2(&mp->addr) ? MDB_PERMANENT : 0; if (desc->state_mask && (state & desc->state_mask) != desc->state) return; br_multicast_host_leave(mp, true); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } static void br_mdb_flush_pgs(struct net_bridge *br, struct net_bridge_mdb_entry *mp, const struct br_mdb_flush_desc *desc) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;) { u8 state; if (desc->port_ifindex && desc->port_ifindex != p->key.port->dev->ifindex) { pp = &p->next; continue; } if (desc->rt_protocol && desc->rt_protocol != p->rt_protocol) { pp = &p->next; continue; } state = p->flags & MDB_PG_FLAGS_PERMANENT ? MDB_PERMANENT : 0; if (desc->state_mask && (state & desc->state_mask) != desc->state) { pp = &p->next; continue; } br_multicast_del_pg(mp, p, pp); } } static void br_mdb_flush(struct net_bridge *br, const struct br_mdb_flush_desc *desc) { struct net_bridge_mdb_entry *mp; spin_lock_bh(&br->multicast_lock); /* Safe variant is not needed because entries are removed from the list * upon group timer expiration or bridge deletion. */ hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { if (desc->vid && desc->vid != mp->addr.vid) continue; br_mdb_flush_host(br, mp, desc); br_mdb_flush_pgs(br, mp, desc); } spin_unlock_bh(&br->multicast_lock); } int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct br_mdb_flush_desc desc = {}; int err; err = br_mdb_flush_desc_init(&desc, tb, extack); if (err) return err; br_mdb_flush(br, &desc); return 0; } static const struct nla_policy br_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static int br_mdb_get_parse(struct net_device *dev, struct nlattr *tb[], struct br_ip *group, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; if (!tb[MDBA_GET_ENTRY_ATTRS]) { __mdb_entry_to_br_ip(entry, group, NULL); return 0; } err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_GET_ENTRY_ATTRS], br_mdbe_attrs_get_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_SOURCE] && !is_valid_mdb_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; __mdb_entry_to_br_ip(entry, group, mdbe_attrs); return 0; } static struct sk_buff * br_mdb_get_reply_alloc(const struct net_bridge_mdb_entry *mp) { struct net_bridge_port_group *pg; size_t nlmsg_size; nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0); if (mp->host_joined) nlmsg_size += rtnl_mdb_nlmsg_pg_size(NULL); for (pg = mlock_dereference(mp->ports, mp->br); pg; pg = mlock_dereference(pg->next, mp->br)) nlmsg_size += rtnl_mdb_nlmsg_pg_size(pg); return nlmsg_new(nlmsg_size, GFP_ATOMIC); } static int br_mdb_get_reply_fill(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, u32 portid, u32 seq) { struct nlattr *mdb_nest, *mdb_entry_nest; struct net_bridge_port_group *pg; struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = mp->br->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) { err = -EMSGSIZE; goto cancel; } mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) { err = -EMSGSIZE; goto cancel; } if (mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) goto cancel; } for (pg = mlock_dereference(mp->ports, mp->br); pg; pg = mlock_dereference(pg->next, mp->br)) { err = __mdb_fill_info(skb, mp, pg); if (err) goto cancel; } nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return err; } int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct sk_buff *skb; struct br_ip group; int err; err = br_mdb_get_parse(dev, tb, &group, extack); if (err) return err; /* Hold the multicast lock to ensure that the MDB entry does not change * between the time the reply size is determined and when the reply is * filled in. */ spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &group); if (!mp) { NL_SET_ERR_MSG_MOD(extack, "MDB entry not found"); err = -ENOENT; goto unlock; } skb = br_mdb_get_reply_alloc(mp); if (!skb) { err = -ENOMEM; goto unlock; } err = br_mdb_get_reply_fill(skb, mp, portid, seq); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply"); goto free; } spin_unlock_bh(&br->multicast_lock); return rtnl_unicast(skb, dev_net(dev), portid); free: kfree_skb(skb); unlock: spin_unlock_bh(&br->multicast_lock); return err; } |
| 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 | /* * ppp_mppe.c - interface MPPE to the PPP code. * This version is for use with Linux kernel 2.6.14+ * * By Frank Cusack <fcusack@fcusack.com>. * Copyright (c) 2002,2003,2004 Google, Inc. * All rights reserved. * * License: * Permission to use, copy, modify, and distribute this software and its * documentation is hereby granted, provided that the above copyright * notice appears in all copies. This software is provided without any * warranty, express or implied. * * ALTERNATIVELY, provided that this notice is retained in full, this product * may be distributed under the terms of the GNU General Public License (GPL), * in which case the provisions of the GPL apply INSTEAD OF those given above. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, see <http://www.gnu.org/licenses/>. * * * Changelog: * 08/12/05 - Matt Domsch <Matt_Domsch@dell.com> * Only need extra skb padding on transmit, not receive. * 06/18/04 - Matt Domsch <Matt_Domsch@dell.com>, Oleg Makarenko <mole@quadra.ru> * Use Linux kernel 2.6 arc4 and sha1 routines rather than * providing our own. * 2/15/04 - TS: added #include <version.h> and testing for Kernel * version before using * MOD_DEC_USAGE_COUNT/MOD_INC_USAGE_COUNT which are * deprecated in 2.6 */ #include <crypto/arc4.h> #include <crypto/hash.h> #include <linux/err.h> #include <linux/fips.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/ppp_defs.h> #include <linux/ppp-comp.h> #include <linux/scatterlist.h> #include <asm/unaligned.h> #include "ppp_mppe.h" MODULE_AUTHOR("Frank Cusack <fcusack@fcusack.com>"); MODULE_DESCRIPTION("Point-to-Point Protocol Microsoft Point-to-Point Encryption support"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_MPPE)); MODULE_VERSION("1.0.2"); #define SHA1_PAD_SIZE 40 /* * kernel crypto API needs its arguments to be in kmalloc'd memory, not in the module * static data area. That means sha_pad needs to be kmalloc'd. */ struct sha_pad { unsigned char sha_pad1[SHA1_PAD_SIZE]; unsigned char sha_pad2[SHA1_PAD_SIZE]; }; static struct sha_pad *sha_pad; static inline void sha_pad_init(struct sha_pad *shapad) { memset(shapad->sha_pad1, 0x00, sizeof(shapad->sha_pad1)); memset(shapad->sha_pad2, 0xF2, sizeof(shapad->sha_pad2)); } /* * State for an MPPE (de)compressor. */ struct ppp_mppe_state { struct arc4_ctx arc4; struct shash_desc *sha1; unsigned char *sha1_digest; unsigned char master_key[MPPE_MAX_KEY_LEN]; unsigned char session_key[MPPE_MAX_KEY_LEN]; unsigned keylen; /* key length in bytes */ /* NB: 128-bit == 16, 40-bit == 8! */ /* If we want to support 56-bit, */ /* the unit has to change to bits */ unsigned char bits; /* MPPE control bits */ unsigned ccount; /* 12-bit coherency count (seqno) */ unsigned stateful; /* stateful mode flag */ int discard; /* stateful mode packet loss flag */ int sanity_errors; /* take down LCP if too many */ int unit; int debug; struct compstat stats; }; /* struct ppp_mppe_state.bits definitions */ #define MPPE_BIT_A 0x80 /* Encryption table were (re)inititalized */ #define MPPE_BIT_B 0x40 /* MPPC only (not implemented) */ #define MPPE_BIT_C 0x20 /* MPPC only (not implemented) */ #define MPPE_BIT_D 0x10 /* This is an encrypted frame */ #define MPPE_BIT_FLUSHED MPPE_BIT_A #define MPPE_BIT_ENCRYPTED MPPE_BIT_D #define MPPE_BITS(p) ((p)[4] & 0xf0) #define MPPE_CCOUNT(p) ((((p)[4] & 0x0f) << 8) + (p)[5]) #define MPPE_CCOUNT_SPACE 0x1000 /* The size of the ccount space */ #define MPPE_OVHD 2 /* MPPE overhead/packet */ #define SANITY_MAX 1600 /* Max bogon factor we will tolerate */ /* * Key Derivation, from RFC 3078, RFC 3079. * Equivalent to Get_Key() for MS-CHAP as described in RFC 3079. */ static void get_new_key_from_sha(struct ppp_mppe_state * state) { crypto_shash_init(state->sha1); crypto_shash_update(state->sha1, state->master_key, state->keylen); crypto_shash_update(state->sha1, sha_pad->sha_pad1, sizeof(sha_pad->sha_pad1)); crypto_shash_update(state->sha1, state->session_key, state->keylen); crypto_shash_update(state->sha1, sha_pad->sha_pad2, sizeof(sha_pad->sha_pad2)); crypto_shash_final(state->sha1, state->sha1_digest); } /* * Perform the MPPE rekey algorithm, from RFC 3078, sec. 7.3. * Well, not what's written there, but rather what they meant. */ static void mppe_rekey(struct ppp_mppe_state * state, int initial_key) { get_new_key_from_sha(state); if (!initial_key) { arc4_setkey(&state->arc4, state->sha1_digest, state->keylen); arc4_crypt(&state->arc4, state->session_key, state->sha1_digest, state->keylen); } else { memcpy(state->session_key, state->sha1_digest, state->keylen); } if (state->keylen == 8) { /* See RFC 3078 */ state->session_key[0] = 0xd1; state->session_key[1] = 0x26; state->session_key[2] = 0x9e; } arc4_setkey(&state->arc4, state->session_key, state->keylen); } /* * Allocate space for a (de)compressor. */ static void *mppe_alloc(unsigned char *options, int optlen) { struct ppp_mppe_state *state; struct crypto_shash *shash; unsigned int digestsize; if (optlen != CILEN_MPPE + sizeof(state->master_key) || options[0] != CI_MPPE || options[1] != CILEN_MPPE || fips_enabled) goto out; state = kzalloc(sizeof(*state), GFP_KERNEL); if (state == NULL) goto out; shash = crypto_alloc_shash("sha1", 0, 0); if (IS_ERR(shash)) goto out_free; state->sha1 = kmalloc(sizeof(*state->sha1) + crypto_shash_descsize(shash), GFP_KERNEL); if (!state->sha1) { crypto_free_shash(shash); goto out_free; } state->sha1->tfm = shash; digestsize = crypto_shash_digestsize(shash); if (digestsize < MPPE_MAX_KEY_LEN) goto out_free; state->sha1_digest = kmalloc(digestsize, GFP_KERNEL); if (!state->sha1_digest) goto out_free; /* Save keys. */ memcpy(state->master_key, &options[CILEN_MPPE], sizeof(state->master_key)); memcpy(state->session_key, state->master_key, sizeof(state->master_key)); /* * We defer initial key generation until mppe_init(), as mppe_alloc() * is called frequently during negotiation. */ return (void *)state; out_free: kfree(state->sha1_digest); if (state->sha1) { crypto_free_shash(state->sha1->tfm); kfree_sensitive(state->sha1); } kfree(state); out: return NULL; } /* * Deallocate space for a (de)compressor. */ static void mppe_free(void *arg) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; if (state) { kfree(state->sha1_digest); crypto_free_shash(state->sha1->tfm); kfree_sensitive(state->sha1); kfree_sensitive(state); } } /* * Initialize (de)compressor state. */ static int mppe_init(void *arg, unsigned char *options, int optlen, int unit, int debug, const char *debugstr) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; unsigned char mppe_opts; if (optlen != CILEN_MPPE || options[0] != CI_MPPE || options[1] != CILEN_MPPE) return 0; MPPE_CI_TO_OPTS(&options[2], mppe_opts); if (mppe_opts & MPPE_OPT_128) state->keylen = 16; else if (mppe_opts & MPPE_OPT_40) state->keylen = 8; else { printk(KERN_WARNING "%s[%d]: unknown key length\n", debugstr, unit); return 0; } if (mppe_opts & MPPE_OPT_STATEFUL) state->stateful = 1; /* Generate the initial session key. */ mppe_rekey(state, 1); if (debug) { printk(KERN_DEBUG "%s[%d]: initialized with %d-bit %s mode\n", debugstr, unit, (state->keylen == 16) ? 128 : 40, (state->stateful) ? "stateful" : "stateless"); printk(KERN_DEBUG "%s[%d]: keys: master: %*phN initial session: %*phN\n", debugstr, unit, (int)sizeof(state->master_key), state->master_key, (int)sizeof(state->session_key), state->session_key); } /* * Initialize the coherency count. The initial value is not specified * in RFC 3078, but we can make a reasonable assumption that it will * start at 0. Setting it to the max here makes the comp/decomp code * do the right thing (determined through experiment). */ state->ccount = MPPE_CCOUNT_SPACE - 1; /* * Note that even though we have initialized the key table, we don't * set the FLUSHED bit. This is contrary to RFC 3078, sec. 3.1. */ state->bits = MPPE_BIT_ENCRYPTED; state->unit = unit; state->debug = debug; return 1; } static int mppe_comp_init(void *arg, unsigned char *options, int optlen, int unit, int hdrlen, int debug) { /* ARGSUSED */ return mppe_init(arg, options, optlen, unit, debug, "mppe_comp_init"); } /* * We received a CCP Reset-Request (actually, we are sending a Reset-Ack), * tell the compressor to rekey. Note that we MUST NOT rekey for * every CCP Reset-Request; we only rekey on the next xmit packet. * We might get multiple CCP Reset-Requests if our CCP Reset-Ack is lost. * So, rekeying for every CCP Reset-Request is broken as the peer will not * know how many times we've rekeyed. (If we rekey and THEN get another * CCP Reset-Request, we must rekey again.) */ static void mppe_comp_reset(void *arg) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; state->bits |= MPPE_BIT_FLUSHED; } /* * Compress (encrypt) a packet. * It's strange to call this a compressor, since the output is always * MPPE_OVHD + 2 bytes larger than the input. */ static int mppe_compress(void *arg, unsigned char *ibuf, unsigned char *obuf, int isize, int osize) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; int proto; /* * Check that the protocol is in the range we handle. */ proto = PPP_PROTOCOL(ibuf); if (proto < 0x0021 || proto > 0x00fa) return 0; /* Make sure we have enough room to generate an encrypted packet. */ if (osize < isize + MPPE_OVHD + 2) { /* Drop the packet if we should encrypt it, but can't. */ printk(KERN_DEBUG "mppe_compress[%d]: osize too small! " "(have: %d need: %d)\n", state->unit, osize, osize + MPPE_OVHD + 2); return -1; } osize = isize + MPPE_OVHD + 2; /* * Copy over the PPP header and set control bits. */ obuf[0] = PPP_ADDRESS(ibuf); obuf[1] = PPP_CONTROL(ibuf); put_unaligned_be16(PPP_COMP, obuf + 2); obuf += PPP_HDRLEN; state->ccount = (state->ccount + 1) % MPPE_CCOUNT_SPACE; if (state->debug >= 7) printk(KERN_DEBUG "mppe_compress[%d]: ccount %d\n", state->unit, state->ccount); put_unaligned_be16(state->ccount, obuf); if (!state->stateful || /* stateless mode */ ((state->ccount & 0xff) == 0xff) || /* "flag" packet */ (state->bits & MPPE_BIT_FLUSHED)) { /* CCP Reset-Request */ /* We must rekey */ if (state->debug && state->stateful) printk(KERN_DEBUG "mppe_compress[%d]: rekeying\n", state->unit); mppe_rekey(state, 0); state->bits |= MPPE_BIT_FLUSHED; } obuf[0] |= state->bits; state->bits &= ~MPPE_BIT_FLUSHED; /* reset for next xmit */ obuf += MPPE_OVHD; ibuf += 2; /* skip to proto field */ isize -= 2; arc4_crypt(&state->arc4, obuf, ibuf, isize); state->stats.unc_bytes += isize; state->stats.unc_packets++; state->stats.comp_bytes += osize; state->stats.comp_packets++; return osize; } /* * Since every frame grows by MPPE_OVHD + 2 bytes, this is always going * to look bad ... and the longer the link is up the worse it will get. */ static void mppe_comp_stats(void *arg, struct compstat *stats) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; *stats = state->stats; } static int mppe_decomp_init(void *arg, unsigned char *options, int optlen, int unit, int hdrlen, int mru, int debug) { /* ARGSUSED */ return mppe_init(arg, options, optlen, unit, debug, "mppe_decomp_init"); } /* * We received a CCP Reset-Ack. Just ignore it. */ static void mppe_decomp_reset(void *arg) { /* ARGSUSED */ return; } /* * Decompress (decrypt) an MPPE packet. */ static int mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, int osize) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; unsigned ccount; int flushed = MPPE_BITS(ibuf) & MPPE_BIT_FLUSHED; if (isize <= PPP_HDRLEN + MPPE_OVHD) { if (state->debug) printk(KERN_DEBUG "mppe_decompress[%d]: short pkt (%d)\n", state->unit, isize); return DECOMP_ERROR; } /* * Make sure we have enough room to decrypt the packet. * Note that for our test we only subtract 1 byte whereas in * mppe_compress() we added 2 bytes (+MPPE_OVHD); * this is to account for possible PFC. */ if (osize < isize - MPPE_OVHD - 1) { printk(KERN_DEBUG "mppe_decompress[%d]: osize too small! " "(have: %d need: %d)\n", state->unit, osize, isize - MPPE_OVHD - 1); return DECOMP_ERROR; } osize = isize - MPPE_OVHD - 2; /* assume no PFC */ ccount = MPPE_CCOUNT(ibuf); if (state->debug >= 7) printk(KERN_DEBUG "mppe_decompress[%d]: ccount %d\n", state->unit, ccount); /* sanity checks -- terminate with extreme prejudice */ if (!(MPPE_BITS(ibuf) & MPPE_BIT_ENCRYPTED)) { printk(KERN_DEBUG "mppe_decompress[%d]: ENCRYPTED bit not set!\n", state->unit); state->sanity_errors += 100; goto sanity_error; } if (!state->stateful && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set in " "stateless mode!\n", state->unit); state->sanity_errors += 100; goto sanity_error; } if (state->stateful && ((ccount & 0xff) == 0xff) && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set on " "flag packet!\n", state->unit); state->sanity_errors += 100; goto sanity_error; } /* * Check the coherency count. */ if (!state->stateful) { /* Discard late packet */ if ((ccount - state->ccount) % MPPE_CCOUNT_SPACE > MPPE_CCOUNT_SPACE / 2) { state->sanity_errors++; goto sanity_error; } /* RFC 3078, sec 8.1. Rekey for every packet. */ while (state->ccount != ccount) { mppe_rekey(state, 0); state->ccount = (state->ccount + 1) % MPPE_CCOUNT_SPACE; } } else { /* RFC 3078, sec 8.2. */ if (!state->discard) { /* normal state */ state->ccount = (state->ccount + 1) % MPPE_CCOUNT_SPACE; if (ccount != state->ccount) { /* * (ccount > state->ccount) * Packet loss detected, enter the discard state. * Signal the peer to rekey (by sending a CCP Reset-Request). */ state->discard = 1; return DECOMP_ERROR; } } else { /* discard state */ if (!flushed) { /* ccp.c will be silent (no additional CCP Reset-Requests). */ return DECOMP_ERROR; } else { /* Rekey for every missed "flag" packet. */ while ((ccount & ~0xff) != (state->ccount & ~0xff)) { mppe_rekey(state, 0); state->ccount = (state->ccount + 256) % MPPE_CCOUNT_SPACE; } /* reset */ state->discard = 0; state->ccount = ccount; /* * Another problem with RFC 3078 here. It implies that the * peer need not send a Reset-Ack packet. But RFC 1962 * requires it. Hopefully, M$ does send a Reset-Ack; even * though it isn't required for MPPE synchronization, it is * required to reset CCP state. */ } } if (flushed) mppe_rekey(state, 0); } /* * Fill in the first part of the PPP header. The protocol field * comes from the decrypted data. */ obuf[0] = PPP_ADDRESS(ibuf); /* +1 */ obuf[1] = PPP_CONTROL(ibuf); /* +1 */ obuf += 2; ibuf += PPP_HDRLEN + MPPE_OVHD; isize -= PPP_HDRLEN + MPPE_OVHD; /* -6 */ /* net osize: isize-4 */ /* * Decrypt the first byte in order to check if it is * a compressed or uncompressed protocol field. */ arc4_crypt(&state->arc4, obuf, ibuf, 1); /* * Do PFC decompression. * This would be nicer if we were given the actual sk_buff * instead of a char *. */ if ((obuf[0] & 0x01) != 0) { obuf[1] = obuf[0]; obuf[0] = 0; obuf++; osize++; } /* And finally, decrypt the rest of the packet. */ arc4_crypt(&state->arc4, obuf + 1, ibuf + 1, isize - 1); state->stats.unc_bytes += osize; state->stats.unc_packets++; state->stats.comp_bytes += isize; state->stats.comp_packets++; /* good packet credit */ state->sanity_errors >>= 1; return osize; sanity_error: if (state->sanity_errors < SANITY_MAX) return DECOMP_ERROR; else /* Take LCP down if the peer is sending too many bogons. * We don't want to do this for a single or just a few * instances since it could just be due to packet corruption. */ return DECOMP_FATALERROR; } /* * Incompressible data has arrived (this should never happen!). * We should probably drop the link if the protocol is in the range * of what should be encrypted. At the least, we should drop this * packet. (How to do this?) */ static void mppe_incomp(void *arg, unsigned char *ibuf, int icnt) { struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; if (state->debug && (PPP_PROTOCOL(ibuf) >= 0x0021 && PPP_PROTOCOL(ibuf) <= 0x00fa)) printk(KERN_DEBUG "mppe_incomp[%d]: incompressible (unencrypted) data! " "(proto %04x)\n", state->unit, PPP_PROTOCOL(ibuf)); state->stats.inc_bytes += icnt; state->stats.inc_packets++; state->stats.unc_bytes += icnt; state->stats.unc_packets++; } /************************************************************* * Module interface table *************************************************************/ /* * Procedures exported to if_ppp.c. */ static struct compressor ppp_mppe = { .compress_proto = CI_MPPE, .comp_alloc = mppe_alloc, .comp_free = mppe_free, .comp_init = mppe_comp_init, .comp_reset = mppe_comp_reset, .compress = mppe_compress, .comp_stat = mppe_comp_stats, .decomp_alloc = mppe_alloc, .decomp_free = mppe_free, .decomp_init = mppe_decomp_init, .decomp_reset = mppe_decomp_reset, .decompress = mppe_decompress, .incomp = mppe_incomp, .decomp_stat = mppe_comp_stats, .owner = THIS_MODULE, .comp_extra = MPPE_PAD, }; /* * ppp_mppe_init() * * Prior to allowing load, try to load the arc4 and sha1 crypto * libraries. The actual use will be allocated later, but * this way the module will fail to insmod if they aren't available. */ static int __init ppp_mppe_init(void) { int answer; if (fips_enabled || !crypto_has_ahash("sha1", 0, CRYPTO_ALG_ASYNC)) return -ENODEV; sha_pad = kmalloc(sizeof(struct sha_pad), GFP_KERNEL); if (!sha_pad) return -ENOMEM; sha_pad_init(sha_pad); answer = ppp_register_compressor(&ppp_mppe); if (answer == 0) printk(KERN_INFO "PPP MPPE Compression module registered\n"); else kfree(sha_pad); return answer; } static void __exit ppp_mppe_cleanup(void) { ppp_unregister_compressor(&ppp_mppe); kfree(sha_pad); } module_init(ppp_mppe_init); module_exit(ppp_mppe_cleanup); |
| 2 2 1525 1524 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "LAPB via ethernet" driver release 001 * * This code REQUIRES 2.1.15 or higher/ NET3.038 * * This is a "pseudo" network driver to allow LAPB over Ethernet. * * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * History * LAPBETH 001 Jonathan Naylor Cloned from bpqether.c * 2000-10-29 Henner Eisen lapb_data_indication() return status. * 2000-11-14 Henner Eisen dev_hold/put, NETDEV_GOING_DOWN support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/stat.h> #include <linux/module.h> #include <linux/lapb.h> #include <linux/init.h> #include <net/x25device.h> static const u8 bcast_addr[6] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; /* If this number is made larger, check that the temporary string buffer * in lapbeth_new_device is large enough to store the probe device name. */ #define MAXLAPBDEV 100 struct lapbethdev { struct list_head node; struct net_device *ethdev; /* link to ethernet device */ struct net_device *axdev; /* lapbeth device (lapb#) */ bool up; spinlock_t up_lock; /* Protects "up" */ struct sk_buff_head rx_queue; struct napi_struct napi; }; static LIST_HEAD(lapbeth_devices); static void lapbeth_connected(struct net_device *dev, int reason); static void lapbeth_disconnected(struct net_device *dev, int reason); /* ------------------------------------------------------------------------ */ /* Get the LAPB device for the ethernet device */ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) { struct lapbethdev *lapbeth; list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) { if (lapbeth->ethdev == dev) return lapbeth; } return NULL; } static __inline__ int dev_is_ethdev(struct net_device *dev) { return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); } /* ------------------------------------------------------------------------ */ static int lapbeth_napi_poll(struct napi_struct *napi, int budget) { struct lapbethdev *lapbeth = container_of(napi, struct lapbethdev, napi); struct sk_buff *skb; int processed = 0; for (; processed < budget; ++processed) { skb = skb_dequeue(&lapbeth->rx_queue); if (!skb) break; netif_receive_skb_core(skb); } if (processed < budget) napi_complete(napi); return processed; } /* Receive a LAPB frame via an ethernet interface. */ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { int len, err; struct lapbethdev *lapbeth; if (dev_net(dev) != &init_net) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, 2)) goto drop; rcu_read_lock(); lapbeth = lapbeth_get_x25_dev(dev); if (!lapbeth) goto drop_unlock_rcu; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop_unlock; len = skb->data[0] + skb->data[1] * 256; dev->stats.rx_packets++; dev->stats.rx_bytes += len; skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ err = lapb_data_received(lapbeth->axdev, skb); if (err != LAPB_OK) { printk(KERN_DEBUG "lapbether: lapb_data_received err - %d\n", err); goto drop_unlock; } out: spin_unlock_bh(&lapbeth->up_lock); rcu_read_unlock(); return 0; drop_unlock: kfree_skb(skb); goto out; drop_unlock_rcu: rcu_read_unlock(); drop: kfree_skb(skb); return 0; } static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; if (skb_cow(skb, 1)) { kfree_skb(skb); return NET_RX_DROP; } skb_push(skb, 1); ptr = skb->data; *ptr = X25_IFACE_DATA; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); return NET_RX_SUCCESS; } /* Send a LAPB frame via an ethernet interface */ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop; /* There should be a pseudo header of 1 byte added by upper layers. * Check to make sure it is there before reading it. */ if (skb->len < 1) goto drop; switch (skb->data[0]) { case X25_IFACE_DATA: break; case X25_IFACE_CONNECT: err = lapb_connect_request(dev); if (err == LAPB_CONNECTED) lapbeth_connected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_connect_request error: %d\n", err); goto drop; case X25_IFACE_DISCONNECT: err = lapb_disconnect_request(dev); if (err == LAPB_NOTCONNECTED) lapbeth_disconnected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_disconnect_request err: %d\n", err); fallthrough; default: goto drop; } skb_pull(skb, 1); err = lapb_data_request(dev, skb); if (err != LAPB_OK) { pr_err("lapb_data_request error - %d\n", err); goto drop; } out: spin_unlock_bh(&lapbeth->up_lock); return NETDEV_TX_OK; drop: kfree_skb(skb); goto out; } static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(ndev); unsigned char *ptr; struct net_device *dev; int size = skb->len; ptr = skb_push(skb, 2); *ptr++ = size % 256; *ptr++ = size / 256; ndev->stats.tx_packets++; ndev->stats.tx_bytes += size; skb->dev = dev = lapbeth->ethdev; skb->protocol = htons(ETH_P_DEC); skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); } static void