| 1 1 1 4 2 4 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/ethtool_netlink.h> #include "netlink.h" #include "common.h" struct plca_req_info { struct ethnl_req_info base; }; struct plca_reply_data { struct ethnl_reply_data base; struct phy_plca_cfg plca_cfg; struct phy_plca_status plca_st; }; // Helpers ------------------------------------------------------------------ // #define PLCA_REPDATA(__reply_base) \ container_of(__reply_base, struct plca_reply_data, base) // PLCA get configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_get_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, bool *mod) { const struct nlattr *attr = tb[attrid]; if (!attr || WARN_ON_ONCE(attrid >= ARRAY_SIZE(ethnl_plca_set_cfg_policy))) return; switch (ethnl_plca_set_cfg_policy[attrid].type) { case NLA_U8: *dst = nla_get_u8(attr); break; case NLA_U32: *dst = nla_get_u32(attr); break; default: WARN_ON_ONCE(1); } *mod = true; } static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } // note: rtnl_lock is held already by ethnl_default_doit ops = ethtool_phy_ops; if (!ops || !ops->get_plca_cfg) { ret = -EOPNOTSUPP; goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out; memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); ret = ops->get_plca_cfg(phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: return ret; } static int plca_get_cfg_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u16)) + /* _VERSION */ nla_total_size(sizeof(u8)) + /* _ENABLED */ nla_total_size(sizeof(u32)) + /* _NODE_CNT */ nla_total_size(sizeof(u32)) + /* _NODE_ID */ nla_total_size(sizeof(u32)) + /* _TO_TIMER */ nla_total_size(sizeof(u32)) + /* _BURST_COUNT */ nla_total_size(sizeof(u32)); /* _BURST_TIMER */ } static int plca_get_cfg_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct plca_reply_data *data = PLCA_REPDATA(reply_base); const struct phy_plca_cfg *plca = &data->plca_cfg; if ((plca->version >= 0 && nla_put_u16(skb, ETHTOOL_A_PLCA_VERSION, plca->version)) || (plca->enabled >= 0 && nla_put_u8(skb, ETHTOOL_A_PLCA_ENABLED, !!plca->enabled)) || (plca->node_id >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_ID, plca->node_id)) || (plca->node_cnt >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_CNT, plca->node_cnt)) || (plca->to_tmr >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_TO_TMR, plca->to_tmr)) || (plca->burst_cnt >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_CNT, plca->burst_cnt)) || (plca->burst_tmr >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_TMR, plca->burst_tmr))) return -EMSGSIZE; return 0; }; // PLCA set configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_set_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), [ETHTOOL_A_PLCA_TO_TMR] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_BURST_CNT] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_BURST_TMR] = NLA_POLICY_MAX(NLA_U32, 255), }; static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; struct phy_device *phydev; bool mod = false; int ret; phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; ops = ethtool_phy_ops; if (!ops || !ops->set_plca_cfg) return -EOPNOTSUPP; memset(&plca_cfg, 0xff, sizeof(plca_cfg)); plca_update_sint(&plca_