lapbeth_connected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_CONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } static void lapbeth_disconnected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_DISCONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } /* Set AX.25 callsign */ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; dev_addr_set(dev, sa->sa_data); return 0; } static const struct lapb_register_struct lapbeth_callbacks = { .connect_confirmation = lapbeth_connected, .connect_indication = lapbeth_connected, .disconnect_confirmation = lapbeth_disconnected, .disconnect_indication = lapbeth_disconnected, .data_indication = lapbeth_data_indication, .data_transmit = lapbeth_data_transmit, }; /* open/close a device */ static int lapbeth_open(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; napi_enable(&lapbeth->napi); err = lapb_register(dev, &lapbeth_callbacks); if (err != LAPB_OK) { napi_disable(&lapbeth->napi); pr_err("lapb_register error: %d\n", err); return -ENODEV; } spin_lock_bh(&lapbeth->up_lock); lapbeth->up = true; spin_unlock_bh(&lapbeth->up_lock); return 0; } static int lapbeth_close(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); lapbeth->up = false; spin_unlock_bh(&lapbeth->up_lock); err = lapb_unregister(dev); if (err != LAPB_OK) pr_err("lapb_unregister error: %d\n", err); napi_disable(&lapbeth->napi); return 0; } /* ------------------------------------------------------------------------ */ static const struct net_device_ops lapbeth_netdev_ops = { .ndo_open = lapbeth_open, .ndo_stop = lapbeth_close, .ndo_start_xmit = lapbeth_xmit, .ndo_set_mac_address = lapbeth_set_mac_address, }; static void lapbeth_setup(struct net_device *dev) { dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; dev->hard_header_len = 0; dev->mtu = 1000; dev->addr_len = 0; } /* Setup a new device. */ static int lapbeth_new_device(struct net_device *dev) { struct net_device *ndev; struct lapbethdev *lapbeth; int rc = -ENOMEM; ASSERT_RTNL(); if (dev->type != ARPHRD_ETHER) return -EINVAL; ndev = alloc_netdev(sizeof(*lapbeth), "lapb%d", NET_NAME_UNKNOWN, lapbeth_setup); if (!ndev) goto out; /* When transmitting data: * first this driver removes a pseudo header of 1 byte, * then the lapb module prepends an LAPB header of at most 3 bytes, * then this driver prepends a length field of 2 bytes, * then the underlying Ethernet device prepends its own header. */ ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + dev->needed_headroom; ndev->needed_tailroom = dev->needed_tailroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; dev_hold(dev); lapbeth->ethdev = dev; lapbeth->up = false; spin_lock_init(&lapbeth->up_lock); skb_queue_head_init(&lapbeth->rx_queue); netif_napi_add_weight(ndev, &lapbeth->napi, lapbeth_napi_poll, 16); rc = -EIO; if (register_netdevice(ndev)) goto fail; list_add_rcu(&lapbeth->node, &lapbeth_devices); rc = 0; out: return rc; fail: dev_put(dev); free_netdev(ndev); goto out; } /* Free a lapb network device. */ static void lapbeth_free_device(struct lapbethdev *lapbeth) { dev_put(lapbeth->ethdev); list_del_rcu(&lapbeth->node); unregister_netdevice(lapbeth->axdev); } /* Handle device status changes. * * Called from notifier with RTNL held. */ static int lapbeth_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct lapbethdev *lapbeth; struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (!dev_is_ethdev(dev) && !lapbeth_get_x25_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: /* New ethernet device -> new LAPB interface */ if (!lapbeth_get_x25_dev(dev)) lapbeth_new_device(dev); break; case NETDEV_GOING_DOWN: /* ethernet device closes -> close LAPB interface */ lapbeth = lapbeth_get_x25_dev(dev); if (lapbeth) dev_close(lapbeth->axdev); break; case NETDEV_UNREGISTER: /* ethernet device disappears -> remove LAPB interface */ lapbeth = lapbeth_get_x25_dev(dev); if (lapbeth) lapbeth_free_device(lapbeth); break; } return NOTIFY_DONE; } /* ------------------------------------------------------------------------ */ static struct packet_type lapbeth_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DEC), .func = lapbeth_rcv, }; static struct notifier_block lapbeth_dev_notifier = { .notifier_call = lapbeth_device_event, }; static const char banner[] __initconst = KERN_INFO "LAPB Ethernet driver version 0.02\n"; static int __init lapbeth_init_driver(void) { dev_add_pack(&lapbeth_packet_type); register_netdevice_notifier(&lapbeth_dev_notifier); printk(banner); return 0; } module_init(lapbeth_init_driver); static void __exit lapbeth_cleanup_driver(void) { struct lapbethdev *lapbeth; struct list_head *entry, *tmp; dev_remove_pack(&lapbeth_packet_type); unregister_netdevice_notifier(&lapbeth_dev_notifier); rtnl_lock(); list_for_each_safe(entry, tmp, &lapbeth_devices) { lapbeth = list_entry(entry, struct lapbethdev, node); dev_put(lapbeth->ethdev); unregister_netdevice(lapbeth->axdev); } rtnl_unlock(); } module_exit(lapbeth_cleanup_driver); MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The unofficial LAPB over Ethernet driver"); MODULE_LICENSE("GPL"); |
| 545 840 840 545 1380 5955 5190 1379 838 545 1380 1381 1381 1381 11 1383 1321 1323 5957 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_r_func_t)0 #define SWAP_WORDS_32 (swap_r_func_t)1 #define SWAP_BYTES (swap_r_func_t)2 #define SWAP_WRAPPER (swap_r_func_t)3 struct wrapper { cmp_func_t cmp; swap_func_t swap; }; /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { ((const struct wrapper *)priv)->swap(a, b, (int)size); return; } if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size, priv); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((const struct wrapper *)priv)->cmp(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ if (!a) /* num < 2 || size == 0 */ return; /* called from 'sort' without swap function, let's pick the default */ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) swap_func = NULL; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ a -= size; else if (n -= size) /* Sorting: Extract root to --n */ do_swap(base, base + n, size, swap_func, priv); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func, priv); } } } EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); } EXPORT_SYMBOL(sort); |
| 13 365 21 19 329 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 | /* 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 _INET_HASHTABLES_H #define _INET_HASHTABLES_H #include <linux/interrupt.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/wait.h> #include <net/inet_connection_sock.h> #include <net/inet_sock.h> #include <net/ip.h> #include <net/sock.h> #include <net/route.h> #include <net/tcp_states.h> #include <net/netns/hash.h> #include <linux/refcount.h> #include <asm/byteorder.h> /* This is for all connections with a full identity, no wildcards. * The 'e' prefix stands for Establish, but we really put all sockets * but LISTEN ones. */ struct inet_ehash_bucket { struct hlist_nulls_head chain; }; /* There are a few simple rules, which allow for local port reuse by * an application. In essence: * * 1) Sockets bound to different interfaces may share a local port. * Failing that, goto test 2. * 2) If all sockets have sk->sk_reuse set, and none of them are in * TCP_LISTEN state, the port may be shared. * Failing that, goto test 3. * 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local * address, and none of them are the same, the port may be * shared. * Failing this, the port cannot be shared. * * The interesting point, is test #2. This is what an FTP server does * all day. To optimize this case we use a specific flag bit defined * below. As we add sockets to a bind bucket list, we perform a * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN)) * As long as all sockets added to a bind bucket pass this test, * the flag bit will be set. * The resulting situation is that tcp_v[46]_verify_bind() can just check * for this flag bit, if it is set and the socket trying to bind has * sk->sk_reuse set, we don't even have to walk the owners list at all, * we return that it is ok to bind this socket to the requested local port. * * Sounds like a lot of work, but it is worth it. In a more naive * implementation (ie. current FreeBSD etc.) the entire list of ports * must be walked for each data port opened by an ftp server. Needless * to say, this does not scale at all. With a couple thousand FTP * users logged onto your box, isn't it nice to know that new data * ports are created in O(1) time? I thought so. ;-) -DaveM */ #define FASTREUSEPORT_ANY 1 #define FASTREUSEPORT_STRICT 2 struct inet_bind_bucket { possible_net_t ib_net; int l3mdev; unsigned short port; signed char fastreuse; signed char fastreuseport; kuid_t fastuid; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr fast_v6_rcv_saddr; #endif __be32 fast_rcv_saddr; unsigned short fast_sk_family; bool fast_ipv6_only; struct hlist_node node; struct hlist_head bhash2; }; struct inet_bind2_bucket { possible_net_t ib_net; int l3mdev; unsigned short port; #if IS_ENABLED(CONFIG_IPV6) unsigned short addr_type; struct in6_addr v6_rcv_saddr; #define rcv_saddr v6_rcv_saddr.s6_addr32[3] #else __be32 rcv_saddr; #endif /* Node in the bhash2 inet_bind_hashbucket chain */ struct hlist_node node; struct hlist_node bhash_node; /* List of sockets hashed to this bucket */ struct hlist_head owners; }; static inline struct net *ib_net(const struct inet_bind_bucket *ib) { return read_pnet(&ib->ib_net); } static inline struct net *ib2_net(const struct inet_bind2_bucket *ib) { return read_pnet(&ib->ib_net); } #define inet_bind_bucket_for_each(tb, head) \ hlist_for_each_entry(tb, head, node) struct inet_bind_hashbucket { spinlock_t lock; struct hlist_head chain; }; /* Sockets can be hashed in established or listening table. * We must use different 'nulls' end-of-chain value for all hash buckets : * A socket might transition from ESTABLISH to LISTEN state without * RCU grace period. A lookup in ehash table needs to handle this case. */ #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; struct hlist_nulls_head nulls_head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ #define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */ struct inet_hashinfo { /* This is for sockets with full identity only. Sockets here will * always be without wildcards and will have the following invariant: * * TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE * */ struct inet_ehash_bucket *ehash; spinlock_t *ehash_locks; unsigned int ehash_mask; unsigned int ehash_locks_mask; /* Ok, let's try this, I give up, we do need a local binding * TCP hash as well as the others for fast bind/connect. */ struct kmem_cache *bind_bucket_cachep; /* This bind table is hashed by local port */ struct inet_bind_hashbucket *bhash; struct kmem_cache *bind2_bucket_cachep; /* This bind table is hashed by local port and sk->sk_rcv_saddr (ipv4) * or sk->sk_v6_rcv_saddr (ipv6). This 2nd bind table is used * primarily for expediting bind conflict resolution. */ struct inet_bind_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; bool pernet; } ____cacheline_aligned_in_smp; static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk) { #if IS_ENABLED(CONFIG_IP_DCCP) return sk->sk_prot->h.hashinfo ? : sock_net(sk)->ipv4.tcp_death_row.hashinfo; #else return sock_net(sk)->ipv4.tcp_death_row.hashinfo; #endif } static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { return &h->lhash2[hash & h->lhash2_mask]; } static inline struct inet_ehash_bucket *inet_ehash_bucket( struct inet_hashinfo *hashinfo, unsigned int hash) { return &hashinfo->ehash[hash & hashinfo->ehash_mask]; } static inline spinlock_t *inet_ehash_lockp( struct inet_hashinfo *hashinfo, unsigned int hash) { return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask]; } int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo); static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h) { kfree(h->lhash2); h->lhash2 = NULL; } static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) { kvfree(hashinfo->ehash_locks); hashinfo->ehash_locks = NULL; } struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo, unsigned int ehash_entries); void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo); struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, const unsigned short snum, int l3mdev); void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net, unsigned short port, int l3mdev); struct inet_bind2_bucket * inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, struct inet_bind_bucket *tb, const struct sock *sk); void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb); struct inet_bind2_bucket * inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk); bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk); static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, const u32 bhash_size) { return (lport + net_hash_mix(net)) & (bhash_size - 1); } static inline struct inet_bind_hashbucket * inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk, const struct net *net, unsigned short port) { u32 hash; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port); else #endif hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port); return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port); /* This should be called whenever a socket's sk_rcv_saddr (ipv4) or * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's * rcv_saddr field should already have been updated when this is called. */ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); void inet_bhash2_reset_saddr(struct sock *sk); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, unsigned long high_limit); int inet_hashinfo2_init_mod(struct inet_hashinfo *h); bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk); int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif); static inline struct sock *inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif) { return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, sdif); } /* Socket demux engine toys. */ /* What happens here is ugly; there's a pair of adjacent fields in struct inet_sock; __be16 dport followed by __u16 num. We want to search by pair, so we combine the keys into a single 32bit value and compare with 32bit value read from &...->dport. Let's at least make sure that it's not mixed with anything else... On 64bit targets we combine comparisons with pair of adjacent __be32 fields in the same way. */ #ifdef __BIG_ENDIAN #define INET_COMBINED_PORTS(__sport, __dport) \ ((__force __portpair)(((__force __u32)(__be16)(__sport) << 16) | (__u32)(__dport))) #else /* __LITTLE_ENDIAN */ #define INET_COMBINED_PORTS(__sport, __dport) \ ((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport))) #endif #ifdef __BIG_ENDIAN #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const __addrpair __name = (__force __addrpair) ( \ (((__force __u64)(__be32)(__saddr)) << 32) | \ ((__force __u64)(__be32)(__daddr))) #else /* __LITTLE_ENDIAN */ #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const __addrpair __name = (__force __addrpair) ( \ (((__force __u64)(__be32)(__daddr)) << 32) | \ ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ static inline bool inet_match(struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { if (!net_eq(sock_net(sk), net) || sk->sk_portpair != ports || sk->sk_addrpair != cookie) 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); } /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, const int dif, const int sdif); typedef u32 (inet_ehashfn_t)(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport); inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); struct sock *inet_lookup_run_sk_lookup(struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, u16 hnum, const int dif, inet_ehashfn_t *ehashfn); static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) { return __inet_lookup_established(net, hashinfo, saddr, sport, daddr, ntohs(dport), dif, 0); } static inline struct sock *__inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif, const int sdif, bool *refcounted) { u16 hnum = ntohs(dport); struct sock *sk; sk = __inet_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif, sdif); } static inline struct sock *inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) { struct sock *sk; bool refcounted; sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, dport, dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } static inline struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, bool *refcounted, inet_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool prefetched; sk = skb_steal_sock(skb, refcounted, &prefetched); if (!sk) return NULL; if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { if (sk->sk_state != TCP_LISTEN) return sk; } else if (sk->sk_protocol == IPPROTO_UDP) { if (sk->sk_state != TCP_CLOSE) return sk; } else { return sk; } reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, ntohs(dport), ehashfn); if (!reuse_sk) return sk; /* We've chosen a new reuseport sock which is never refcounted. This * implies that sk also isn't refcounted. */ WARN_ON_ONCE(*refcounted); return reuse_sk; } static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, const int sdif, bool *refcounted) { struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct sock *sk; sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport, refcounted, inet_ehashfn); if (IS_ERR(sk)) return NULL; if (sk) return sk; return __inet_lookup(net, hashinfo, skb, doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), sdif, refcounted); } static inline void sk_daddr_set(struct sock *sk, __be32 addr) { sk->sk_daddr = addr; /* alias of inet_daddr */ #if IS_ENABLED(CONFIG_IPV6) ipv6_addr_set_v4mapped(addr, &sk->sk_v6_daddr); #endif } static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) { sk->sk_rcv_saddr = addr; /* alias of inet_rcv_saddr */ #if IS_ENABLED(CONFIG_IPV6) ipv6_addr_set_v4mapped(addr, &sk->sk_v6_rcv_saddr); #endif } int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); #endif /* _INET_HASHTABLES_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_VXLAN_H #define __NET_VXLAN_H 1 #include <linux/if_vlan.h> #include <linux/rhashtable-types.h> #include <net/udp_tunnel.h> #include <net/dst_metadata.h> #include <net/rtnetlink.h> #include <net/switchdev.h> #include <net/nexthop.h> #define IANA_VXLAN_UDP_PORT 4789 #define IANA_VXLAN_GPE_UDP_PORT 4790 /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |R|R|R|R|I|R|R|R| Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | VXLAN Network Identifier (VNI) | Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * I = VXLAN Network Identifier (VNI) present. */ struct vxlanhdr { __be32 vx_flags; __be32 vx_vni; }; /* VXLAN header flags. */ #define VXLAN_HF_VNI cpu_to_be32(BIT(27)) #define VXLAN_N_VID (1u << 24) #define VXLAN_VID_MASK (VXLAN_N_VID - 1) #define VXLAN_VNI_MASK cpu_to_be32(VXLAN_VID_MASK << 8) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) #define FDB_HASH_BITS 8 #define FDB_HASH_SIZE (1<<FDB_HASH_BITS) /* Remote checksum offload for VXLAN (VXLAN_F_REMCSUM_[RT]X): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |R|R|R|R|I|R|R|R|R|R|C| Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | VXLAN Network Identifier (VNI) |O| Csum start | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * C = Remote checksum offload bit. When set indicates that the * remote checksum offload data is present. * * O = Offset bit. Indicates the checksum offset relative to * checksum start. * * Csum start = Checksum start divided by two. * * http://tools.ietf.org/html/draft-herbert-vxlan-rco */ /* VXLAN-RCO header flags. */ #define VXLAN_HF_RCO cpu_to_be32(BIT(21)) /* Remote checksum offload header option */ #define VXLAN_RCO_MASK cpu_to_be32(0x7f) /* Last byte of vni field */ #define VXLAN_RCO_UDP cpu_to_be32(0x80) /* Indicate UDP RCO (TCP when not set *) */ #define VXLAN_RCO_SHIFT 1 /* Left shift of start */ #define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1) #define VXLAN_MAX_REMCSUM_START (0x7f << VXLAN_RCO_SHIFT) /* * VXLAN Group Based Policy Extension (VXLAN_F_GBP): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |G|R|R|R|I|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | VXLAN Network Identifier (VNI) | Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * G = Group Policy ID present. * * D = Don't Learn bit. When set, this bit indicates that the egress * VTEP MUST NOT learn the source address of the encapsulated frame. * * A = Indicates that the group policy has already been applied to * this packet. Policies MUST NOT be applied by devices when the * A bit is set. * * https://tools.ietf.org/html/draft-smith-vxlan-group-policy */ struct vxlanhdr_gbp { u8 vx_flags; #ifdef __LITTLE_ENDIAN_BITFIELD u8 reserved_flags1:3, policy_applied:1, reserved_flags2:2, dont_learn:1, reserved_flags3:1; #elif defined(__BIG_ENDIAN_BITFIELD) u8 reserved_flags1:1, dont_learn:1, reserved_flags2:2, policy_applied:1, reserved_flags3:3; #else #error "Please fix <asm/byteorder.h>" #endif __be16 policy_id; __be32 vx_vni; }; /* VXLAN-GBP header flags. */ #define VXLAN_HF_GBP cpu_to_be32(BIT(31)) #define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | cpu_to_be32(0xFFFFFF)) /* skb->mark mapping * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |R|R|R|R|R|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define VXLAN_GBP_DONT_LEARN (BIT(6) << 16) #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) #define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ VXLAN_GBP_ID_MASK) /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |R|R|Ver|I|P|R|O| Reserved |Next Protocol | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | VXLAN Network Identifier (VNI) | Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Ver = Version. Indicates VXLAN GPE protocol version. * * P = Next Protocol Bit. The P bit is set to indicate that the * Next Protocol field is present. * * O = OAM Flag Bit. The O bit is set to indicate that the packet * is an OAM packet. * * Next Protocol = This 8 bit field indicates the protocol header * immediately following the VXLAN GPE header. * * https://tools.ietf.org/html/draft-ietf-nvo3-vxlan-gpe-01 */ struct vxlanhdr_gpe { #if defined(__LITTLE_ENDIAN_BITFIELD) u8 oam_flag:1, reserved_flags1:1, np_applied:1, instance_applied:1, version:2, reserved_flags2:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 reserved_flags2:2, version:2, instance_applied:1, np_applied:1, reserved_flags1:1, oam_flag:1; #endif u8 reserved_flags3; u8 reserved_flags4; u8 next_protocol; __be32 vx_vni; }; /* VXLAN-GPE header flags. */ #define VXLAN_HF_VER cpu_to_be32(BIT(29) | BIT(28)) #define VXLAN_HF_NP cpu_to_be32(BIT(26)) #define VXLAN_HF_OAM cpu_to_be32(BIT(24)) #define VXLAN_GPE_USED_BITS (VXLAN_HF_VER | VXLAN_HF_NP | VXLAN_HF_OAM | \ cpu_to_be32(0xff)) struct vxlan_metadata { u32 gbp; }; /* per UDP socket information */ struct vxlan_sock { struct hlist_node hlist; struct socket *sock; struct hlist_head vni_list[VNI_HASH_SIZE]; refcount_t refcnt; u32 flags; }; union vxlan_addr { struct sockaddr_in sin; struct sockaddr_in6 sin6; struct sockaddr sa; }; struct vxlan_rdst { union vxlan_addr remote_ip; __be16 remote_port; u8 offloaded:1; __be32 remote_vni; u32 remote_ifindex; struct net_device *remote_dev; struct list_head list; struct rcu_head rcu; struct dst_cache dst_cache; }; struct vxlan_config { union vxlan_addr remote_ip; union vxlan_addr saddr; __be32 vni; int remote_ifindex; int mtu; __be16 dst_port; u16 port_min; u16 port_max; u8 tos; u8 ttl; __be32 label; enum ifla_vxlan_label_policy label_policy; u32 flags; unsigned long age_interval; unsigned int addrmax; bool no_share; enum ifla_vxlan_df df; }; enum { VXLAN_VNI_STATS_RX, VXLAN_VNI_STATS_RX_DROPS, VXLAN_VNI_STATS_RX_ERRORS, VXLAN_VNI_STATS_TX, VXLAN_VNI_STATS_TX_DROPS, VXLAN_VNI_STATS_TX_ERRORS, }; struct vxlan_vni_stats { u64 rx_packets; u64 rx_bytes; u64 rx_drops; u64 rx_errors; u64 tx_packets; u64 tx_bytes; u64 tx_drops; u64 tx_errors; }; struct vxlan_vni_stats_pcpu { struct vxlan_vni_stats stats; struct u64_stats_sync syncp; }; struct vxlan_dev_node { struct hlist_node hlist; struct vxlan_dev *vxlan; }; struct vxlan_vni_node { struct rhash_head vnode; struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct vxlan_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct list_head vlist; __be32 vni; union vxlan_addr remote_ip; /* default remote ip for this vni */ struct vxlan_vni_stats_pcpu __percpu *stats; struct rcu_head rcu; }; struct vxlan_vni_group { struct rhashtable vni_hash; struct list_head vni_list; u32 num_vnis; }; /* Pseudo network device */ struct vxlan_dev { struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct vxlan_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct list_head next; /* vxlan's per namespace list */ struct vxlan_sock __rcu *vn4_sock; /* listening socket for IPv4 */ #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock __rcu *vn6_sock; /* listening socket for IPv6 */ #endif struct net_device *dev; struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ struct timer_list age_timer; spinlock_t hash_lock[FDB_HASH_SIZE]; unsigned int addrcnt; struct gro_cells gro_cells; struct vxlan_config cfg; struct vxlan_vni_group __rcu *vnigrp; struct hlist_head fdb_head[FDB_HASH_SIZE]; struct rhashtable mdb_tbl; struct hlist_head mdb_list; unsigned int mdb_seq; }; #define VXLAN_F_LEARN 0x01 #define VXLAN_F_PROXY 0x02 #define VXLAN_F_RSC 0x04 #define VXLAN_F_L2MISS 0x08 #define VXLAN_F_L3MISS 0x10 #define VXLAN_F_IPV6 0x20 #define VXLAN_F_UDP_ZERO_CSUM_TX 0x40 #define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80 #define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100 #define VXLAN_F_REMCSUM_TX 0x200 #define VXLAN_F_REMCSUM_RX 0x400 #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 #define VXLAN_F_COLLECT_METADATA 0x2000 #define VXLAN_F_GPE 0x4000 #define VXLAN_F_IPV6_LINKLOCAL 0x8000 #define VXLAN_F_TTL_INHERIT 0x10000 #define VXLAN_F_VNIFILTER 0x20000 #define VXLAN_F_MDB 0x40000 #define VXLAN_F_LOCALBYPASS 0x80000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ VXLAN_F_GPE | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_REMCSUM_RX | \ VXLAN_F_REMCSUM_NOPARTIAL | \ VXLAN_F_COLLECT_METADATA | \ VXLAN_F_VNIFILTER) /* Flags that can be set together with VXLAN_F_GPE. */ #define VXLAN_F_ALLOWED_GPE (VXLAN_F_GPE | \ VXLAN_F_IPV6 | \ VXLAN_F_IPV6_LINKLOCAL | \ VXLAN_F_UDP_ZERO_CSUM_TX | \ VXLAN_F_UDP_ZERO_CSUM6_TX | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_COLLECT_METADATA | \ VXLAN_F_VNIFILTER | \ VXLAN_F_LOCALBYPASS) struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, netdev_features_t features) { u8 l4_hdr = 0; if (!skb->encapsulation) return features; switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): l4_hdr = ip_hdr(skb)->protocol; break; case htons(ETH_P_IPV6): l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: return features; } if ((l4_hdr == IPPROTO_UDP) && (skb->inner_protocol_type != ENCAP_TYPE_ETHER || skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)) || (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, inner_eth_hdr(skb)->h_proto)))) return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } static inline int vxlan_headroom(u32 flags) { /* VXLAN: IP4/6 header + UDP + VXLAN + Ethernet header */ /* VXLAN-GPE: IP4/6 header + UDP + VXLAN */ return (flags & VXLAN_F_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr)) + sizeof(struct udphdr) + sizeof(struct vxlanhdr) + (flags & VXLAN_F_GPE ? 0 : ETH_HLEN); } static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb) { return (struct vxlanhdr *)(udp_hdr(skb) + 1); } static inline __be32 vxlan_vni(__be32 vni_field) { #if defined(__BIG_ENDIAN) return (__force __be32)((__force u32)vni_field >> 8); #else return (__force __be32)((__force u32)(vni_field & VXLAN_VNI_MASK) << 8); #endif } static inline __be32 vxlan_vni_field(__be32 vni) { #if defined(__BIG_ENDIAN) return (__force __be32)((__force u32)vni << 8); #else return (__force __be32)((__force u32)vni >> 8); #endif } static inline size_t vxlan_rco_start(__be32 vni_field) { return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; } static inline size_t vxlan_rco_offset(__be32 vni_field) { return (vni_field & VXLAN_RCO_UDP) ? offsetof(struct udphdr, check) : offsetof(struct tcphdr, check); } static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) { __be32 vni_field = cpu_to_be32(start >> VXLAN_RCO_SHIFT); if (offset == offsetof(struct udphdr, check)) vni_field |= VXLAN_RCO_UDP; return vni_field; } static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) { return vs->sock->sk->sk_family; } #if IS_ENABLED(CONFIG_IPV6) static inline bool vxlan_addr_any(const union vxlan_addr *ipa) { if (ipa->sa.sa_family == AF_INET6) return ipv6_addr_any(&ipa->sin6.sin6_addr); else return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); } static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) { if (ipa->sa.sa_family == AF_INET6) return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr); else return ipv4_is_multicast(ipa->sin.sin_addr.s_addr); } #else /* !IS_ENABLED(CONFIG_IPV6) */ static inline bool vxlan_addr_any(const union vxlan_addr *ipa) { return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); } static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) { return ipv4_is_multicast(ipa->sin.sin_addr.s_addr); } #endif /* IS_ENABLED(CONFIG_IPV6) */ static inline bool netif_is_vxlan(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "vxlan"); } struct switchdev_notifier_vxlan_fdb_info { struct switchdev_notifier_info info; /* must be first */ union vxlan_addr remote_ip; __be16 remote_port; __be32 remote_vni; u32 remote_ifindex; u8 eth_addr[ETH_ALEN]; __be32 vni; bool offloaded; bool added_by_user; }; #if IS_ENABLED(CONFIG_VXLAN) int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info); int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni); #else static inline int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { return -ENOENT; } static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { } #endif static inline void vxlan_flag_attr_error(int attrtype, struct netlink_ext_ack *extack) { #define VXLAN_FLAG(flg) \ case IFLA_VXLAN_##flg: \ NL_SET_ERR_MSG_MOD(extack, \ "cannot change " #flg " flag"); \ break switch (attrtype) { VXLAN_FLAG(TTL_INHERIT); VXLAN_FLAG(LEARNING); VXLAN_FLAG(PROXY); VXLAN_FLAG(RSC); VXLAN_FLAG(L2MISS); VXLAN_FLAG(L3MISS); VXLAN_FLAG(COLLECT_METADATA); VXLAN_FLAG(UDP_ZERO_CSUM6_TX); VXLAN_FLAG(UDP_ZERO_CSUM6_RX); VXLAN_FLAG(REMCSUM_TX); VXLAN_FLAG(REMCSUM_RX); VXLAN_FLAG(GBP); VXLAN_FLAG(GPE); VXLAN_FLAG(REMCSUM_NOPARTIAL); default: NL_SET_ERR_MSG_MOD(extack, \ "cannot change flag"); break; } #undef VXLAN_FLAG } static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, u32 hash, struct vxlan_rdst *rdst) { struct fib_nh_common *nhc; nhc = nexthop_path_fdb_result(nh, hash >> 1); if (unlikely(!nhc)) return false; switch (nhc->nhc_gw_family) { case AF_INET: rdst->remote_ip.sin.sin_addr.s_addr = nhc->nhc_gw.ipv4; rdst->remote_ip.sa.sa_family = AF_INET; break; case AF_INET6: rdst->remote_ip.sin6.sin6_addr = nhc->nhc_gw.ipv6; rdst->remote_ip.sa.sa_family = AF_INET6; break; } return true; } static inline void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, const struct vxlan_metadata *md) { struct vxlanhdr_gbp *gbp; if (!md->gbp) return; gbp = (struct vxlanhdr_gbp *)vxh; vxh->vx_flags |= VXLAN_HF_GBP; if (md->gbp & VXLAN_GBP_DONT_LEARN) gbp->dont_learn = 1; if (md->gbp & VXLAN_GBP_POLICY_APPLIED) gbp->policy_applied = 1; gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK); } #endif |
| 23 21 13 47 118 118 118 1 1 1 117 118 7 118 119 119 119 119 119 119 119 119 1 1 119 119 110 9 8 117 3 110 8 118 118 114 25 3 4 3 1 1 2 19 3 19 3 2 121 2 3 2 2 5 1 3 1 1 6 5 11 3 156 156 121 3 119 3 3 119 2 1 119 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* AF_RXRPC sendmsg() implementation. * * 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/net.h> #include <linux/gfp.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" /* * Propose an abort to be made in the I/O thread. */ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, enum rxrpc_abort_reason why) { _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); if (!call->send_abort && !rxrpc_call_is_complete(call)) { call->send_abort_why = why; call->send_abort_err = error; call->send_abort_seq = 0; /* Request abort locklessly vs rxrpc_input_call_event(). */ smp_store_release(&call->send_abort, abort_code); rxrpc_poke_call(call, rxrpc_call_poke_abort); return true; } return false; } /* * Wait for a call to become connected. Interruption here doesn't cause the * call to be aborted. */ static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) { DECLARE_WAITQUEUE(myself, current); int ret = 0; _enter("%d", call->debug_id); if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) goto no_wait; add_wait_queue_exclusive(&call->waitq, &myself); for (;;) { switch (call->interruptibility) { case RXRPC_INTERRUPTIBLE: case RXRPC_PREINTERRUPTIBLE: set_current_state(TASK_INTERRUPTIBLE); break; case RXRPC_UNINTERRUPTIBLE: default: set_current_state(TASK_UNINTERRUPTIBLE); break; } if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) break; if ((call->interruptibility == RXRPC_INTERRUPTIBLE || call->interruptibility == RXRPC_PREINTERRUPTIBLE) && signal_pending(current)) { ret = sock_intr_errno(*timeo); break; } *timeo = schedule_timeout(*timeo); } remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); no_wait: if (ret == 0 && rxrpc_call_is_complete(call)) ret = call->error; _leave(" = %d", ret); return ret; } /* * Return true if there's sufficient Tx queue space. */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { if (_tx_win) *_tx_win = call->tx_bottom; return call->tx_prepared - call->tx_bottom < 256; } /* * Wait for space to appear in the Tx queue or a signal to occur. */ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, struct rxrpc_call *call, long *timeo) { for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (rxrpc_check_tx_space(call, NULL)) return 0; if (rxrpc_call_is_complete(call)) return call->error; if (signal_pending(current)) return sock_intr_errno(*timeo); trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } /* * Wait for space to appear in the Tx queue uninterruptibly, but with * a timeout of 2*RTT if no progress was made and a signal occurred. */ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, struct rxrpc_call *call) { rxrpc_seq_t tx_start, tx_win; signed long rtt, timeout; rtt = READ_ONCE(call->peer->srtt_us) >> 3; rtt = usecs_to_jiffies(rtt) * 2; if (rtt < 2) rtt = 2; timeout = rtt; tx_start = smp_load_acquire(&call->acks_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (rxrpc_check_tx_space(call, &tx_win)) return 0; if (rxrpc_call_is_complete(call)) return call->error; if (timeout == 0 && tx_win == tx_start && signal_pending(current)) return -EINTR; if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; } trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); timeout = schedule_timeout(timeout); } } /* * Wait for space to appear in the Tx queue uninterruptibly. */ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, struct rxrpc_call *call, long *timeo) { for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (rxrpc_check_tx_space(call, NULL)) return 0; if (rxrpc_call_is_complete(call)) return call->error; trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } /* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, struct rxrpc_call *call, long *timeo, bool waitall) { DECLARE_WAITQUEUE(myself, current); int ret; _enter(",{%u,%u,%u,%u}", call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); switch (call->interruptibility) { case RXRPC_INTERRUPTIBLE: if (waitall) ret = rxrpc_wait_for_tx_window_waitall(rx, call); else ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); break; case RXRPC_PREINTERRUPTIBLE: case RXRPC_UNINTERRUPTIBLE: default: ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo); break; } remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); _leave(" = %d", ret); return ret; } /* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. */ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_notify_end_tx_t notify_end_tx) { if (notify_end_tx) notify_end_tx(&rx->sk, call, call->user_call_ID); } /* * Queue a DATA packet for transmission, set the resend timeout and send * the packet immediately. Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, struct rxrpc_txbuf *txb, rxrpc_notify_end_tx_t notify_end_tx) { rxrpc_seq_t seq = txb->seq; bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; rxrpc_inc_stat(call->rxnet, stat_tx_data); ASSERTCMP(txb->seq, ==, call->tx_prepared + 1); /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ txb->last_sent = ktime_get_real(); if (last) trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); /* Add the packet to the call's output buffer */ spin_lock(&call->tx_lock); poke = list_empty(&call->tx_sendmsg); list_add_tail(&txb->call_link, &call->tx_sendmsg); call->tx_prepared = seq; if (last) rxrpc_notify_end_tx(rx, call, notify_end_tx); spin_unlock(&call->tx_lock); if (poke) rxrpc_poke_call(call, rxrpc_call_poke_start); } /* * send data through a socket * - must be called in process context * - The caller holds the call user access mutex, but not the socket lock. */ static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, struct msghdr *msg, size_t len, rxrpc_notify_end_tx_t notify_end_tx, bool *_dropped_lock) { struct rxrpc_txbuf *txb; struct sock *sk = &rx->sk; enum rxrpc_call_state state; long timeo; bool more = msg->msg_flags & MSG_MORE; int ret, copied = 0; timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); ret = rxrpc_wait_to_be_connected(call, &timeo); if (ret < 0) return ret; if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) { ret = rxrpc_init_client_conn_security(call->conn); if (ret < 0) return ret; } /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); reload: ret = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) goto maybe_error; state = rxrpc_call_state(call); ret = -ESHUTDOWN; if (state >= RXRPC_CALL_COMPLETE) goto maybe_error; ret = -EPROTO; if (state != RXRPC_CALL_CLIENT_SEND_REQUEST && state != RXRPC_CALL_SERVER_ACK_REQUEST && state != RXRPC_CALL_SERVER_SEND_REPLY) { /* Request phase complete for this client call */ trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, call->cid, call->call_id, call->rx_consumed, 0, -EPROTO); goto maybe_error; } ret = -EMSGSIZE; if (call->tx_total_len != -1) { if (len - copied > call->tx_total_len) goto maybe_error; if (!more && len - copied != call->tx_total_len) goto maybe_error; } txb = call->tx_pending; call->tx_pending = NULL; if (txb) rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { if (!txb) { size_t remain, bufsize, chunk, offset; _debug("alloc"); if (!rxrpc_check_tx_space(call, NULL)) goto wait_for_space; /* Work out the maximum size of a packet. Assume that * the security header is going to be in the padded * region (enc blocksize), but the trailer is not. */ remain = more ? INT_MAX : msg_data_left(msg); ret = call->conn->security->how_much_data(call, remain, &bufsize, &chunk, &offset); if (ret < 0) goto maybe_error; _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); /* create a buffer that we can retain until it's ACK'd */ ret = -ENOMEM; txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, GFP_KERNEL); if (!txb) goto maybe_error; txb->offset = offset; txb->space -= offset; txb->space = min_t(size_t, chunk, txb->space); } _debug("append"); /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); _debug("add %zu", copy); if (!copy_from_iter_full(txb->data + txb->offset, copy, &msg->msg_iter)) goto efault; _debug("added"); txb->space -= copy; txb->len += copy; txb->offset += copy; copied += copy; if (call->tx_total_len != -1) call->tx_total_len -= copy; } /* check for the far side aborting the call or a network error * occurring */ if (rxrpc_call_is_complete(call)) goto call_terminated; /* add the packet to the send queue if it's now full */ if (!txb->space || (msg_data_left(msg) == 0 && !more)) { if (msg_data_left(msg) == 0 && !more) { txb->wire.flags |= RXRPC_LAST_PACKET; __set_bit(RXRPC_TXBUF_LAST, &txb->flags); } else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) txb->wire.flags |= RXRPC_MORE_PACKETS; ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } } while (msg_data_left(msg) > 0); success: ret = copied; if (rxrpc_call_is_complete(call) && call->error < 0) ret = call->error; out: call->tx_pending = txb; _leave(" = %d", ret); return ret; call_terminated: rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted); _leave(" = %d", call->error); return call->error; maybe_error: if (copied) goto success; goto out; efault: ret = -EFAULT; goto out; wait_for_space: ret = -EAGAIN; if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; mutex_unlock(&call->user_mutex); *_dropped_lock = true; ret = rxrpc_wait_for_tx_window(rx, call, &timeo, msg->msg_flags & MSG_WAITALL); if (ret < 0) goto maybe_error; if (call->interruptibility == RXRPC_INTERRUPTIBLE) { if (mutex_lock_interruptible(&call->user_mutex) < 0) { ret = sock_intr_errno(timeo); goto maybe_error; } } else { mutex_lock(&call->user_mutex); } *_dropped_lock = false; goto reload; } /* * extract control messages from the sendmsg() control buffer */ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) { struct cmsghdr *cmsg; bool got_user_ID = false; int len; if (msg->msg_controllen == 0) return -EINVAL; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; len = cmsg->cmsg_len - sizeof(struct cmsghdr); _debug("CMSG %d, %d, %d", cmsg->cmsg_level, cmsg->cmsg_type, len); if (cmsg->cmsg_level != SOL_RXRPC) continue; switch (cmsg->cmsg_type) { case RXRPC_USER_CALL_ID: if (msg->msg_flags & MSG_CMSG_COMPAT) { if (len != sizeof(u32)) return -EINVAL; p->call.user_call_ID = *(u32 *)CMSG_DATA(cmsg); } else { if (len != sizeof(unsigned long)) return -EINVAL; p->call.user_call_ID = *(unsigned long *) CMSG_DATA(cmsg); } got_user_ID = true; break; case RXRPC_ABORT: if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; p->command = RXRPC_CMD_SEND_ABORT; if (len != sizeof(p->abort_code)) return -EINVAL; p->abort_code = *(unsigned int *)CMSG_DATA(cmsg); if (p->abort_code == 0) return -EINVAL; break; case RXRPC_CHARGE_ACCEPT: if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; p->command = RXRPC_CMD_CHARGE_ACCEPT; if (len != 0) return -EINVAL; break; case RXRPC_EXCLUSIVE_CALL: p->exclusive = true; if (len != 0) return -EINVAL; break; case RXRPC_UPGRADE_SERVICE: p->upgrade = true; if (len != 0) return -EINVAL; break; case RXRPC_TX_LENGTH: if (p->call.tx_total_len != -1 || len != sizeof(__s64)) return -EINVAL; p->call.tx_total_len = *(__s64 *)CMSG_DATA(cmsg); if (p->call.tx_total_len < 0) return -EINVAL; break; case RXRPC_SET_CALL_TIMEOUT: if (len & 3 || len < 4 || len > 12) return -EINVAL; memcpy(&p->call.timeouts, CMSG_DATA(cmsg), len); p->call.nr_timeouts = len / 4; if (p->call.timeouts.hard > INT_MAX / HZ) return -ERANGE; if (p->call.nr_timeouts >= 2 && p->call.timeouts.idle > 60 * 60 * 1000) return -ERANGE; if (p->call.nr_timeouts >= 3 && p->call.timeouts.normal > 60 * 60 * 1000) return -ERANGE; break; default: return -EINVAL; } } if (!got_user_ID) return -EINVAL; if (p->call.tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; _leave(" = 0"); return 0; } /* * Create a new client call for sendmsg(). * - Called with the socket lock held, which it must release. * - If it returns a call, the call's lock will need releasing by the caller. */ static struct rxrpc_call * rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, struct rxrpc_send_params *p) __releases(&rx->sk.sk_lock.slock) __acquires(&call->user_mutex) { struct rxrpc_conn_parameters cp; struct rxrpc_peer *peer; struct rxrpc_call *call; struct key *key; DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name); _enter(""); if (!msg->msg_name) { release_sock(&rx->sk); return ERR_PTR(-EDESTADDRREQ); } peer = rxrpc_lookup_peer(rx->local, srx, GFP_KERNEL); if (!peer) { release_sock(&rx->sk); return ERR_PTR(-ENOMEM); } key = rx->key; if (key && !rx->key->payload.data[0]) key = NULL; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; cp.peer = peer; cp.key = rx->key; cp.security_level = rx->min_sec_level; cp.exclusive = rx->exclusive | p->exclusive; cp.upgrade = p->upgrade; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, &p->call, GFP_KERNEL, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ rxrpc_put_peer(peer, rxrpc_peer_put_application); _leave(" = %p\n", call); return call; } /* * send a message forming part of a client call through an RxRPC socket * - caller holds the socket locked * - the socket may be either a client socket or a server socket */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call; unsigned long now, j; bool dropped_lock = false; int ret; struct rxrpc_send_params p = { .call.tx_total_len = -1, .call.user_call_ID = 0, .call.nr_timeouts = 0, .call.interruptibility = RXRPC_INTERRUPTIBLE, .abort_code = 0, .command = RXRPC_CMD_SEND_DATA, .exclusive = false, .upgrade = false, }; _enter(""); ret = rxrpc_sendmsg_cmsg(msg, &p); if (ret < 0) goto error_release_sock; if (p.command == RXRPC_CMD_CHARGE_ACCEPT) { ret = -EINVAL; if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) goto error_release_sock; ret = rxrpc_user_charge_accept(rx, p.call.user_call_ID); goto error_release_sock; } call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID); if (!call) { ret = -EBADSLT; if (p.command != RXRPC_CMD_SEND_DATA) goto error_release_sock; call = rxrpc_new_client_call_for_sendmsg(rx, msg, &p); /* The socket is now unlocked... */ if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ p.call.nr_timeouts = 0; ret = 0; if (rxrpc_call_is_complete(call)) goto out_put_unlock; } else { switch (rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_SECURING: if (p.command == RXRPC_CMD_SEND_ABORT) break; fallthrough; case RXRPC_CALL_UNINITIALISED: case RXRPC_CALL_SERVER_PREALLOC: rxrpc_put_call(call, rxrpc_call_put_sendmsg); ret = -EBUSY; goto error_release_sock; default: break; } ret = mutex_lock_interruptible(&call->user_mutex); release_sock(&rx->sk); if (ret < 0) { ret = -ERESTARTSYS; goto error_put; } if (p.call.tx_total_len != -1) { ret = -EINVAL; if (call->tx_total_len != -1 || call->tx_pending || call->tx_top != 0) goto out_put_unlock; call->tx_total_len = p.call.tx_total_len; } } switch (p.call.nr_timeouts) { case 3: j = msecs_to_jiffies(p.call.timeouts.normal); if (p.call.timeouts.normal > 0 && j == 0) j = 1; WRITE_ONCE(call->next_rx_timo, j); fallthrough; case 2: j = msecs_to_jiffies(p.call.timeouts.idle); if (p.call.timeouts.idle > 0 && j == 0) j = 1; WRITE_ONCE(call->next_req_timo, j); fallthrough; case 1: if (p.call.timeouts.hard > 0) { j = p.call.timeouts.hard * HZ; now = jiffies; j += now; WRITE_ONCE(call->expect_term_by, j); rxrpc_reduce_call_timer(call, j, now, rxrpc_timer_set_for_hard); } break; } if (rxrpc_call_is_complete(call)) { /* it's too late for this call */ ret = -ESHUTDOWN; } else if (p.command == RXRPC_CMD_SEND_ABORT) { rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, rxrpc_abort_call_sendmsg); ret = 0; } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else { ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock); } out_put_unlock: if (!dropped_lock) mutex_unlock(&call->user_mutex); error_put: rxrpc_put_call(call, rxrpc_call_put_sendmsg); _leave(" = %d", ret); return ret; error_release_sock: release_sock(&rx->sk); return ret; } /** * rxrpc_kernel_send_data - Allow a kernel service to send data on a call * @sock: The socket the call is on * @call: The call to send data through * @msg: The data to send * @len: The amount of data to send * @notify_end_tx: Notification that the last packet is queued. * * Allow a kernel service to send data on a call. The call must be in an state * appropriate to sending data. No control data should be supplied in @msg, * nor should an address be supplied. MSG_MORE should be flagged if there's * more data to come, otherwise this data will end the transmission phase. */ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, struct msghdr *msg, size_t len, rxrpc_notify_end_tx_t notify_end_tx) { bool dropped_lock = false; int ret; _enter("{%d},", call->debug_id); ASSERTCMP(msg->msg_name, ==, NULL); ASSERTCMP(msg->msg_control, ==, NULL); mutex_lock(&call->user_mutex); ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, notify_end_tx, &dropped_lock); if (ret == -ESHUTDOWN) ret = call->error; if (!dropped_lock) mutex_unlock(&call->user_mutex); _leave(" = %d", ret); return ret; } EXPORT_SYMBOL(rxrpc_kernel_send_data); /** * rxrpc_kernel_abort_call - Allow a kernel service to abort a call * @sock: The socket the call is on * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet * @error: Local error value * @why: Indication as to why. * * Allow a kernel service to abort a call, if it's still in an abortable state * and return true if the call was aborted, false if it was already complete. */ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, u32 abort_code, int error, enum rxrpc_abort_reason why) { bool aborted; _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); mutex_lock(&call->user_mutex); aborted = rxrpc_propose_abort(call, abort_code, error, why); mutex_unlock(&call->user_mutex); return aborted; } EXPORT_SYMBOL(rxrpc_kernel_abort_call); /** * rxrpc_kernel_set_tx_length - Set the total Tx length on a call * @sock: The socket the call is on * @call: The call to be informed * @tx_total_len: The amount of data to be transmitted for this call * * Allow a kernel service to set the total transmit length on a call. This * allows buffer-to-packet encrypt-and-copy to be performed. * * This function is primarily for use for setting the reply length since the * request length can be set when beginning the call. */ void rxrpc_kernel_set_tx_length(struct socket *sock, struct rxrpc_call *call, s64 tx_total_len) { WARN_ON(call->tx_total_len != -1); call->tx_total_len = tx_total_len; } EXPORT_SYMBOL(rxrpc_kernel_set_tx_length); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * consolidates trace point definitions * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/slab.h> #include <asm/unaligned.h> #include <asm/bitops.h> #define CREATE_TRACE_POINTS #include <trace/events/skb.h> #include <trace/events/net.h> #include <trace/events/napi.h> #include <trace/events/sock.h> #include <trace/events/udp.h> #include <trace/events/tcp.h> #include <trace/events/fib.h> #include <trace/events/qdisc.h> #if IS_ENABLED(CONFIG_BRIDGE) #include <trace/events/bridge.h> EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add); EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); EXPORT_TRACEPOINT_SYMBOL_GPL(br_mdb_full); #endif #if IS_ENABLED(CONFIG_PAGE_POOL) #include <trace/events/page_pool.h> #endif #include <trace/events/neigh.h> EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update_done); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_timer_handler); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_done); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_dead); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_cleanup_and_release); EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); EXPORT_TRACEPOINT_SYMBOL_GPL(udp_fail_queue_rcv_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(sk_data_ready); |
| 2098 4425 1125 1587 1700 1390 3 124 99 2 42 4421 4425 4425 4423 42 6733 2389 6728 6730 6733 6728 2387 2389 2388 268 2256 734 2389 1738 4672 10 10 4672 10 4425 10 4407 357 479 4424 4671 4672 1 4425 4322 135 3 269 269 268 1 4323 270 4323 4425 4038 1911 4340 264 1786 370 2399 2400 2459 2307 829 827 2458 1955 1954 1954 1 73 1928 1928 1928 1928 1928 711 1 20 17 15 20 20 20 2958 1810 1265 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefor each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ lvl * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefor the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON # define NR_BASES 2 # define BASE_STD 0 # define BASE_DEF 1 #else # define NR_BASES 1 # define BASE_STD 0 # define BASE_DEF 0 #endif struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool next_expiry_recalc; bool is_idle; bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #ifdef CONFIG_SYSCTL static int timer_migration_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, {} }; static int __init timer_sysctl_init(void) { register_sysctl("kernel", timer_sysctl); return 0; } device_initcall(timer_sysctl_init); #endif /* CONFIG_SYSCTL */ #else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffie is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, false); } EXPORT_SYMBOL_GPL(__round_jiffies); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, true); } EXPORT_SYMBOL_GPL(__round_jiffies_up); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { /* * The timer wheel has to guarantee that a timer does not fire * early. Early expiry can happen due to: * - Timer is armed at the edge of a tick * - Truncation of the expiry time in the outer wheel levels * * Round up with level granularity to prevent this. */ expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0, bucket_expiry); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1, bucket_expiry); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2, bucket_expiry); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3, bucket_expiry); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4, bucket_expiry); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5, bucket_expiry); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6, bucket_expiry); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7, bucket_expiry); } else if ((long) delta < 0) { idx = clk & LVL_MASK; *bucket_expiry = clk; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry); } return idx; } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { /* * Deferrable timers do not prevent the CPU from entering dynticks and * are not taken into account on the idle/nohz_full path. An IPI when a * new deferrable timer is enqueued will wake up the remote CPU but * nothing will be done with the deferrable timer base. Therefore skip * the remote IPI for deferrable timers completely. */ if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE) return; /* * We might have to IPI the remote CPU if the base is idle and the * timer is not deferrable. If the other CPU is on the way to idle * then it can't set base->is_idle as we hold the base lock: */ if (base->is_idle) wake_up_nohz_cpu(base->cpu); } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, bucket_expiry); /* * Check whether this is the new first expiring timer. The * effective expiry time of the timer is required here * (bucket_expiry) instead of timer->expires. */ if (time_before(bucket_expiry, base->next_expiry)) { /* * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long bucket_expiry; unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry); enqueue_timer(base, timer, idx, bucket_expiry); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; struct timer_hint { void (*function)(struct timer_list *t); long offset; }; #define TIMER_HINT(fn, container, timr, hintfn) \ { \ .function = fn, \ .offset = offsetof(container, hintfn) - \ offsetof(container, timr) \ } static const struct timer_hint timer_hints[] = { TIMER_HINT(delayed_work_timer_fn, struct delayed_work, timer, work.func), TIMER_HINT(kthread_delayed_work_timer_fn, struct kthread_delayed_work, timer, work.func), }; static void *timer_debug_hint(void *addr) { struct timer_list *timer = addr; int i; for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { if (timer_hints[i].function == timer->function) { void (**fn)(void) = addr + timer_hints[i].offset; return *fn; } } return timer->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static const struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_timer_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS)) flags &= TIMER_INIT_FLAGS; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * init_timer_key() must be done to a timer prior calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map); base->next_expiry_recalc = true; } detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); return base; } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = this_cpu_ptr(&timer_bases[BASE_DEF]); return base; } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline struct timer_base * get_target_base(struct timer_base *base, unsigned tflags) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !(tflags & TIMER_PINNED)) return get_timer_cpu_base(tflags, get_nohz_timer_target()); #endif return get_timer_this_cpu_base(tflags); } static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { /* * Check whether we can forward the base. We can only do that when * @basej is past base->clk otherwise we might rewind base->clk. */ if (time_before_eq(basej, base->clk)) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, basej)) { base->clk = basej; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } } static inline void forward_timer_base(struct timer_base *base) { __forward_timer_base(base, READ_ONCE(jiffies)); } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 #define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { unsigned long clk = 0, flags, bucket_expiry; struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; int ret = 0; debug_assert_init(timer); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk, &bucket_expiry); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_target_base(base, timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() is required. Otherwise we need to (re)calculate * the wheel index via internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry); else internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and not modified or was in * shutdown state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the del_timer() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * If @timer->function == NULL then the start operation is silently * discarded. In this case the return value is 0 and meaningless. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_REDUCE); } EXPORT_SYMBOL(timer_reduce); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->function == NULL then the start operation is silently * discarded. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; debug_assert_init(timer); if (WARN_ON_ONCE(timer_pending(timer))) return; new_base = get_timer_cpu_base(timer->flags, cpu); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated while * holding base lock to prevent a race against the shutdown code. */ if (!timer->function) goto out_unlock; if (base != new_base) { timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } forward_timer_base(base); debug_timer_activate(timer); internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * __timer_delete - Internal function: Deactivate a timer * @timer: The timer to be deactivated * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the time. In that * case any attempt to rearm @timer after this function returns will be * silently ignored. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); /* * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock * aquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * * If timer->function is currently executed, then this makes sure * that the callback cannot requeue the timer. */ if (timer_pending(timer) || shutdown) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } /** * timer_delete - Deactivate a timer * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * timer_delete_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete(struct timer_list *timer) { return __timer_delete(timer, false); } EXPORT_SYMBOL(timer_delete); /** * timer_shutdown - Deactivate a timer and prevent rearming * @timer: The timer to be deactivated * * The function does not wait for an eventually running timer callback on a * different CPU but it prevents rearming of the timer. Any attempt to arm * @timer after this function returns will be silently ignored. * * This function is useful for teardown code and should only be used when * timer_shutdown_sync() cannot be invoked due to locking or context constraints. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown(struct timer_list *timer) { return __timer_delete(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown); /** * __try_to_del_timer_sync - Internal function: Try to deactivate a timer * @timer: Timer to deactivate * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the timer. Any * attempt to rearm @timer after this function returns will be silently * ignored. * * This function cannot guarantee that the timer cannot be rearmed * right after dropping the base lock if @shutdown is false. That * needs to be prevented by the calling code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { return __try_to_del_timer_sync(timer, false); } EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reacquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { } static inline void timer_base_lock_expiry(struct timer_base *base) { } static inline void timer_base_unlock_expiry(struct timer_base *base) { } static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif /** * __timer_delete_sync - Internal function: Deactivate a timer and wait * for the handler to finish. * @timer: The timer to be deactivated * @shutdown: If true, @timer->function will be set to NULL under the * timer base lock which prevents rearming of @timer * * If @shutdown is not set the timer can be rearmed later. If the timer can * be rearmed concurrently, i.e. after dropping the base lock then the * return value is meaningless. * * If @shutdown is set then @timer->function is set to NULL under timer * base lock which prevents rearming of the timer. Any attempt to rearm * a shutdown timer is silently ignored. * * If the timer should be reused after shutdown it has to be initialized * again. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete_sync(struct timer_list *timer, bool shutdown) { int ret; #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_hardirq() && !(timer->flags & TIMER_IRQSAFE)); /* * Must be able to sleep on PREEMPT_RT because of the slowpath in * del_timer_wait_running(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(timer->flags & TIMER_IRQSAFE)) lockdep_assert_preemption_enabled(); do { ret = __try_to_del_timer_sync(timer, shutdown); if (unlikely(ret < 0)) { del_timer_wait_running(timer); cpu_relax(); } } while (ret < 0); return ret; } /** * timer_delete_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * * Now timer_delete_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * If such a guarantee is needed, e.g. for teardown situations then use * timer_shutdown_sync() instead. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete_sync(struct timer_list *timer) { return __timer_delete_sync(timer, false); } EXPORT_SYMBOL(timer_delete_sync); /** * timer_shutdown_sync - Shutdown a timer and prevent rearming * @timer: The timer to be shutdown * * When the function returns it is guaranteed that: * - @timer is not queued * - The callback function of @timer is not running * - @timer cannot be enqueued again. Any attempt to rearm * @timer is silently ignored. * * See timer_delete_sync() for synchronization rules. * * This function is useful for final teardown of an infrastructure where * the timer is subject to a circular dependency problem. * * A common pattern for this is a timer and a workqueue where the timer can * schedule work and work can arm the timer. On shutdown the workqueue must * be destroyed and the timer must be prevented from rearming. Unless the * code has conditionals like 'if (mything->in_shutdown)' to prevent that * there is no way to get this correct with timer_delete_sync(). * * timer_shutdown_sync() is solving the problem. The correct ordering of * calls in this case is: * * timer_shutdown_sync(&mything->timer); * workqueue_destroy(&mything->workqueue); * * After this 'mything' can be safely freed. * * This obviously implies that the timer is not required to be functional * for the rest of the shutdown operation. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown_sync(struct timer_list *timer) { return __timer_delete_sync(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * timer_delete_sync() by acquiring the lock_map around the fn() * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } static void expire_timers(struct timer_base *base, struct hlist_head *head) { /* * This value is required only for tracing. base->clk was * incremented directly before expire_timers was called. But expiry * is related to the old base->clk value. */ unsigned long baseclk = base->clk - 1; while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); timer = hlist_entry(head->first, struct timer_list, entry); base->running_timer = timer; detach_timer(timer, true); fn = timer->function; if (WARN_ON_ONCE(!fn)) { /* Should never happen. Emphasis on should! */ base->running_timer = NULL; continue; } if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); } } } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { unsigned long clk = base->clk = base->next_expiry; struct hlist_head *vec; int i, levels = 0; unsigned int idx; for (i = 0; i < LVL_DEPTH; i++) { idx = (clk & LVL_MASK) + i * LVL_SIZE; if (__test_and_clear_bit(idx, base->pending_map)) { vec = base->vectors + idx; hlist_move_list(vec, heads++); levels++; } /* Is it time to look at the next level? */ if (clk & LVL_CLK_MASK) break; /* Shift clock for the next level granularity */ clk >>= LVL_CLK_SHIFT; } return levels; } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { unsigned pos, start = offset + clk; unsigned end = offset + LVL_SIZE; pos = find_next_bit(base->pending_map, end, start); if (pos < end) return pos - start; pos = find_next_bit(base->pending_map, start, offset); return pos < start ? pos + LVL_SIZE - start : -1; } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. * * Store next expiry time in base->next_expiry. */ static void next_expiry_recalc(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; next = base->clk + NEXT_TIMER_MAX_DELTA; clk = base->clk; for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { int pos = next_pending_bucket(base, offset, clk & LVL_MASK); unsigned long lvl_clk = clk & LVL_CLK_MASK; if (pos >= 0) { unsigned long tmp = clk + (unsigned long) pos; tmp <<= LVL_SHIFT(lvl); if (time_before(tmp, next)) next = tmp; /* * If the next expiration happens before we reach * the next level, no need to check further. */ if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK)) break; } /* * Clock for the next level. If the current level clock lower * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next * expiring jiffie. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 * * we have to look at all levels @index 0. With * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 2 * * LVL0 has the next expiring bucket @index 2. The upper * levels have the next expiring bucket @index 1. * * In case that the propagation wraps the next level the same * rules apply: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 F 2 * * So after looking at LVL0 we get: * * LVL5 LVL4 LVL3 LVL2 LVL1 * 0 0 0 1 0 * * So no propagation from LVL1 to LVL2 because that happened * with the add already, but then we need to propagate further * from LVL2 to LVL3. * * So the simple check whether the lower bits of the current * level are 0 or not is sufficient for all cases. */ adj = lvl_clk ? 1 : 0; clk >>= LVL_CLK_SHIFT; clk += adj; } base->next_expiry = next; base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffie. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } /** * get_next_timer_interrupt - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending * timer or KTIME_MAX if no timer is pending. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA; u64 expires = KTIME_MAX; bool was_idle; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) return expires; raw_spin_lock(&base->lock); if (base->next_expiry_recalc) next_expiry_recalc(base); /* * We have a fresh next event. Check whether we can forward the * base. */ __forward_timer_base(base, basej); if (base->timers_pending) { nextevt = base->next_expiry; /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; expires = basem + (u64)(nextevt - basej) * TICK_NSEC; } else { /* * Move next_expiry for the empty base into the future to * prevent a unnecessary raise of the timer softirq when the * next_expiry value will be reached even if there is no timer * pending. */ base->next_expiry = nextevt; } /* * Base is idle if the next event is more than a tick away. * * If the base is marked idle then any timer add operation must forward * the base clk itself to keep granularity small. This idle logic is * only maintained for the BASE_STD base, deferrable timers may still * see large granularity skew (by design). */ was_idle = base->is_idle; base->is_idle = time_after(nextevt, basej + 1); if (was_idle != base->is_idle) trace_timer_base_idle(base->is_idle, base->cpu); raw_spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * We do this unlocked. The worst outcome is a remote enqueue sending * a pointless IPI, but taking the lock would just make the window for * sending the IPI a few instructions smaller for the cost of taking * the lock in the exit from idle path. */ if (base->is_idle) { base->is_idle = false; trace_timer_base_idle(false, smp_processor_id()); } } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; if (time_before(jiffies, base->next_expiry)) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * NEXT_TIMER_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); /* * While executing timers, base->clk is set 1 offset ahead of * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; next_expiry_recalc(base); while (levels--) expire_timers(base, heads + levels); } raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->next_expiry)) { if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; if (time_before(jiffies, base->next_expiry)) return; } raise_softirq(TIMER_SOFTIRQ); } /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { struct timer_list timer; struct task_struct *task; }; static void process_timeout(struct timer_list *t) { struct process_timer *timeout = from_timer(timeout, t, timer); wake_up_process(timeout->task); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have elapsed. * The function behavior depends on the current task state * (see also set_current_state() description): * * %TASK_RUNNING - the scheduler is called, but the task does not sleep * at all. That happens because sched_submit_work() does nothing for * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns 0 when the timer has expired otherwise the remaining time in * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct process_timer timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { printk(KERN_ERR "schedule_timeout: wrong timeout " "value %lx\n", timeout); dump_stack(); __set_current_state(TASK_RUNNING); goto out; } } expire = timeout + jiffies; timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* * Like schedule_timeout_uninterruptible(), except this task will not contribute * to load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) { struct timer_base *base; int b; for (b = 0; b < NR_BASES; b++) { base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } return 0; } int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; int b, i; for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); /* * The current CPUs base clock might be stale. Update it * before moving the timers over. */ forward_timer_base(new_base); WARN_ON_ONCE(old_base->running_timer); old_base->running_timer = NULL; for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); raw_spin_unlock(&old_base->lock); raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct timer_base *base; int i; for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; timer_base_init_expiry_lock(base); } } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init init_timers(void) { init_timer_cpus(); posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); /** * usleep_range_state - Sleep for an approximate time in a given state * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } EXPORT_SYMBOL(usleep_range_state); |
| 28 28 1 29 28 1 10 10 1107 1117 6 5 11 11 11 11 11 11 11 1 11 11 1 10 11 11 11 11 11 11 11 11 11 11 11 277 200 5 87 87 87 87 87 87 87 | 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 | // 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. * * Support for INET connection oriented protocols. * * Authors: See the TCP sources */ #include <linux/module.h> #include <linux/jhash.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/tcp.h> #include <net/sock_reuseport.h> #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) /* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses * if IPv6 only, and any IPv4 addresses * if not IPv6 only * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, * and 0.0.0.0 equals to 0.0.0.0 only */ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, const struct in6_addr *sk2_rcv_saddr6, __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk1_ipv6only, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) return true; if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return true; if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) return true; if (sk2_rcv_saddr6 && ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6)) return true; return false; } #endif /* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr, inet6_rcv_saddr(sk2), sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk), ipv6_only_sock(sk2), match_wildcard, match_wildcard); #endif return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk2), match_wildcard, match_wildcard); } EXPORT_SYMBOL(inet_rcv_saddr_equal); bool inet_rcv_saddr_any(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_addr_any(&sk->sk_v6_rcv_saddr); #endif return !sk->sk_rcv_saddr; } /** * inet_sk_get_local_port_range - fetch ephemeral ports range * @sk: socket * @low: pointer to low port * @high: pointer to high port * * Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range) * Range can be overridden if socket got IP_LOCAL_PORT_RANGE option. * Returns true if IP_LOCAL_PORT_RANGE was set on this socket. */ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) { int lo, hi, sk_lo, sk_hi; bool local_range = false; u32 sk_range; inet_get_local_port_range(sock_net(sk), &lo, &hi); sk_range = READ_ONCE(inet_sk(sk)->local_port_range); if (unlikely(sk_range)) { sk_lo = sk_range & 0xffff; sk_hi = sk_range >> 16; if (lo <= sk_lo && sk_lo <= hi) lo = sk_lo; if (lo <= sk_hi && sk_hi <= hi) hi = sk_hi; local_range = true; } *low = lo; *high = hi; return local_range; } EXPORT_SYMBOL(inet_sk_get_local_port_range); static bool inet_use_bhash2_on_bind(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); if (addr_type == IPV6_ADDR_ANY) return false; if (addr_type != IPV6_ADDR_MAPPED) return true; } #endif return sk->sk_rcv_saddr != htonl(INADDR_ANY); } static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { int bound_dev_if2; if (sk == sk2) return false; bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); if (!sk->sk_bound_dev_if || !bound_dev_if2 || sk->sk_bound_dev_if == bound_dev_if2) { if (sk->sk_reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN) { if (!relax || (!reuseport_ok && sk->sk_reuseport && sk2->sk_reuseport && reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(sk_uid, sock_i_uid(sk2))))) return true; } else if (!reuseport_ok || !sk->sk_reuseport || !sk2->sk_reuseport || !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(sk_uid, sock_i_uid(sk2)))) { return true; } } return false; } static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) return false; return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); } static bool inet_bhash2_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { struct sock *sk2; sk_for_each_bound(sk2, &tb2->owners) { if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok)) return true; } return false; } #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ sk_for_each_bound(sk2, &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, const struct inet_bind2_bucket *tb2, /* may be null */ bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); struct sock_reuseport *reuseport_cb; bool reuseport_cb_ok; struct sock *sk2; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); /* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if * ipv4) should have been checked already. We need to do these two * checks separately because their spinlocks have to be acquired/released * independently of each other, to prevent possible deadlocks */ if (inet_use_bhash2_on_bind(sk)) return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok); /* Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed * in tb->owners and tb2->owners list belong * to the same net - the one this bucket belongs to. */ sk_for_each_bound_bhash(sk2, tb2, tb) { if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok)) continue; if (inet_rcv_saddr_equal(sk, sk2, true)) return true; } return false; } /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or * INADDR_ANY (if ipv4) socket. * * Caller must hold bhash hashbucket lock with local bh disabled, to protect * against concurrent binds on the port for addr any */ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l3mdev, bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); const struct net *net = sock_net(sk); struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; bool reuseport_cb_ok; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); head2 = inet_bhash2_addr_any_hashbucket(sk, net, port); spin_lock(&head2->lock); inet_bind_bucket_for_each(tb2, &head2->chain) if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) break; if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) { spin_unlock(&head2->lock); return true; } spin_unlock(&head2->lock); return false; } /* * Find an open port number for the socket. Returns with the * inet_bind_hashbucket locks held if successful. */ static struct inet_bind_hashbucket * inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, struct inet_bind2_bucket **tb2_ret, struct inet_bind_hashbucket **head2_ret, int *port_ret) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); int i, low, high, attempt_half, port, l3mdev; struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; bool relax = false; l3mdev = inet_sk_bound_l3mdev(sk); ports_exhausted: attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; other_half_scan: inet_sk_get_local_port_range(sk, &low, &high); high++; /* [32768, 60999] -> [32768, 61000[ */ if (high - low < 4) attempt_half = 0; if (attempt_half) { int half = low + (((high - low) >> 2) << 1); if (attempt_half == 1) high = half; else low = half; } remaining = high - low; if (likely(remaining > 1)) remaining &= ~1U; offset = get_random_u32_below(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ offset |= 1U; other_parity_scan: port = low + offset; for (i = 0; i < remaining; i += 2, port += 2) { if (unlikely(port >= high)) port -= remaining; if (inet_is_local_reserved_port(net, port)) continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); if (inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false)) goto next_port; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) { if (!inet_csk_bind_conflict(sk, tb, tb2, relax, false)) goto success; spin_unlock(&head2->lock); goto next_port; } tb = NULL; goto success; next_port: spin_unlock_bh(&head->lock); cond_resched(); } offset--; if (!(offset & 1)) goto other_parity_scan; if (attempt_half == 1) { /* OK we now try the upper half of the range */ attempt_half = 2; goto other_half_scan; } if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; } return NULL; success: *port_ret = port; *tb_ret = tb; *tb2_ret = tb2; *head2_ret = head2; return head; } static inline int sk_reuseport_match(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); if (tb->fastreuseport <= 0) return 0; if (!sk->sk_reuseport) return 0; if (rcu_access_pointer(sk->sk_reuseport_cb)) return 0; if (!uid_eq(tb->fastuid, uid)) return 0; /* We only need to check the rcv_saddr if this tb was once marked * without fastreuseport and then was reset, as we can only know that * the fast_*rcv_saddr doesn't have any conflicts with the socks on the * owners list. */ if (tb->fastreuseport == FASTREUSEPORT_ANY) return 1; #if IS_ENABLED(CONFIG_IPV6) if (tb->fast_sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr, inet6_rcv_saddr(sk), tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, ipv6_only_sock(sk), true, false); #endif return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr, ipv6_only_sock(sk), true, false); } void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; if (hlist_empty(&tb->bhash2)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } else { tb->fastreuseport = 0; } } else { if (!reuse) tb->fastreuse = 0; if (sk->sk_reuseport) { /* We didn't match or we don't have fastreuseport set on * the tb, but we have sk_reuseport set on this socket * and we know that there are no bind conflicts with * this socket in this tb, so reset our tb's reuseport * settings so that any subsequent sockets that match * our current socket will be put on the fast path. * * If we reset we need to set FASTREUSEPORT_STRICT so we * do extra checking for all subsequent sk_reuseport * socks. */ if (!sk_reuseport_match(tb, sk)) { tb->fastreuseport = FASTREUSEPORT_STRICT; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } } else { tb->fastreuseport = 0; } } } /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) */ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); if (!port) { head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port); if (!head) return ret; head2_lock_acquired = true; if (tb && tb2) goto success; found_port = true; } else { head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) break; } if (!tb) { tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, head, port, l3mdev); if (!tb) goto fail_unlock; bhash_created = true; } if (!found_port) { if (!hlist_empty(&tb->bhash2)) { if (sk->sk_reuse == SK_FORCE_REUSE || (tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) check_bind_conflict = false; } if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true)) goto fail_unlock; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); head2_lock_acquired = true; tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); } if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, head2, tb, sk); if (!tb2) goto fail_unlock; bhash2_created = true; } if (!found_port && check_bind_conflict) { if (inet_csk_bind_conflict(sk, tb, tb2, true, true)) goto fail_unlock; } success: inet_csk_update_fastreuse(tb, sk); if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, tb2, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); ret = 0; fail_unlock: if (ret) { if (bhash2_created) inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2); if (bhash_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); } if (head2_lock_acquired) spin_unlock(&head2->lock); spin_unlock_bh(&head->lock); return ret; } EXPORT_SYMBOL_GPL(inet_csk_get_port); /* * Wait for an incoming connection, avoid race conditions. This must be called * with the socket locked. */ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) { struct inet_connection_sock *icsk = inet_csk(sk); DEFINE_WAIT(wait); int err; /* * True wake-one mechanism for incoming connections: only * one process gets woken up, not the 'whole herd'. * Since we do not 'race & poll' for established sockets * anymore, the common case will execute the loop only once. * * Subtle issue: "add_wait_queue_exclusive()" will be added * after any current non-exclusive waiters, and we know that * it will always _stay_ after any new non-exclusive waiters * because all non-exclusive waiters are added at the * beginning of the wait-queue. As such, it's ok to "drop" * our exclusiveness temporarily when we get woken up without * having to remove and re-insert us on the wait queue. */ for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) timeo = schedule_timeout(timeo); sched_annotate_sleep(); lock_sock(sk); err = 0; if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) break; err = -EINVAL; if (sk->sk_state != TCP_LISTEN) break; err = sock_intr_errno(timeo); if (signal_pending(current)) break; err = -EAGAIN; if (!timeo) break; } finish_wait(sk_sleep(sk), &wait); return err; } /* * This will accept the next outstanding connection. */ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *req; struct sock *newsk; int error; lock_sock(sk); /* We need to make sure that this socket is listening, * and that it has something pending. */ error = -EINVAL; if (sk->sk_state != TCP_LISTEN) goto out_err; /* Find already established connection */ if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; if (!timeo) goto out_err; error = inet_csk_wait_for_connect(sk, timeo); if (error) goto out_err; } req = reqsk_queue_remove(queue, sk); newsk = req->sk; if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { spin_lock_bh(&queue->fastopenq.lock); if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken * so reqsk_fastopen_remove() will free the req * when 3WHS finishes (or is aborted). */ req->sk = NULL; req = NULL; } spin_unlock_bh(&queue->fastopenq.lock); } out: release_sock(sk); if (newsk && mem_cgroup_sockets_enabled) { int amt = 0; /* atomically get the memory usage, set and charge the * newsk->sk_memcg. */ lock_sock(newsk); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg) { /* The socket has not been accepted yet, no need * to look at newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + atomic_read(&newsk->sk_rmem_alloc)); } if (amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt, GFP_KERNEL | __GFP_NOFAIL); release_sock(newsk); } if (req) reqsk_put(req); if (newsk) inet_init_csk_locks(newsk); return newsk; out_err: newsk = NULL; req = NULL; *err = error; goto out; } EXPORT_SYMBOL(inet_csk_accept); /* * Using different timers for retransmit, delayed acks and probes * We may wish use just one timer maintaining a list of expire jiffies * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *t), void (*delack_handler)(struct timer_list *t), void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); void inet_csk_clear_xmit_timers(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_pending = icsk->icsk_ack.pending = 0; sk_stop_timer(sk, &icsk->icsk_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_delete_keepalive_timer); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) { sk_reset_timer(sk, &sk->sk_timer, jiffies + len); } EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct ip_options_rcu *opt; struct rtable *rt; rcu_read_lock(); opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct inet_sock *newinet = inet_sk(newsk); struct ip_options_rcu *opt; struct flowi4 *fl4; struct rtable *rt; opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; route_err: ip_rt_put(rt); no_route: __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); /* Decide when to expire the request and when to resend SYN-ACK */ static void syn_ack_recalc(struct request_sock *req, const int max_syn_ack_retries, const u8 rskq_defer_accept, int *expire, int *resend) { if (!rskq_defer_accept) { *expire = req->num_timeout >= max_syn_ack_retries; *resend = 1; return; } *expire = req->num_timeout >= max_syn_ack_retries && (!inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept); /* Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ *resend = !inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept - 1; } int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) { int err = req->rsk_ops->rtx_syn_ack(parent, req); if (!err) req->num_retrans++; return err; } EXPORT_SYMBOL(inet_rtx_syn_ack); static struct request_sock *inet_reqsk_clone(struct request_sock *req, struct sock *sk) { struct sock *req_sk, *nreq_sk; struct request_sock *nreq; nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!nreq) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ sock_put(sk); return NULL; } req_sk = req_to_sk(req); nreq_sk = req_to_sk(nreq); memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; #endif nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; nreq->rsk_listener = sk; /* We need not acquire fastopenq->lock * because the child socket is locked in inet_csk_listen_stop(). */ if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); return nreq; } static void reqsk_queue_migrated(struct request_sock_queue *queue, const struct request_sock *req) { if (req->num_timeout == 0) atomic_inc(&queue->young); atomic_inc(&queue->qlen); } static void reqsk_migrate_reset(struct request_sock *req) { req->saved_syn = NULL; #if IS_ENABLED(CONFIG_IPV6) inet_rsk(req)->ipv6_opt = NULL; inet_rsk(req)->pktopts = NULL; #else inet_rsk(req)->ireq_opt = NULL; #endif } /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { struct sock *sk = req_to_sk(req); bool found = false; if (sk_hashed(sk)) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash); spin_lock(lock); found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); } if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) reqsk_put(req); return found; } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { bool unlinked = reqsk_queue_unlink(req); if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } return unlinked; } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_put(req); } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; struct inet_connection_sock *icsk; struct request_sock_queue *queue; struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { struct sock *nsk; nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); if (!nsk) goto drop; nreq = inet_reqsk_clone(req, nsk); if (!nreq) goto drop; /* The new timer for the cloned req can decrease the 2 * by calling inet_csk_reqsk_queue_drop_and_put(), so * hold another count to prevent use-after-free and * call reqsk_put() just before return. */ refcount_set(&nreq->rsk_refcnt, 2 + 1); timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); req = nreq; sk_listener = nsk; } icsk = inet_csk(sk_listener); net = sock_net(sk_listener); max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means * one of the following things: synack was lost, ack was lost, * rtt is high or nobody planned to ack (i.e. synflood). * When server is a bit loaded, queue is populated with old * open requests, reducing effective size of queue. * When server is well loaded, queue size reduces to zero * after several minutes of work. It is not synflood, * it is normal operation. The solution is pruning * too old entries overriding normal timeout, when * situation becomes dangerous. * * Essentially, we reserve half of room for young * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; while (max_syn_ack_retries > 2) { if (qlen < young) break; max_syn_ack_retries--; young <<= 1; } } syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); req->rsk_ops->syn_ack_timeout(req); if (!expire && (!resend || !inet_rtx_syn_ack(sk_listener, req) || inet_rsk(req)->acked)) { if (req->num_timeout++ == 0) atomic_dec(&queue->young); mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); if (!nreq) return; if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ inet_csk_reqsk_queue_drop(sk_listener, nreq); goto no_ownership; } __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(oreq); reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); reqsk_put(oreq); reqsk_put(nreq); return; } /* Even if we can clone the req, we may need not retransmit any more * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another * CPU may win the "own_req" race so that inet_ehash_insert() fails. */ if (nreq) { __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); no_ownership: reqsk_migrate_reset(nreq); reqsk_queue_removed(queue, nreq); __reqsk_free(nreq); } drop: inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } static void reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { reqsk_queue_hash_req(req, timeout); inet_csk_reqsk_queue_added(sk); } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, const gfp_t priority) { struct inet_connection_sock *icsk = inet_csk(newsk); if (!icsk->icsk_ulp_ops) return; icsk->icsk_ulp_ops->clone(req, newsk, priority); } /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone * @req: request_sock * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority) { struct sock *newsk = sk_clone_lock(sk, priority); if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); inet_sk(newsk)->mc_list = NULL; newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; newicsk->icsk_probes_out = 0; newicsk->icsk_probes_tstamp = 0; /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); inet_clone_ulp(req, newsk, priority); security_inet_csk_clone(newsk, req); } return newsk; } EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this * socket, and thus no user references at all. Therefore we * can assume the socket waitqueue is inactive and nobody will * try to jump onto it. */ void inet_csk_destroy_sock(struct sock *sk) { WARN_ON(sk->sk_state != TCP_CLOSE); WARN_ON(!sock_flag(sk, SOCK_DEAD)); /* It cannot be in hash table! */ WARN_ON(!sk_unhashed(sk)); /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */ WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); this_cpu_dec(*sk->sk_prot->orphan_count); sock_put(sk); } EXPORT_SYMBOL(inet_csk_destroy_sock); /* This function allows to force a closure of a socket after the call to * tcp/dccp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) __releases(&sk->sk_lock.slock) { /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); sock_put(sk); inet_csk_prepare_for_destroy_sock(sk); inet_sk(sk)->inet_num = 0; } EXPORT_SYMBOL(inet_csk_prepare_forced_close); static int inet_ulp_can_listen(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone) return -EINVAL; return 0; } int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); int err; err = inet_ulp_can_listen(sk); if (unlikely(err)) return err; reqsk_queue_alloc(&icsk->icsk_accept_queue); sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); err = sk->sk_prot->get_port(sk, inet->inet_num); if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); err = sk->sk_prot->hash(sk); if (likely(!err)) return 0; } inet_sk_set_state(sk, TCP_CLOSE); return err; } EXPORT_SYMBOL_GPL(inet_csk_listen_start); static void inet_child_forget(struct sock *sk, struct request_sock *req, struct sock *child) { sk->sk_prot->disconnect(child, O_NONBLOCK); sock_orphan(child); this_cpu_inc(*sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is * blocked by sock lock in tcp_v4_rcv(). * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); child = NULL; } else { req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { inet_csk_reqsk_queue_drop(req->rsk_listener, req); reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); if (sk != req->rsk_listener) { /* another listening sk has been selected, * migrate the req to it. */ struct request_sock *nreq; /* hold a refcnt for the nreq->rsk_listener * which is assigned in inet_reqsk_clone() */ sock_hold(sk); nreq = inet_reqsk_clone(req, sk); if (!nreq) { inet_child_forget(sk, req, child); goto child_put; } refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(sk, nreq, child)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); reqsk_put(req); return child; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; } } /* Too bad, another child took ownership of the request, undo. */ child_put: bh_unlock_sock(child); sock_put(child); return NULL; } EXPORT_SYMBOL(inet_csk_complete_hashdance); /* * This routine closes sockets which have been at least partially * opened, but not yet accepted. */ void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *next, *req; /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) * or to send active reset (abort). * Certainly, it is pretty dangerous while synflood, but it is * bad justification for our negligence 8) * To be honest, we are not able to make either * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { struct sock *child = req->sk, *nsk; struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); nsk = reuseport_migrate_sock(sk, child, NULL); if (nsk) { nreq = inet_reqsk_clone(req, nsk); if (nreq) { refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); } else { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } /* inet_csk_reqsk_queue_add() has already * called inet_child_forget() on failure case. */ goto skip_child_forget; } } inet_child_forget(sk, req, child); skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); sock_put(child); cond_resched(); } if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq.lock); req = queue->fastopenq.rskq_rst_head; queue->fastopenq.rskq_rst_head = NULL; spin_unlock_bh(&queue->fastopenq.lock); while (req != NULL) { next = req->dl_next; reqsk_put(req); req = next; } } WARN_ON_ONCE(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; const struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; sin->sin_addr.s_addr = inet->inet_daddr; sin->sin_port = inet->inet_dport; } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; fl4 = &fl->u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) sk_setup_caps(sk, &rt->dst); rcu_read_unlock(); return &rt->dst; } struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) { struct dst_entry *dst = __sk_dst_check(sk, 0); struct inet_sock *inet = inet_sk(sk); if (!dst) { dst = inet_csk_rebuild_route(sk, &inet->cork.fl); if (!dst) goto out; } dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) dst = inet_csk_rebuild_route(sk, &inet->cork.fl); out: return dst; } EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); |
| 17134 17130 17134 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xsave/xrstor support. * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ #include <linux/bitops.h> #include <linux/compat.h> #include <linux/cpu.h> #include <linux/mman.h> #include <linux/nospec.h> #include <linux/pkeys.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/xcr.h> #include <asm/tlbflush.h> #include <asm/prctl.h> #include <asm/elf.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" #define for_each_extended_xfeature(bit, mask) \ (bit) = FIRST_EXTENDED_XFEATURE; \ for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask)) /* * Although we spell it out in here, the Processor Trace * xfeature is completely unused. We use other mechanisms * to save/restore PT state in Linux. */ static const char *xfeature_names[] = { "x87 floating point registers", "SSE registers", "AVX registers", "MPX bounds registers", "MPX CSR", "AVX-512 opmask", "AVX-512 Hi256", "AVX-512 ZMM_Hi256", "Processor Trace (unused)", "Protection Keys User registers", "PASID state", "Control-flow User registers", "Control-flow Kernel registers (unused)", "unknown xstate feature", "unknown xstate feature", "unknown xstate feature", "unknown xstate feature", "AMX Tile config", "AMX Tile data", "unknown xstate feature", }; static unsigned short xsave_cpuid_features[] __initdata = { [XFEATURE_FP] = X86_FEATURE_FPU, [XFEATURE_SSE] = X86_FEATURE_XMM, [XFEATURE_YMM] = X86_FEATURE_AVX, [XFEATURE_BNDREGS] = X86_FEATURE_MPX, [XFEATURE_BNDCSR] = X86_FEATURE_MPX, [XFEATURE_OPMASK] = X86_FEATURE_AVX512F, [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F, [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F, [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, [XFEATURE_PKRU] = X86_FEATURE_OSPKE, [XFEATURE_PASID] = X86_FEATURE_ENQCMD, [XFEATURE_CET_USER] = X86_FEATURE_SHSTK, [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, }; static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init; #define XSTATE_FLAG_SUPERVISOR BIT(0) #define XSTATE_FLAG_ALIGNED64 BIT(1) /* * Return whether the system supports a given xfeature. * * Also return the name of the (most advanced) feature that the caller requested: */ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) { u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features; if (unlikely(feature_name)) { long xfeature_idx, max_idx; u64 xfeatures_print; /* * So we use FLS here to be able to print the most advanced * feature that was requested but is missing. So if a driver * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the * missing AVX feature - this is the most informative message * to users: */ if (xfeatures_missing) xfeatures_print = xfeatures_missing; else xfeatures_print = xfeatures_needed; xfeature_idx = fls64(xfeatures_print)-1; max_idx = ARRAY_SIZE(xfeature_names)-1; xfeature_idx = min(xfeature_idx, max_idx); *feature_name = xfeature_names[xfeature_idx]; } if (xfeatures_missing) return 0; return 1; } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); static bool xfeature_is_aligned64(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64; } static bool xfeature_is_supervisor(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR; } static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) { unsigned int offs, i; /* * Non-compacted format and legacy features use the cached fixed * offsets. */ if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) || xfeature <= XFEATURE_SSE) return xstate_offsets[xfeature]; /* * Compacted format offsets depend on the actual content of the * compacted xsave area which is determined by the xcomp_bv header * field. */ offs = FXSAVE_SIZE + XSAVE_HDR_SIZE; for_each_extended_xfeature(i, xcomp_bv) { if (xfeature_is_aligned64(i)) offs = ALIGN(offs, 64); if (i == xfeature) break; offs += xstate_sizes[i]; } return offs; } /* * Enable the extended processor state save/restore feature. * Called once per CPU onlining. */ void fpu__init_cpu_xstate(void) { if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features) return; cr4_set_bits(X86_CR4_OSXSAVE); /* * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures * that any stale state is wiped out from XFD. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user * states can be set here. */ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * MSR_IA32_XSS sets supervisor states managed by XSAVES. */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } } static bool xfeature_enabled(enum xfeature xfeature) { return fpu_kernel_cfg.max_features & BIT_ULL(xfeature); } /* * Record the offsets and sizes of various xstates contained * in the XSAVE state memory layout. */ static void __init setup_xstate_cache(void) { u32 eax, ebx, ecx, edx, i; /* start at the beginning of the "extended state" */ unsigned int last_good_offset = offsetof(struct xregs_state, extended_state_area); /* * The FP xstates and SSE xstates are legacy states. They are always * in the fixed offsets in the xsave area in either compacted form * or standard form. */ xstate_offsets[XFEATURE_FP] = 0; xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state, xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; xstate_flags[i] = ecx; /* * If an xfeature is supervisor state, the offset in EBX is * invalid, leave it to -1. */ if (xfeature_is_supervisor(i)) continue; xstate_offsets[i] = ebx; /* * In our xstate size checks, we assume that the highest-numbered * xstate feature has the highest offset in the buffer. Ensure * it does. */ WARN_ONCE(last_good_offset > xstate_offsets[i], "x86/fpu: misordered xstate at %d\n", last_good_offset); last_good_offset = xstate_offsets[i]; } } static void __init print_xstate_feature(u64 xstate_mask) { const char *feature_name; if (cpu_has_xfeatures(xstate_mask, &feature_name)) pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name); } /* * Print out all the supported xstate features: */ static void __init print_xstate_features(void) { print_xstate_feature(XFEATURE_MASK_FP); print_xstate_feature(XFEATURE_MASK_SSE); print_xstate_feature(XFEATURE_MASK_YMM); print_xstate_feature(XFEATURE_MASK_BNDREGS); print_xstate_feature(XFEATURE_MASK_BNDCSR); print_xstate_feature(XFEATURE_MASK_OPMASK); print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); print_xstate_feature(XFEATURE_MASK_PKRU); print_xstate_feature(XFEATURE_MASK_PASID); print_xstate_feature(XFEATURE_MASK_CET_USER); print_xstate_feature(XFEATURE_MASK_XTILE_CFG); print_xstate_feature(XFEATURE_MASK_XTILE_DATA); } /* * This check is important because it is easy to get XSTATE_* * confused with XSTATE_BIT_*. */ #define CHECK_XFEATURE(nr) do { \ WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \ WARN_ON(nr >= XFEATURE_MAX); \ } while (0) /* * Print out xstate component offsets and sizes */ static void __init print_xstate_offset_size(void) { int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, xfeature_get_offset(fpu_kernel_cfg.max_features, i), i, xstate_sizes[i]); } } /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static __init void os_xrstor_booting(struct xregs_state *xstate) { u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE; u32 lmask = mask; u32 hmask = mask >> 32; int err; if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * All supported features have either init state all zeros or are * handled in setup_init_fpu() individually. This is an explicit * feature list and does not use XFEATURE_MASK*SUPPORTED to catch * newly added supported features at build time and make people * actually look at the init state for the new feature. */ #define XFEATURES_INIT_FPSTATE_HANDLED \ (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_PASID | \ XFEATURE_MASK_CET_USER | \ XFEATURE_MASK_XTILE) /* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) { BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED) != XFEATURES_INIT_FPSTATE_HANDLED); if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; print_xstate_features(); xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures); /* * Init all the features state with header.xfeatures being 0x0 */ os_xrstor_booting(&init_fpstate.regs.xsave); /* * All components are now in init state. Read the state back so * that init_fpstate contains all non-zero init state. This only * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because * those use the init optimization which skips writing data for * components in init state. * * XSAVE could be used, but that would require to reshuffle the * data when XSAVEC/S is available because XSAVEC/S uses xstate * compaction. But doing so is a pointless exercise because most * components have an all zeros init state except for the legacy * ones (FP and SSE). Those can be saved with FXSAVE into the * legacy area. Adding new features requires to ensure that init * state is all zeroes or if not to add the necessary handling * here. */ fxsave(&init_fpstate.regs.fxsave); } int xfeature_size(int xfeature_nr) { u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ static int validate_user_xstate_header(const struct xstate_header *hdr, struct fpstate *fpstate) { /* No unknown or supervisor features may be set */ if (hdr->xfeatures & ~fpstate->user_xfeatures) return -EINVAL; /* Userspace must use the uncompacted format */ if (hdr->xcomp_bv) return -EINVAL; /* * If 'reserved' is shrunken to add a new field, make sure to validate * that new field here! */ BUILD_BUG_ON(sizeof(hdr->reserved) != 48); /* No reserved bits may be set */ if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) return -EINVAL; return 0; } static void __init __xstate_dump_leaves(void) { int i; u32 eax, ebx, ecx, edx; static int should_dump = 1; if (!should_dump) return; should_dump = 0; /* * Dump out a few leaves past the ones that we support * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", XSTATE_CPUID, i, eax, ebx, ecx, edx); } } #define XSTATE_WARN_ON(x, fmt, ...) do { \ if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) { \ __xstate_dump_leaves(); \ } \ } while (0) #define XCHECK_SZ(sz, nr, __struct) ({ \ if (WARN_ONCE(sz != sizeof(__struct), \ "[%s]: struct is %zu bytes, cpu state %d bytes\n", \ xfeature_names[nr], sizeof(__struct), sz)) { \ __xstate_dump_leaves(); \ } \ true; \ }) /** * check_xtile_data_against_struct - Check tile data state size. * * Calculate the state size by multiplying the single tile size which is * recorded in a C struct, and the number of tiles that the CPU informs. * Compare the provided size with the calculation. * * @size: The tile data state size * * Returns: 0 on success, -EINVAL on mismatch. */ static int __init check_xtile_data_against_struct(int size) { u32 max_palid, palid, state_size; u32 eax, ebx, ecx, edx; u16 max_tile; /* * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of * supported tiles. */ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) { u16 tile_size, max; /* * Check the tile size info: * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; if (tile_size != sizeof(struct xtile_data)) { pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n", __stringify(XFEATURE_XTILE_DATA), sizeof(struct xtile_data), tile_size); __xstate_dump_leaves(); return -EINVAL; } if (max > max_tile) max_tile = max; } state_size = sizeof(struct xtile_data) * max_tile; if (size != state_size) { pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n", __stringify(XFEATURE_XTILE_DATA), state_size, size); __xstate_dump_leaves(); return -EINVAL; } return 0; } /* * We have a C struct for each 'xstate'. We need to ensure * that our software representation matches what the CPU * tells us about the state's size. */ static bool __init check_xstate_against_struct(int nr) { /* * Ask the CPU for the size of the state. */ int sz = xfeature_size(nr); /* * Match each CPU state with the corresponding software * structure. */ switch (nr) { case XFEATURE_YMM: return XCHECK_SZ(sz, nr, struct ymmh_struct); case XFEATURE_BNDREGS: return XCHECK_SZ(sz, nr, struct mpx_bndreg_state); case XFEATURE_BNDCSR: return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state); case XFEATURE_OPMASK: return XCHECK_SZ(sz, nr, struct avx_512_opmask_state); case XFEATURE_ZMM_Hi256: return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state); case XFEATURE_Hi16_ZMM: return XCHECK_SZ(sz, nr, struct avx_512_hi16_state); case XFEATURE_PKRU: return XCHECK_SZ(sz, nr, struct pkru_state); case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state); case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg); case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state); case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true; default: XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } return true; } static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) { unsigned int topmost = fls64(xfeatures) - 1; unsigned int offset = xstate_offsets[topmost]; if (topmost <= XFEATURE_SSE) return sizeof(struct xregs_state); if (compacted) offset = xfeature_get_offset(xfeatures, topmost); return offset + xstate_sizes[topmost]; } /* * This essentially double-checks what the cpu told us about * how large the XSAVE buffer needs to be. We are recalculating * it to be safe. * * Independent XSAVE features allocate their own buffers and are not * covered by these checks. Only the size of the buffer for task->fpu * is checked here. */ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES); unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { if (!check_xstate_against_struct(i)) return false; /* * Supervisor state components can be managed only by * XSAVES. */ if (!xsaves && xfeature_is_supervisor(i)) { XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i); return false; } } size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted); XSTATE_WARN_ON(size != kernel_size, "size %u != kernel_size %u\n", size, kernel_size); return size == kernel_size; } /* * Get total size of enabled xstates in XCR0 | IA32_XSS. * * Note the SDM's wording here. "sub-function 0" only enumerates * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. * * This also takes compaction into account. So this works for * XSAVEC as well. */ static unsigned int __init get_compacted_size(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 1: * EBX enumerates the size (in bytes) required by * the XSAVES instruction for an XSAVE area * containing all the state components * corresponding to bits currently set in * XCR0 | IA32_XSS. * * When XSAVES is not available but XSAVEC is (virt), then there * are no supervisor states, but XSAVEC still uses compacted * format. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); return ebx; } /* * Get the total size of the enabled xstates without the independent supervisor * features. */ static unsigned int __init get_xsave_compacted_size(void) { u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) return get_compacted_size(); /* Disable independent features. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); /* * Ask the hardware what size is required of the buffer. * This is the size required for the task->fpu buffer. */ size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); return size; } static unsigned int __init get_xsave_size_user(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by * the XSAVE instruction for an XSAVE area * containing all the *user* state components * corresponding to bits currently set in XCR0. */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); return ebx; } static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int user_size, kernel_size, kernel_default_size; bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); /* Uncompacted user space size */ user_size = get_xsave_size_user(); /* * XSAVES kernel size includes supervisor states and uses compacted * format. XSAVEC uses compacted format, but does not save * supervisor states. * * XSAVE[OPT] do not support supervisor states so kernel and user * size is identical. */ if (compacted) kernel_size = get_xsave_compacted_size(); else kernel_size = user_size; kernel_default_size = xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); if (!paranoid_xstate_size_valid(kernel_size)) return -EINVAL; fpu_kernel_cfg.max_size = kernel_size; fpu_user_cfg.max_size = user_size; fpu_kernel_cfg.default_size = kernel_default_size; fpu_user_cfg.default_size = xstate_calculate_size(fpu_user_cfg.default_features, false); return 0; } /* * We enabled the XSAVE hardware, but something went wrong and * we can not use it. Disable it. */ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) { fpu_kernel_cfg.max_features = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); /* Restore the legacy size.*/ fpu_kernel_cfg.max_size = legacy_size; fpu_kernel_cfg.default_size = legacy_size; fpu_user_cfg.max_size = legacy_size; fpu_user_cfg.default_size = legacy_size; /* * Prevent enabling the static branch which enables writes to the * XFD MSR. */ init_fpstate.xfd = 0; fpstate_reset(¤t->thread.fpu); } /* * Enable and initialize the xsave feature. * Called once per system bootup. */ void __init fpu__init_system_xstate(unsigned int legacy_size) { unsigned int eax, ebx, ecx, edx; u64 xfeatures; int err; int i; if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_info("x86/fpu: No FPU detected\n"); return; } if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: x87 FPU will use %s\n", boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { WARN_ON_FPU(1); return; } /* * Find user xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue * booting without it. This is too early to BUG(). */ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", fpu_kernel_cfg.max_features); goto out_disable; } /* * Clear XSAVE features that are disabled in the normal CPUID. */ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { unsigned short cid = xsave_cpuid_features[i]; /* Careful: X86_FEATURE_FPU is 0! */ if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid)) fpu_kernel_cfg.max_features &= ~BIT_ULL(i); } if (!cpu_feature_enabled(X86_FEATURE_XFD)) fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; else fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED; fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; /* Clean out dynamic features from default */ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features; fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; fpu_user_cfg.default_features = fpu_user_cfg.max_features; fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; /* Store it for paranoia check at the end */ xfeatures = fpu_kernel_cfg.max_features; /* * Initialize the default XFD state in initfp_state and enable the * dynamic sizing mechanism if dynamic states are available. The * static key cannot be enabled here because this runs before * jump_label_init(). This is delayed to an initcall. */ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; /* Set up compaction feature bit */ if (cpu_feature_enabled(X86_FEATURE_XSAVEC) || cpu_feature_enabled(X86_FEATURE_XSAVES)) setup_force_cpu_cap(X86_FEATURE_XCOMPACTED); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); /* Cache size, offset and flags for initialization */ setup_xstate_cache(); err = init_xstate_size(); if (err) goto out_disable; /* Reset the state for the current task */ fpstate_reset(¤t->thread.fpu); /* * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ update_regset_xstate_info(fpu_user_cfg.max_size, fpu_user_cfg.max_features); /* * init_fpstate excludes dynamic states as they are large but init * state is zero. */ init_fpstate.size = fpu_kernel_cfg.default_size; init_fpstate.xfeatures = fpu_kernel_cfg.default_features; if (init_fpstate.size > sizeof(init_fpstate.regs)) { pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n", sizeof(init_fpstate.regs), init_fpstate.size); goto out_disable; } setup_init_fpu_buf(); /* * Paranoia check whether something in the setup modified the * xfeatures mask. */ if (xfeatures != fpu_kernel_cfg.max_features) { pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n", xfeatures, fpu_kernel_cfg.max_features); goto out_disable; } /* * CPU capabilities initialization runs before FPU init. So * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely * functional, set the feature bit so depending code works. */ setup_force_cpu_cap(X86_FEATURE_OSXSAVE); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, fpu_kernel_cfg.max_size, boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard"); return; out_disable: /* something went wrong, try to boot without any XSAVE support */ fpu__init_disable_system_xstate(legacy_size); } /* * Restore minimal FPU state after suspend: */ void fpu__resume_cpu(void) { /* * Restore XCR0 on xsave capable CPUs: */ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * Restore IA32_XSS. The same CPUID bit enumerates support * of XSAVES and MSR_IA32_XSS. */ if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } if (fpu_state_size_dynamic()) wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd); } /* * Given an xstate feature nr, calculate where in the xsave * buffer the state is. Callers should ensure that the buffer * is valid. */ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { u64 xcomp_bv = xsave->header.xcomp_bv; if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) { if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) return NULL; } return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr); } /* * Given the xsave area and a state inside, this function returns the * address of the state. * * This is the API that is called to get xstate address in either * standard format or compacted format of xsave area. * * Note that if there is no data for the field in the xsave buffer * this will return NULL. * * Inputs: * xstate: the thread's storage area for all FPU data * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. */ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { /* * Do we even *have* xsave state? */ if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; /* * We should not ever be requesting features that we * have not enabled. */ if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; /* * This assumes the last 'xsave*' instruction to * have requested that 'xfeature_nr' be saved. * If it did not, we might be seeing and old value * of the field in the buffer. * * This can happen because the last 'xsave' did not * request that this feature be saved (unlikely) * or because the "init optimization" caused it * to not be saved. */ if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr))) return NULL; return __raw_xsave_addr(xsave, xfeature_nr); } #ifdef CONFIG_ARCH_HAS_PKEYS /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { u32 old_pkru, new_pkru_bits = 0; int pkey_shift; /* * This check implies XSAVE support. OSPKE only gets * set if we enable XSAVE and we enable PKU in XCR0. */ if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return -EINVAL; /* * This code should only be called with valid 'pkey' * values originating from in-kernel users. Complain * if a bad value is observed. */ if (WARN_ON_ONCE(pkey >= arch_max_pkey())) return -EINVAL; /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; if (init_val & PKEY_DISABLE_WRITE) new_pkru_bits |= PKRU_WD_BIT; /* Shift the bits in to the correct place in PKRU for pkey: */ pkey_shift = pkey * PKRU_BITS_PER_PKEY; new_pkru_bits <<= pkey_shift; /* Get old PKRU and mask off any old bits in place: */ old_pkru = read_pkru(); old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); /* Write old part along with new part: */ write_pkru(old_pkru | new_pkru_bits); return 0; } #endif /* ! CONFIG_ARCH_HAS_PKEYS */ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, void *init_xstate, unsigned int size) { membuf_write(to, from_xstate ? xstate : init_xstate, size); } /** * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; struct xregs_state *xsave = &fpstate->regs.xsave; struct xstate_header header; unsigned int zerofrom; u64 mask; int i; memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; /* Mask out the feature bits depending on copy mode */ switch (copy_mode) { case XSTATE_COPY_FP: header.xfeatures &= XFEATURE_MASK_FP; break; case XSTATE_COPY_FX: header.xfeatures &= XFEATURE_MASK_FP | XFEATURE_MASK_SSE; break; case XSTATE_COPY_XSAVE: header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } /* Copy FP state up to MXCSR */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387, &xinit->i387, off_mxcsr); /* Copy MXCSR when SSE or YMM are set in the feature mask */ copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM), &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr, MXCSR_AND_FLAGS_SIZE); /* Copy the remaining FP state */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387.st_space, &xinit->i387.st_space, sizeof(xsave->i387.st_space)); /* Copy the SSE state - shared with YMM, but independently managed */ copy_feature(header.xfeatures & XFEATURE_MASK_SSE, &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space, sizeof(xsave->i387.xmm_space)); if (copy_mode != XSTATE_COPY_XSAVE) goto out; /* Zero the padding area */ membuf_zero(&to, sizeof(xsave->i387.padding)); /* Copy xsave->i387.sw_reserved */ membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved)); /* Copy the user space relevant state of @xsave->header */ membuf_write(&to, &header, sizeof(header)); zerofrom = offsetof(struct xregs_state, extended_state_area); /* * This 'mask' indicates which states to copy from fpstate. * Those extended states that are not present in fpstate are * either disabled or initialized: * * In non-compacted format, disabled features still occupy * state space but there is no state to copy from in the * compacted init_fpstate. The gap tracking will zero these * states. * * The extended features have an all zeroes init state. Thus, * remove them from 'mask' to zero those features in the user * buffer instead of retrieving them from init_fpstate. */ mask = header.xfeatures; for_each_extended_xfeature(i, mask) { /* * If there was a feature or alignment gap, zero the space * in the destination buffer. */ if (zerofrom < xstate_offsets[i]) membuf_zero(&to, xstate_offsets[i] - zerofrom); if (i == XFEATURE_PKRU) { struct pkru_state pkru = {0}; /* * PKRU is not necessarily up to date in the * XSAVE buffer. Use the provided value. */ pkru.pkru = pkru_val; membuf_write(&to, &pkru, sizeof(pkru)); } else { membuf_write(&to, __raw_xsave_addr(xsave, i), xstate_sizes[i]); } /* * Keep track of the last copied state in the non-compacted * target buffer for gap zeroing. */ zerofrom = xstate_offsets[i] + xstate_sizes[i]; } out: if (to.left) membuf_zero(&to, to.left); } /** * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @tsk: The task from which to copy the saved xstate * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, tsk->thread.fpu.fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, const void *kbuf, const void __user *ubuf) { if (kbuf) { memcpy(dst, kbuf + offset, size); } else { if (copy_from_user(dst, ubuf + offset, size)) return -EFAULT; } return 0; } /** * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate * @fpstate: The fpstate buffer to copy to * @kbuf: The UABI format buffer, if it comes from the kernel * @ubuf: The UABI format buffer, if it comes from userspace * @pkru: The location to write the PKRU value to * * Converts from the UABI format into the kernel internal hardware * dependent format. * * This function ultimately has three different callers with distinct PKRU * behavior. * 1. When called from sigreturn the PKRU register will be restored from * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to * @fpstate is sufficient to cover this case, but the caller will also * pass a pointer to the thread_struct's pkru field in @pkru and updating * it is harmless. * 2. When called from ptrace the PKRU register will be restored from the * thread_struct's pkru field. A pointer to that is passed in @pkru. * The kernel will restore it manually, so the XRSTOR behavior that resets * the PKRU register to the hardware init value (0) if the corresponding * xfeatures bit is not set is emulated here. * 3. When called from KVM the PKRU register will be restored from the vcpu's * pkru field. A pointer to that is passed in @pkru. KVM hasn't used * XRSTOR and hasn't had the PKRU resetting behavior described above. To * preserve that KVM behavior, it passes NULL for @pkru if the xfeatures * bit is not set. */ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, const void __user *ubuf, u32 *pkru) { struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int offset, size; struct xstate_header hdr; u64 mask; int i; offset = offsetof(struct xregs_state, header); if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf)) return -EFAULT; if (validate_user_xstate_header(&hdr, fpstate)) return -EINVAL; /* Validate MXCSR when any of the related features is in use */ mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; if (hdr.xfeatures & mask) { u32 mxcsr[2]; offset = offsetof(struct fxregs_state, mxcsr); if (copy_from_buffer(mxcsr, offset, sizeof(mxcsr), kbuf, ubuf)) return -EFAULT; /* Reserved bits in MXCSR must be zero. */ if (mxcsr[0] & ~mxcsr_feature_mask) return -EINVAL; /* SSE and YMM require MXCSR even when FP is not in use. */ if (!(hdr.xfeatures & XFEATURE_MASK_FP)) { xsave->i387.mxcsr = mxcsr[0]; xsave->i387.mxcsr_mask = mxcsr[1]; } } for (i = 0; i < XFEATURE_MAX; i++) { mask = BIT_ULL(i); if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, i); offset = xstate_offsets[i]; size = xstate_sizes[i]; if (copy_from_buffer(dst, offset, size, kbuf, ubuf)) return -EFAULT; } } if (hdr.xfeatures & XFEATURE_MASK_PKRU) { struct pkru_state *xpkru; xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU); *pkru = xpkru->pkru; } else { /* * KVM may pass NULL here to indicate that it does not need * PKRU updated. */ if (pkru) *pkru = 0; } /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': */ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; /* * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= hdr.xfeatures; return 0; } /* * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] * format and copy to the target thread. Used by ptrace and KVM. */ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru) { return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru); } /* * Convert from a sigreturn standard-format user-space buffer to kernel * XSAVE[S] format and copy to the target thread. This is called from the * sigreturn() and rt_sigreturn() system calls. */ int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf) { return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru); } static bool validate_independent_components(u64 mask) { u64 xchk; if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES))) return false; xchk = ~xfeatures_mask_independent(); if (WARN_ON_ONCE(!mask || mask & xchk)) return false; return true; } /** * xsaves - Save selected components to a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to save * * The @xstate buffer must be 64 byte aligned and correctly initialized as * XSAVES does not write the full xstate header. Before first use the * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer * can #GP. * * The feature mask must be a subset of the independent features. */ void xsaves(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } /** * xrstors - Restore selected components from a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to restore * * The @xstate buffer must be 64 byte aligned and correctly initialized * otherwise XRSTORS from that buffer can #GP. * * Proper usage is to restore the state which was saved with * xsaves() into @xstate. * * The feature mask must be a subset of the independent features. */ void xrstors(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } #if IS_ENABLED(CONFIG_KVM) void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature) { void *addr = get_xsave_addr(&fps->regs.xsave, xfeature); if (addr) memset(addr, 0, xstate_sizes[xfeature]); } EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component); #endif #ifdef CONFIG_X86_64 #ifdef CONFIG_X86_DEBUG_FPU /* * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask * can safely operate on the @fpstate buffer. */ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) { u64 xfd = __this_cpu_read(xfd_state); if (fpstate->xfd == xfd) return true; /* * The XFD MSR does not match fpstate->xfd. That's invalid when * the passed in fpstate is current's fpstate. */ if (fpstate->xfd == current->thread.fpu.fpstate->xfd) return false; /* * XRSTOR(S) from init_fpstate are always correct as it will just * bring all components into init state and not read from the * buffer. XSAVE(S) raises #PF after init. */ if (fpstate == &init_fpstate) return rstor; /* * XSAVE(S): clone(), fpu_swap_kvm_fpu() * XRSTORS(S): fpu_swap_kvm_fpu() */ /* * No XSAVE/XRSTOR instructions (except XSAVE itself) touch * the buffer area for XFD-disabled state components. */ mask &= ~xfd; /* * Remove features which are valid in fpstate. They * have space allocated in fpstate. */ mask &= ~fpstate->xfeatures; /* * Any remaining state components in 'mask' might be written * by XSAVE/XRSTOR. Fail validation it found. */ return !mask; } void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor)); } #endif /* CONFIG_X86_DEBUG_FPU */ static int __init xfd_update_static_branch(void) { /* * If init_fpstate.xfd has bits set then dynamic features are * available and the dynamic sizing must be enabled. */ if (init_fpstate.xfd) static_branch_enable(&__fpu_state_size_dynamic); return 0; } arch_initcall(xfd_update_static_branch) void fpstate_free(struct fpu *fpu) { if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate) vfree(fpu->fpstate); } /** * fpstate_realloc - Reallocate struct fpstate for the requested new features * * @xfeatures: A bitmap of xstate features which extend the enabled features * of that task * @ksize: The required size for the kernel buffer * @usize: The required size for user space buffers * @guest_fpu: Pointer to a guest FPU container. NULL for host allocations * * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer * terminates quickly, vfree()-induced IPIs may be a concern, but tasks * with large states are likely to live longer. * * Returns: 0 on success, -ENOMEM on allocation error. */ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, unsigned int usize, struct fpu_guest *guest_fpu) { struct fpu *fpu = ¤t->thread.fpu; struct fpstate *curfps, *newfps = NULL; unsigned int fpsize; bool in_use; fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64); newfps = vzalloc(fpsize); if (!newfps) return -ENOMEM; newfps->size = ksize; newfps->user_size = usize; newfps->is_valloc = true; /* * When a guest FPU is supplied, use @guest_fpu->fpstate * as reference independent whether it is in use or not. */ curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate; /* Determine whether @curfps is the active fpstate */ in_use = fpu->fpstate == curfps; if (guest_fpu) { newfps->is_guest = true; newfps->is_confidential = curfps->is_confidential; newfps->in_use = curfps->in_use; guest_fpu->xfeatures |= xfeatures; guest_fpu->uabi_size = usize; } fpregs_lock(); /* * If @curfps is in use, ensure that the current state is in the * registers before swapping fpstate as that might invalidate it * due to layout changes. */ if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures); if (guest_fpu) { guest_fpu->fpstate = newfps; /* If curfps is active, update the FPU fpstate pointer */ if (in_use) fpu->fpstate = newfps; } else { fpu->fpstate = newfps; } if (in_use) xfd_update_state(fpu->fpstate); fpregs_unlock(); /* Only free valloc'ed state */ if (curfps && curfps->is_valloc) vfree(curfps); return 0; } static int validate_sigaltstack(unsigned int usize) { struct task_struct *thread, *leader = current->group_leader; unsigned long framesize = get_sigframe_size(); lockdep_assert_held(¤t->sighand->siglock); /* get_sigframe_size() is based on fpu_user_cfg.max_size */ framesize -= fpu_user_cfg.max_size; framesize += usize; for_each_thread(leader, thread) { if (thread->sas_ss_size && thread->sas_ss_size < framesize) return -ENOSPC; } return 0; } static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) { /* * This deliberately does not exclude !XSAVES as we still might * decide to optionally context switch XCR0 or talk the silicon * vendors into extending XFD for the pre AMX states, especially * AVX512. */ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; unsigned int ksize, usize; u64 mask; int ret = 0; /* Check whether fully enabled */ if ((permitted & requested) == requested) return 0; /* Calculate the resulting kernel state size */ mask = permitted | requested; /* Take supervisor states into account on the host */ if (!guest) mask |= xfeatures_mask_supervisor(); ksize = xstate_calculate_size(mask, compacted); /* Calculate the resulting user state size */ mask &= XFEATURE_MASK_USER_SUPPORTED; usize = xstate_calculate_size(mask, false); if (!guest) { ret = validate_sigaltstack(usize); if (ret) return ret; } perm = guest ? &fpu->guest_perm : &fpu->perm; /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ WRITE_ONCE(perm->__state_perm, mask); /* Protected by sighand lock */ perm->__state_size = ksize; perm->__user_state_size = usize; return ret; } /* * Permissions array to map facilities with more than one component */ static const u64 xstate_prctl_req[XFEATURE_MAX] = { [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA, }; static int xstate_request_perm(unsigned long idx, bool guest) { u64 permitted, requested; int ret; if (idx >= XFEATURE_MAX) return -EINVAL; /* * Look up the facility mask which can require more than * one xstate component. */ idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req)); requested = xstate_prctl_req[idx]; if (!requested) return -EOPNOTSUPP; if ((fpu_user_cfg.max_features & requested) != requested) return -EOPNOTSUPP; /* Lockless quick check */ permitted = xstate_get_group_perm(guest); if ((permitted & requested) == requested) return 0; /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); permitted = xstate_get_group_perm(guest); /* First vCPU allocation locks the permissions. */ if (guest && (permitted & FPU_GUEST_PERM_LOCKED)) ret = -EBUSY; else ret = __xstate_request_perm(permitted, requested, guest); spin_unlock_irq(¤t->sighand->siglock); return ret; } int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu) { u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC; struct fpu_state_perm *perm; unsigned int ksize, usize; struct fpu *fpu; if (!xfd_event) { if (!guest_fpu) pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); return 0; } /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); /* If not permitted let it die */ if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) { spin_unlock_irq(¤t->sighand->siglock); return -EPERM; } fpu = ¤t->group_leader->thread.fpu; perm = guest_fpu ? &fpu->guest_perm : &fpu->perm; ksize = perm->__state_size; usize = perm->__user_state_size; /* * The feature is permitted. State size is sufficient. Dropping * the lock is safe here even if more features are added from * another task, the retrieved buffer sizes are valid for the * currently requested feature(s). */ spin_unlock_irq(¤t->sighand->siglock); /* * Try to allocate a new fpstate. If that fails there is no way * out. */ if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu)) return -EFAULT; return 0; } int xfd_enable_feature(u64 xfd_err) { return __xfd_enable_feature(xfd_err, NULL); } #else /* CONFIG_X86_64 */ static inline int xstate_request_perm(unsigned long idx, bool guest) { return -EPERM; } #endif /* !CONFIG_X86_64 */ u64 xstate_get_guest_group_perm(void) { return xstate_get_group_perm(true); } EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); /** * fpu_xstate_prctl - xstate permission operations * @option: A subfunction of arch_prctl() * @arg2: option argument * Return: 0 if successful; otherwise, an error code * * Option arguments: * * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info * ARCH_REQ_XCOMP_PERM: Facility number requested * * For facilities which require more than one XSTATE component, the request * must be the highest state component number related to that facility, * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). */ long fpu_xstate_prctl(int option, unsigned long arg2) { u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; bool guest = false; switch (option) { case ARCH_GET_XCOMP_SUPP: supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; return put_user(supported, uptr); case ARCH_GET_XCOMP_PERM: /* * Lockless snapshot as it can also change right after the * dropping the lock. */ permitted = xstate_get_host_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_GET_XCOMP_GUEST_PERM: permitted = xstate_get_guest_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_REQ_XCOMP_GUEST_PERM: guest = true; fallthrough; case ARCH_REQ_XCOMP_PERM: if (!IS_ENABLED(CONFIG_X86_64)) return -EOPNOTSUPP; return xstate_request_perm(idx, guest); default: return -EINVAL; } } #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 * use in the task. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp); long delta; if (!timestamp) { /* * Report -1 if no AVX512 usage */ delta = -1; } else { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX */ if (delta < 0) delta = LONG_MAX; delta = jiffies_to_msecs(delta); } seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta); seq_putc(m, '\n'); } /* * Report architecture specific information */ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { /* * Report AVX512 state if the processor and build option supported. */ if (cpu_feature_enabled(X86_FEATURE_AVX512F)) avx512_status(m, task); return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ |
| 20 20 20 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/profile.c * Simple profiling. Manages a direct-mapped profile hit count buffer, * with configurable resolution, support for restricting the cpus on * which profiling is done, and switching between cpu time and * schedule() calls via kernel command line parameters passed at boot. * * Scheduler profiling support, Arjan van de Ven and Ingo Molnar, * Red Hat, July 2004 * Consolidation of architecture support code for profiling, * Nadia Yvette Chambers, Oracle, July 2004 * Amortized hit count accounting via per-cpu open-addressed hashtables * to resolve timer interrupt livelocks, Nadia Yvette Chambers, * Oracle, 2004 */ #include <linux/export.h> #include <linux/profile.h> #include <linux/memblock.h> #include <linux/notifier.h> #include <linux/mm.h> #include <linux/cpumask.h> #include <linux/cpu.h> #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/sched/stat.h> #include <asm/sections.h> #include <asm/irq_regs.h> #include <asm/ptrace.h> struct profile_hit { u32 pc, hits; }; #define PROFILE_GRPSHIFT 3 #define PROFILE_GRPSZ (1 << PROFILE_GRPSHIFT) #define NR_PROFILE_HIT (PAGE_SIZE/sizeof(struct profile_hit)) #define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) static atomic_t *prof_buffer; static unsigned long prof_len; static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); static cpumask_var_t prof_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); static DEFINE_PER_CPU(int, cpu_profile_flip); static DEFINE_MUTEX(profile_flip_mutex); #endif /* CONFIG_SMP */ int profile_setup(char *str) { static const char schedstr[] = "schedule"; static const char sleepstr[] = "sleep"; static const char kvmstr[] = "kvm"; const char *select = NULL; int par; if (!strncmp(str, sleepstr, strlen(sleepstr))) { #ifdef CONFIG_SCHEDSTATS force_schedstat_enabled(); prof_on = SLEEP_PROFILING; select = sleepstr; #else pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); #endif /* CONFIG_SCHEDSTATS */ } else if (!strncmp(str, schedstr, strlen(schedstr))) { prof_on = SCHED_PROFILING; select = schedstr; } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { prof_on = KVM_PROFILING; select = kvmstr; } else if (get_option(&str, &par)) { prof_shift = clamp(par, 0, BITS_PER_LONG - 1); prof_on = CPU_PROFILING; pr_info("kernel profiling enabled (shift: %u)\n", prof_shift); } if (select) { if (str[strlen(select)] == ',') str += strlen(select) + 1; if (get_option(&str, &par)) prof_shift = clamp(par, 0, BITS_PER_LONG - 1); pr_info("kernel %s profiling enabled (shift: %u)\n", select, prof_shift); } return 1; } __setup("profile=", profile_setup); int __ref profile_init(void) { int buffer_bytes; if (!prof_on) return 0; /* only text is profiled */ prof_len = (_etext - _stext) >> prof_shift; if (!prof_len) { pr_warn("profiling shift: %u too large\n", prof_shift); prof_on = 0; return -EINVAL; } buffer_bytes = prof_len*sizeof(atomic_t); if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) return -ENOMEM; cpumask_copy(prof_cpu_mask, cpu_possible_mask); prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = vzalloc(buffer_bytes); if (prof_buffer) return 0; free_cpumask_var(prof_cpu_mask); return -ENOMEM; } #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending * profile hits. read_profile() IPI's all cpus to request them * to flip buffers and flushes their contents to prof_buffer itself. * Flip requests are serialized by the profile_flip_mutex. The sole * use of having a second hashtable is for avoiding cacheline * contention that would otherwise happen during flushes of pending * profile hits required for the accuracy of reported profile hits * and so resurrect the interrupt livelock issue. * * The open-addressed hashtables are indexed by profile buffer slot * and hold the number of pending hits to that profile buffer slot on * a cpu in an entry. When the hashtable overflows, all pending hits * are accounted to their corresponding profile buffer slots with * atomic_add() and the hashtable emptied. As numerous pending hits * may be accounted to a profile buffer slot in a hashtable entry, * this amortizes a number of atomic profile buffer increments likely * to be far larger than the number of entries in the hashtable, * particularly given that the number of distinct profile buffer * positions to which hits are accounted during short intervals (e.g. * several seconds) is usually very small. Exclusion from buffer * flipping is provided by interrupt disablement (note that for * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from * process context). * The hash function is meant to be lightweight as opposed to strong, * and was vaguely inspired by ppc64 firmware-supported inverted * pagetable hash functions, but uses a full hashtable full of finite * collision chains, not just pairs of them. * * -- nyc */ static void __profile_flip_buffers(void *unused) { int cpu = smp_processor_id(); per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); } static void profile_flip_buffers(void) { int i, j, cpu; mutex_lock(&profile_flip_mutex); j = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; for (i = 0; i < NR_PROFILE_HIT; ++i) { if (!hits[i].hits) { if (hits[i].pc) hits[i].pc = 0; continue; } atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); hits[i].hits = hits[i].pc = 0; } } mutex_unlock(&profile_flip_mutex); } static void profile_discard_flip_buffers(void) { int i, cpu; mutex_lock(&profile_flip_mutex); i = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); } mutex_unlock(&profile_flip_mutex); } static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long primary, secondary, flags, pc = (unsigned long)__pc; int i, j, cpu; struct profile_hit *hits; pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; cpu = get_cpu(); hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; if (!hits) { put_cpu(); return; } /* * We buffer the global profiler buffer into a per-CPU * queue and thus reduce the number of global (and possibly * NUMA-alien) accesses. The write-queue is self-coalescing: */ local_irq_save(flags); do { for (j = 0; j < PROFILE_GRPSZ; ++j) { if (hits[i + j].pc == pc) { hits[i + j].hits += nr_hits; goto out; } else if (!hits[i + j].hits) { hits[i + j].pc = pc; hits[i + j].hits = nr_hits; goto out; } } i = (i + secondary) & (NR_PROFILE_HIT - 1); } while (i != primary); /* * Add the current hit(s) and flush the write-queue out * to the global buffer: */ atomic_add(nr_hits, &prof_buffer[pc]); for (i = 0; i < NR_PROFILE_HIT; ++i) { atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); hits[i].pc = hits[i].hits = 0; } out: local_irq_restore(flags); put_cpu(); } static int profile_dead_cpu(unsigned int cpu) { struct page *page; int i; if (cpumask_available(prof_cpu_mask)) cpumask_clear_cpu(cpu, prof_cpu_mask); for (i = 0; i < 2; i++) { if (per_cpu(cpu_profile_hits, cpu)[i]) { page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); per_cpu(cpu_profile_hits, cpu)[i] = NULL; __free_page(page); } } return 0; } static int profile_prepare_cpu(unsigned int cpu) { int i, node = cpu_to_mem(cpu); struct page *page; per_cpu(cpu_profile_flip, cpu) = 0; for (i = 0; i < 2; i++) { if (per_cpu(cpu_profile_hits, cpu)[i]) continue; page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) { profile_dead_cpu(cpu); return -ENOMEM; } per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); } return 0; } static int profile_online_cpu(unsigned int cpu) { if (cpumask_available(prof_cpu_mask)) cpumask_set_cpu(cpu, prof_cpu_mask); return 0; } #else /* !CONFIG_SMP */ #define profile_flip_buffers() do { } while (0) #define profile_discard_flip_buffers() do { } while (0) static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); } #endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { if (prof_on != type || !prof_buffer) return; do_profile_hits(type, __pc, nr_hits); } EXPORT_SYMBOL_GPL(profile_hits); void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); } #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uaccess.h> static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) { seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); return 0; } static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) { return single_open(file, prof_cpu_mask_proc_show, NULL); } static ssize_t prof_cpu_mask_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { cpumask_var_t new_value; int err; if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) return -ENOMEM; err = cpumask_parse_user(buffer, count, new_value); if (!err) { cpumask_copy(prof_cpu_mask, new_value); err = count; } free_cpumask_var(new_value); return err; } static const struct proc_ops prof_cpu_mask_proc_ops = { .proc_open = prof_cpu_mask_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, .proc_write = prof_cpu_mask_proc_write, }; void create_prof_cpu_mask(void) { /* create /proc/irq/prof_cpu_mask */ proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); } /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile * buffer. Use of the program readprofile is recommended in order to * get meaningful info out of these data. */ static ssize_t read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long p = *ppos; ssize_t read; char *pnt; unsigned long sample_step = 1UL << prof_shift; profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) count = (prof_len+1)*sizeof(unsigned int) - p; read = 0; while (p < sizeof(unsigned int) && count > 0) { if (put_user(*((char *)(&sample_step)+p), buf)) return -EFAULT; buf++; p++; count--; read++; } pnt = (char *)prof_buffer + p - sizeof(atomic_t); if (copy_to_user(buf, (void *)pnt, count)) return -EFAULT; read += count; *ppos += read; return read; } /* default is to not implement this call */ int __weak setup_profiling_timer(unsigned mult) { return -EINVAL; } /* * Writing to /proc/profile resets the counters * * Writing a 'profiling multiplier' value into it also re-sets the profiling * interrupt frequency, on architectures that support this. */ static ssize_t write_profile(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { #ifdef CONFIG_SMP if (count == sizeof(int)) { unsigned int multiplier; if (copy_from_user(&multiplier, buf, sizeof(int))) return -EFAULT; if (setup_profiling_timer(multiplier)) return -EINVAL; } #endif profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } static const struct proc_ops profile_proc_ops = { .proc_read = read_profile, .proc_write = write_profile, .proc_lseek = default_llseek, }; int __ref create_proc_profile(void) { struct proc_dir_entry *entry; #ifdef CONFIG_SMP enum cpuhp_state online_state; #endif int err = 0; if (!prof_on) return 0; #ifdef CONFIG_SMP err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", profile_prepare_cpu, profile_dead_cpu); if (err) return err; err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", profile_online_cpu, NULL); if (err < 0) goto err_state_prep; online_state = err; err = 0; #endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); if (!entry) goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); return err; err_state_onl: #ifdef CONFIG_SMP cpuhp_remove_state(online_state); err_state_prep: cpuhp_remove_state(CPUHP_PROFILE_PREPARE); #endif return err; } subsys_initcall(create_proc_profile); #endif /* CONFIG_PROC_FS */ |
| 456 456 137 137 137 137 137 137 137 137 137 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/dd.c - The core device/driver interactions. * * This file contains the (sometimes tricky) code that controls the * interactions between devices and drivers, which primarily includes * driver binding and unbinding. * * All of this code used to exist in drivers/base/bus.c, but was * relocated to here in the name of compartmentalization (since it wasn't * strictly code just for the 'struct bus_type'. * * Copyright (c) 2002-5 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007-2009 Novell Inc. */ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/delay.h> #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> #include <linux/pinctrl/devinfo.h> #include <linux/slab.h> #include "base.h" #include "power/power.h" /* * Deferred Probe infrastructure. * * Sometimes driver probe order matters, but the kernel doesn't always have * dependency information which means some drivers will get probed before a * resource it depends on is available. For example, an SDHCI driver may * first need a GPIO line from an i2c GPIO controller before it can be * initialized. If a required resource is not available yet, a driver can * request probing to be deferred by returning -EPROBE_DEFER from its probe hook * * Deferred probe maintains two lists of devices, a pending list and an active * list. A driver returning -EPROBE_DEFER causes the device to be added to the * pending list. A successful driver probe will trigger moving all devices * from the pending to the active list so that the workqueue will eventually * retry them. * * The deferred_probe_mutex must be held any time the deferred_probe_*_list * of the (struct device*)->p->deferred_probe pointers are manipulated */ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static atomic_t deferred_trigger_count = ATOMIC_INIT(0); static bool initcalls_done; /* Save the async probe drivers' name from kernel cmdline */ #define ASYNC_DRV_NAMES_MAX_LEN 256 static char async_probe_drv_names[ASYNC_DRV_NAMES_MAX_LEN]; static bool async_probe_default; /* * In some cases, like suspend to RAM or hibernation, It might be reasonable * to prohibit probing of devices as it could be unsafe. * Once defer_all_probes is true all drivers probes will be forcibly deferred. */ static bool defer_all_probes; static void __device_set_deferred_probe_reason(const struct device *dev, char *reason) { kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = reason; } /* * deferred_probe_work_func() - Retry probing devices in the active list. */ static void deferred_probe_work_func(struct work_struct *work) { struct device *dev; struct device_private *private; /* * This block processes every device in the deferred 'active' list. * Each device is removed from the active list and passed to * bus_probe_device() to re-attempt the probe. The loop continues * until every device in the active list is removed and retried. * * Note: Once the device is removed from the list and the mutex is * released, it is possible for the device get freed by another thread * and cause a illegal pointer dereference. This code uses * get/put_device() to ensure the device structure cannot disappear * from under our feet. */ mutex_lock(&deferred_probe_mutex); while (!list_empty(&deferred_probe_active_list)) { private = list_first_entry(&deferred_probe_active_list, typeof(*dev->p), deferred_probe); dev = private->device; list_del_init(&private->deferred_probe); get_device(dev); __device_set_deferred_probe_reason(dev, NULL); /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list */ mutex_unlock(&deferred_probe_mutex); /* * Force the device to the end of the dpm_list since * the PM code assumes that the order we add things to * the list is a good order for suspend but deferred * probe makes that very unsafe. */ device_pm_move_to_tail(dev); dev_dbg(dev, "Retrying from deferred list\n"); bus_probe_device(dev); mutex_lock(&deferred_probe_mutex); put_device(dev); } mutex_unlock(&deferred_probe_mutex); } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); void driver_deferred_probe_add(struct device *dev) { if (!dev->can_match) return; mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Added to deferred list\n"); list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list); } mutex_unlock(&deferred_probe_mutex); } void driver_deferred_probe_del(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (!list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Removed from deferred list\n"); list_del_init(&dev->p->deferred_probe); __device_set_deferred_probe_reason(dev, NULL); } mutex_unlock(&deferred_probe_mutex); } static bool driver_deferred_probe_enable; /** * driver_deferred_probe_trigger() - Kick off re-probing deferred devices * * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. * * Note, there is a race condition in multi-threaded probe. In the case where * more than one device is probing at the same time, it is possible for one * probe to complete successfully while another is about to defer. If the second * depends on the first, then it will get put on the pending list after the * trigger event has already occurred and will be stuck there. * * The atomic 'deferred_trigger_count' is used to determine if a successful * trigger has occurred in the midst of probing a driver. If the trigger count * changes in the midst of a probe, then deferred processing should be triggered * again. */ void driver_deferred_probe_trigger(void) { if (!driver_deferred_probe_enable) return; /* * A successful probe means that all the devices in the pending list * should be triggered to be reprobed. Move all the deferred devices * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); /* * Kick the re-probe thread. It may already be scheduled, but it is * safe to kick it again. */ queue_work(system_unbound_wq, &deferred_probe_work); } /** * device_block_probing() - Block/defer device's probes * * It will disable probing of devices and defer their probes instead. */ void device_block_probing(void) { defer_all_probes = true; /* sync with probes to avoid races. */ wait_for_device_probe(); } /** * device_unblock_probing() - Unblock/enable device's probes * * It will restore normal behavior and trigger re-probing of deferred * devices. */ void device_unblock_probing(void) { defer_all_probes = false; driver_deferred_probe_trigger(); } /** * device_set_deferred_probe_reason() - Set defer probe reason message for device * @dev: the pointer to the struct device * @vaf: the pointer to va_format structure with message */ void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf) { const char *drv = dev_driver_string(dev); char *reason; mutex_lock(&deferred_probe_mutex); reason = kasprintf(GFP_KERNEL, "%s: %pV", drv, vaf); __device_set_deferred_probe_reason(dev, reason); mutex_unlock(&deferred_probe_mutex); } /* * deferred_devs_show() - Show the devices in the deferred probe pending list. */ static int deferred_devs_show(struct seq_file *s, void *data) { struct device_private *curr; mutex_lock(&deferred_probe_mutex); list_for_each_entry(curr, &deferred_probe_pending_list, deferred_probe) seq_printf(s, "%s\t%s", dev_name(curr->device), curr->device->p->deferred_probe_reason ?: "\n"); mutex_unlock(&deferred_probe_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(deferred_devs); #ifdef CONFIG_MODULES static int driver_deferred_probe_timeout = 10; #else static int driver_deferred_probe_timeout; #endif static int __init deferred_probe_timeout_setup(char *str) { int timeout; if (!kstrtoint(str, 10, &timeout)) driver_deferred_probe_timeout = timeout; return 1; } __setup("deferred_probe_timeout=", deferred_probe_timeout_setup); /** * driver_deferred_probe_check_state() - Check deferred probe state * @dev: device to check * * Return: * * -ENODEV if initcalls have completed and modules are disabled. * * -ETIMEDOUT if the deferred probe timeout was set and has expired * and modules are enabled. * * -EPROBE_DEFER in other cases. * * Drivers or subsystems can opt-in to calling this function instead of directly * returning -EPROBE_DEFER. */ int driver_deferred_probe_check_state(struct device *dev) { if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) { dev_warn(dev, "ignoring dependency for device, assuming no driver\n"); return -ENODEV; } if (!driver_deferred_probe_timeout && initcalls_done) { dev_warn(dev, "deferred probe timeout, ignoring dependency\n"); return -ETIMEDOUT; } return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { struct device_private *p; fw_devlink_drivers_done(); driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); mutex_lock(&deferred_probe_mutex); list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) dev_info(p->device, "deferred probe pending: %s", p->deferred_probe_reason ?: "(reason unknown)\n"); mutex_unlock(&deferred_probe_mutex); fw_devlink_probing_done(); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); void deferred_probe_extend_timeout(void) { /* * If the work hasn't been queued yet or if the work expired, don't * start a new one. */ if (cancel_delayed_work(&deferred_probe_timeout_work)) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); pr_debug("Extended deferred probe timeout by %d secs\n", driver_deferred_probe_timeout); } } /** * deferred_probe_initcall() - Enable probing of deferred devices * * We don't want to get in the way when the bulk of drivers are getting probed. * Instead, this initcall makes sure that deferred probing is delayed until * late_initcall time. */ static int deferred_probe_initcall(void) { debugfs_create_file("devices_deferred", 0444, NULL, NULL, &deferred_devs_fops); driver_deferred_probe_enable = true; driver_deferred_probe_trigger(); /* Sort as many dependencies as possible before exiting initcalls */ flush_work(&deferred_probe_work); initcalls_done = true; if (!IS_ENABLED(CONFIG_MODULES)) fw_devlink_drivers_done(); /* * Trigger deferred probe again, this time we won't defer anything * that is optional */ driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); if (driver_deferred_probe_timeout > 0) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); } if (!IS_ENABLED(CONFIG_MODULES)) fw_devlink_probing_done(); return 0; } late_initcall(deferred_probe_initcall); static void __exit deferred_probe_exit(void) { debugfs_lookup_and_remove("devices_deferred", NULL); } __exitcall(deferred_probe_exit); /** * device_is_bound() - Check if device is bound to a driver * @dev: device to check * * Returns true if passed device has already finished probing successfully * against a driver. * * This function must be called with the device lock held. */ bool device_is_bound(struct device *dev) { return dev->p && klist_node_attached(&dev->p->knode_driver); } static void driver_bound(struct device *dev) { if (device_is_bound(dev)) { pr_warn("%s: device %s already bound\n", __func__, kobject_name(&dev->kobj)); return; } pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->driver->name, __func__, dev_name(dev)); klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices); device_links_driver_bound(dev); device_pm_check_callbacks(dev); /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices */ driver_deferred_probe_del(dev); driver_deferred_probe_trigger(); bus_notify(dev, BUS_NOTIFY_BOUND_DRIVER); kobject_uevent(&dev->kobj, KOBJ_BIND); } static ssize_t coredump_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { device_lock(dev); dev->driver->coredump(dev); device_unlock(dev); return count; } static DEVICE_ATTR_WO(coredump); static int driver_sysfs_add(struct device *dev) { int ret; bus_notify(dev, BUS_NOTIFY_BIND_DRIVER); ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj, kobject_name(&dev->kobj)); if (ret) goto fail; ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj, "driver"); if (ret) goto rm_dev; if (!IS_ENABLED(CONFIG_DEV_COREDUMP) || !dev->driver->coredump) return 0; ret = device_create_file(dev, &dev_attr_coredump); if (!ret) return 0; sysfs_remove_link(&dev->kobj, "driver"); rm_dev: sysfs_remove_link(&dev->driver->p->kobj, kobject_name(&dev->kobj)); fail: return ret; } static void driver_sysfs_remove(struct device *dev) { struct device_driver *drv = dev->driver; if (drv) { if (drv->coredump) device_remove_file(dev, &dev_attr_coredump); sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj)); sysfs_remove_link(&dev->kobj, "driver"); } } /** * device_bind_driver - bind a driver to one device. * @dev: device. * * Allow manual attachment of a driver to a device. * Caller must have already set @dev->driver. * * Note that this does not modify the bus reference count. * Please verify that is accounted for before calling this. * (It is ok to call with no other effort from a driver's probe() method.) * * This function must be called with the device lock held. * * Callers should prefer to use device_driver_attach() instead. */ int device_bind_driver(struct device *dev) { int ret; ret = driver_sysfs_add(dev); if (!ret) { device_links_force_bind(dev); driver_bound(dev); } else bus_notify(dev, BUS_NOTIFY_DRIVER_NOT_BOUND); return ret; } EXPORT_SYMBOL_GPL(device_bind_driver); static atomic_t probe_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static ssize_t state_synced_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ret = 0; if (strcmp("1", buf)) return -EINVAL; device_lock(dev); if (!dev->state_synced) { dev->state_synced = true; dev_sync_state(dev); } else { ret = -EINVAL; } device_unlock(dev); return ret ? ret : count; } static ssize_t state_synced_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = dev->state_synced; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RW(state_synced); static void device_unbind_cleanup(struct device *dev) { devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); } static void device_remove(struct device *dev) { device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, dev->driver->dev_groups); if (dev->bus && dev->bus->remove) dev->bus->remove(dev); else if (dev->driver->remove) dev->driver->remove(dev); } static int call_driver_probe(struct device *dev, struct device_driver *drv) { int ret = 0; if (dev->bus->probe) ret = dev->bus->probe(dev); else if (drv->probe) ret = drv->probe(dev); switch (ret) { case 0: break; case -EPROBE_DEFER: /* Driver requested deferred probing */ dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name); break; case -ENODEV: case -ENXIO: pr_debug("%s: probe of %s rejects match %d\n", drv->name, dev_name(dev), ret); break; default: /* driver matched but the probe failed */ pr_warn("%s: probe of %s failed with error %d\n", drv->name, dev_name(dev), ret); break; } return ret; } static int really_probe(struct device *dev, struct device_driver *drv) { bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) && !drv->suppress_bind_attrs; int ret, link_ret; if (defer_all_probes) { /* * Value of defer_all_probes can be set only by * device_block_probing() which, in turn, will call * wait_for_device_probe() right after that to avoid any races. */ dev_dbg(dev, "Driver %s force probe deferral\n", drv->name); return -EPROBE_DEFER; } link_ret = device_links_check_suppliers(dev); if (link_ret == -EPROBE_DEFER) return link_ret; pr_debug("bus: '%s': %s: probing driver %s with device %s\n", drv->bus->name, __func__, drv->name, dev_name(dev)); if (!list_empty(&dev->devres_head)) { dev_crit(dev, "Resources present before probing\n"); ret = -EBUSY; goto done; } re_probe: dev->driver = drv; /* If using pinctrl, bind pins now before probing */ ret = pinctrl_bind_pins(dev); if (ret) goto pinctrl_bind_failed; if (dev->bus->dma_configure) { ret = dev->bus->dma_configure(dev); if (ret) goto pinctrl_bind_failed; } ret = driver_sysfs_add(dev); if (ret) { pr_err("%s: driver_sysfs_add(%s) failed\n", __func__, dev_name(dev)); goto sysfs_failed; } if (dev->pm_domain && dev->pm_domain->activate) { ret = dev->pm_domain->activate(dev); if (ret) goto probe_failed; } ret = call_driver_probe(dev, drv); if (ret) { /* * If fw_devlink_best_effort is active (denoted by -EAGAIN), the * device might actually probe properly once some of its missing * suppliers have probed. So, treat this as if the driver * returned -EPROBE_DEFER. */ if (link_ret == -EAGAIN) ret = -EPROBE_DEFER; /* * Return probe errors as positive values so that the callers * can distinguish them from other errors. */ ret = -ret; goto probe_failed; } ret = device_add_groups(dev, drv->dev_groups); if (ret) { dev_err(dev, "device_add_groups() failed\n"); goto dev_groups_failed; } if (dev_has_sync_state(dev)) { ret = device_create_file(dev, &dev_attr_state_synced); if (ret) { dev_err(dev, "state_synced sysfs add failed\n"); goto dev_sysfs_state_synced_failed; } } if (test_remove) { test_remove = false; device_remove(dev); driver_sysfs_remove(dev); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); device_unbind_cleanup(dev); goto re_probe; } pinctrl_init_done(dev); if (dev->pm_domain && dev->pm_domain->sync) dev->pm_domain->sync(dev); driver_bound(dev); pr_debug("bus: '%s': %s: bound device %s to driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); goto done; dev_sysfs_state_synced_failed: dev_groups_failed: device_remove(dev); probe_failed: driver_sysfs_remove(dev); sysfs_failed: bus_notify(dev, BUS_NOTIFY_DRIVER_NOT_BOUND); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); pinctrl_bind_failed: device_links_no_driver(dev); device_unbind_cleanup(dev); done: return ret; } /* * For initcall_debug, show the driver probe time. */ static int really_probe_debug(struct device *dev, struct device_driver *drv) { ktime_t calltime, rettime; int ret; calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); /* * Don't change this to pr_debug() because that requires * CONFIG_DYNAMIC_DEBUG and we want a simple 'initcall_debug' on the * kernel commandline to print this all the time at the debug level. */ printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } /** * driver_probe_done * Determine if the probe sequence is finished or not. * * Should somehow figure out how to use a semaphore, not an atomic variable... */ bool __init driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); return !local_probe_count; } /** * wait_for_device_probe * Wait for device probing to be completed. */ void wait_for_device_probe(void) { /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); static int __driver_probe_device(struct device_driver *drv, struct device *dev) { int ret = 0; if (dev->p->dead || !device_is_registered(dev)) return -ENODEV; if (dev->driver) return -EBUSY; dev->can_match = true; pr_debug("bus: '%s': %s: matched device %s with driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); pm_runtime_get_suppliers(dev); if (dev->parent) pm_runtime_get_sync(dev->parent); pm_runtime_barrier(dev); if (initcall_debug) ret = really_probe_debug(dev, drv); else ret = really_probe(dev, drv); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); pm_runtime_put_suppliers(dev); return ret; } /** * driver_probe_device - attempt to bind device & driver together * @drv: driver to bind a device to * @dev: device to try to bind to the driver * * This function returns -ENODEV if the device is not registered, -EBUSY if it * already has a driver, 0 if the device is bound successfully and a positive * (inverted) error code for failures from the ->probe method. * * This function must be called with @dev lock held. When called for a * USB interface, @dev->parent lock must be held as well. * * If the device has a parent, runtime-resume the parent before driver probing. */ static int driver_probe_device(struct device_driver *drv, struct device *dev) { int trigger_count = atomic_read(&deferred_trigger_count); int ret; atomic_inc(&probe_count); ret = __driver_probe_device(drv, dev); if (ret == -EPROBE_DEFER || ret == EPROBE_DEFER) { driver_deferred_probe_add(dev); /* * Did a trigger occur while probing? Need to re-trigger if yes */ if (trigger_count != atomic_read(&deferred_trigger_count) && !defer_all_probes) driver_deferred_probe_trigger(); } atomic_dec(&probe_count); wake_up_all(&probe_waitqueue); return ret; } static inline bool cmdline_requested_async_probing(const char *drv_name) { bool async_drv; async_drv = parse_option_str(async_probe_drv_names, drv_name); return (async_probe_default != async_drv); } /* The option format is "driver_async_probe=drv_name1,drv_name2,..." */ static int __init save_async_options(char *buf) { if (strlen(buf) >= ASYNC_DRV_NAMES_MAX_LEN) pr_warn("Too long list of driver names for 'driver_async_probe'!\n"); strscpy(async_probe_drv_names, buf, ASYNC_DRV_NAMES_MAX_LEN); async_probe_default = parse_option_str(async_probe_drv_names, "*"); return 1; } __setup("driver_async_probe=", save_async_options); static bool driver_allows_async_probing(struct device_driver *drv) { switch (drv->probe_type) { case PROBE_PREFER_ASYNCHRONOUS: return true; case PROBE_FORCE_SYNCHRONOUS: return false; default: if (cmdline_requested_async_probing(drv->name)) return true; if (module_requested_async_probing(drv->owner)) return true; return false; } } struct device_attach_data { struct device *dev; /* * Indicates whether we are considering asynchronous probing or * not. Only initial binding after device or driver registration * (including deferral processing) may be done asynchronously, the * rest is always synchronous, as we expect it is being done by * request from userspace. */ bool check_async; /* * Indicates if we are binding synchronous or asynchronous drivers. * When asynchronous probing is enabled we'll execute 2 passes * over drivers: first pass doing synchronous probing and second * doing asynchronous probing (if synchronous did not succeed - * most likely because there was no driver requiring synchronous * probing - and we found asynchronous driver during first pass). * The 2 passes are done because we can't shoot asynchronous * probe for given device and driver from bus_for_each_drv() since * driver pointer is not guaranteed to stay valid once * bus_for_each_drv() iterates to the next driver on the bus. */ bool want_async; /* * We'll set have_async to 'true' if, while scanning for matching * driver, we'll encounter one that requests asynchronous probing. */ bool have_async; }; static int __device_attach_driver(struct device_driver *drv, void *_data) { struct device_attach_data *data = _data; struct device *dev = data->dev; bool async_allowed; int ret; ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Device can't match with a driver right now, so don't attempt * to match or bind with other drivers on the bus. */ return ret; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); return ret; } /* ret > 0 means positive match */ async_allowed = driver_allows_async_probing(drv); if (async_allowed) data->have_async = true; if (data->check_async && async_allowed != data->want_async) return 0; /* * Ignore errors returned by ->probe so that the next driver can try * its luck. */ ret = driver_probe_device(drv, dev); if (ret < 0) return ret; return ret == 0; } static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_attach_data data = { .dev = dev, .check_async = true, .want_async = true, }; device_lock(dev); /* * Check if device has already been removed or claimed. This may * happen with driver loading, device discovery/registration, * and deferred probe processing happens all at once with * multiple threads. */ if (dev->p->dead || dev->driver) goto out_unlock; if (dev->parent) pm_runtime_get_sync(dev->parent); bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); dev_dbg(dev, "async probe completed\n"); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); out_unlock: device_unlock(dev); put_device(dev); } static int __device_attach(struct device *dev, bool allow_async) { int ret = 0; bool async = false; device_lock(dev); if (dev->p->dead) { goto out_unlock; } else if (dev->driver) { if (device_is_bound(dev)) { ret = 1; goto out_unlock; } ret = device_bind_driver(dev); if (ret == 0) ret = 1; else { dev->driver = NULL; ret = 0; } } else { struct device_attach_data data = { .dev = dev, .check_async = allow_async, .want_async = false, }; if (dev->parent) pm_runtime_get_sync(dev->parent); ret = bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); if (!ret && allow_async && data.have_async) { /* * If we could not find appropriate driver * synchronously and we are allowed to do * async probes and there are drivers that * want to probe asynchronously, we'll * try them. */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); async = true; } else { pm_request_idle(dev); } if (dev->parent) pm_runtime_put(dev->parent); } out_unlock: device_unlock(dev); if (async) async_schedule_dev(__device_attach_async_helper, dev); return ret; } /** * device_attach - try to attach device to a driver. * @dev: device. * * Walk the list of drivers that the bus has and call * driver_probe_device() for each pair. If a compatible * pair is found, break out and return. * * Returns 1 if the device was bound to a driver; * 0 if no matching driver was found; * -ENODEV if the device is not registered. * * When called for a USB interface, @dev->parent lock must be held. */ int device_attach(struct device *dev) { return __device_attach(dev, false); } EXPORT_SYMBOL_GPL(device_attach); void device_initial_probe(struct device *dev) { __device_attach(dev, true); } /* * __device_driver_lock - acquire locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will take the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a USB * interface, @parent lock will be held as well. */ static void __device_driver_lock(struct device *dev, struct device *parent) { if (parent && dev->bus->need_parent_lock) device_lock(parent); device_lock(dev); } /* * __device_driver_unlock - release locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will release the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a * USB interface, @parent lock will be released as well. */ static void __device_driver_unlock(struct device *dev, struct device *parent) { device_unlock(dev); if (parent && dev->bus->need_parent_lock) device_unlock(parent); } /** * device_driver_attach - attach a specific driver to a specific device * @drv: Driver to attach * @dev: Device to attach it to * * Manually attach driver to a device. Will acquire both @dev lock and * @dev->parent lock if needed. Returns 0 on success, -ERR on failure. */ int device_driver_attach(struct device_driver *drv, struct device *dev) { int ret; __device_driver_lock(dev, dev->parent); ret = __driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); /* also return probe errors as normal negative errnos */ if (ret > 0) ret = -ret; if (ret == -EPROBE_DEFER) return -EAGAIN; return ret; } EXPORT_SYMBOL_GPL(device_driver_attach); static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_driver *drv; int ret; __device_driver_lock(dev, dev->parent); drv = dev->p->async_driver; dev->p->async_driver = NULL; ret = driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret); put_device(dev); } static int __driver_attach(struct device *dev, void *data) { struct device_driver *drv = data; bool async = false; int ret; /* * Lock device and try to bind to it. We drop the error * here and always return 0, because we need to keep trying * to bind to devices and some drivers will return an error * simply if it didn't support the device. * * driver_probe_device() will spit a warning if there * is an error. */ ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } /* ret > 0 means positive match */ if (driver_allows_async_probing(drv)) { /* * Instead of probing the device synchronously we will * probe it asynchronously to allow for more parallelism. * * We only take the device lock here in order to guarantee * that the dev->driver and async_driver fields are protected */ dev_dbg(dev, "probing driver %s asynchronously\n", drv->name); device_lock(dev); if (!dev->driver && !dev->p->async_driver) { get_device(dev); dev->p->async_driver = drv; async = true; } device_unlock(dev); if (async) async_schedule_dev(__driver_attach_async_helper, dev); return 0; } __device_driver_lock(dev, dev->parent); driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); return 0; } /** * driver_attach - try to bind driver to devices. * @drv: driver. * * Walk the list of devices that the bus has on it and try to * match the driver with each one. If driver_probe_device() * returns 0 and the @dev->driver is set, we've found a * compatible pair. */ int driver_attach(struct device_driver *drv) { return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach); } EXPORT_SYMBOL_GPL(driver_attach); /* * __device_release_driver() must be called with @dev lock held. * When called for a USB interface, @dev->parent lock must be held as well. */ static void __device_release_driver(struct device *dev, struct device *parent) { struct device_driver *drv; drv = dev->driver; if (drv) { pm_runtime_get_sync(dev); while (device_links_busy(dev)) { __device_driver_unlock(dev, parent); device_links_unbind_consumers(dev); __device_driver_lock(dev, parent); /* * A concurrent invocation of the same function might * have released the driver successfully while this one * was waiting, so check for that. */ if (dev->driver != drv) { pm_runtime_put(dev); return; } } driver_sysfs_remove(dev); bus_notify(dev, BUS_NOTIFY_UNBIND_DRIVER); pm_runtime_put_sync(dev); device_remove(dev); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); device_unbind_cleanup(dev); device_links_driver_cleanup(dev); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); bus_notify(dev, BUS_NOTIFY_UNBOUND_DRIVER); kobject_uevent(&dev->kobj, KOBJ_UNBIND); } } void device_release_driver_internal(struct device *dev, struct device_driver *drv, struct device *parent) { __device_driver_lock(dev, parent); if (!drv || drv == dev->driver) __device_release_driver(dev, parent); __device_driver_unlock(dev, parent); } /** * device_release_driver - manually detach device from driver. * @dev: device. * * Manually detach device from driver. * When called for a USB interface, @dev->parent lock must be held. * * If this function is to be called with @dev->parent lock held, ensure that * the device's consumers are unbound in advance or that their locks can be * acquired under the @dev->parent lock. */ void device_release_driver(struct device *dev) { /* * If anyone calls device_release_driver() recursively from * within their ->remove callback for the same device, they * will deadlock right here. */ device_release_driver_internal(dev, NULL, NULL); } EXPORT_SYMBOL_GPL(device_release_driver); /** * device_driver_detach - detach driver from a specific device * @dev: device to detach driver from * * Detach driver from device. Will acquire both @dev lock and @dev->parent * lock if needed. */ void device_driver_detach(struct device *dev) { device_release_driver_internal(dev, NULL, dev->parent); } /** * driver_detach - detach driver from all devices it controls. * @drv: driver. */ void driver_detach(struct device_driver *drv) { struct device_private *dev_prv; struct device *dev; if (driver_allows_async_probing(drv)) async_synchronize_full(); for (;;) { spin_lock(&drv->p->klist_devices.k_lock); if (list_empty(&drv->p->klist_devices.k_list)) { spin_unlock(&drv->p->klist_devices.k_lock); break; } dev_prv = list_last_entry(&drv->p->klist_devices.k_list, struct device_private, knode_driver.n_node); dev = dev_prv->device; get_device(dev); spin_unlock(&drv->p->klist_devices.k_lock); device_release_driver_internal(dev, drv, dev->parent); put_device(dev); } } |
| 703 703 703 703 1 5 703 703 703 703 703 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Glue code for the SHA1 Secure Hash Algorithm assembler implementations * using SSSE3, AVX, AVX2, and SHA-NI instructions. * * This file is based on sha1_generic.c * * Copyright (c) Alan Smithee. * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> * Copyright (c) Jean-Francois Dive <jef@linuxbe.org> * Copyright (c) Mathias Krause <minipli@googlemail.com> * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <crypto/sha1.h> #include <crypto/sha1_base.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> static const struct x86_cpu_id module_cpu_ids[] = { #ifdef CONFIG_AS_SHA1_NI X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL), #endif X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); static int sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *sha1_xform) { struct sha1_state *sctx = shash_desc_ctx(desc); if (!crypto_simd_usable() || (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE) return crypto_sha1_update(desc, data, len); /* * Make sure struct sha1_state begins directly with the SHA1 * 160-bit internal state, as this is what the asm functions expect. */ BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0); kernel_fpu_begin(); sha1_base_do_update(desc, data, len, sha1_xform); kernel_fpu_end(); return 0; } static int sha1_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out, sha1_block_fn *sha1_xform) { if (!crypto_simd_usable()) return crypto_sha1_finup(desc, data, len, out); kernel_fpu_begin(); if (len) sha1_base_do_update(desc, data, len, sha1_xform); sha1_base_do_finalize(desc, sha1_xform); kernel_fpu_end(); return sha1_base_finish(desc, out); } asmlinkage void sha1_transform_ssse3(struct sha1_state *state, const u8 *data, int blocks); static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return sha1_update(desc, data, len, sha1_transform_ssse3); } static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, unsigned in |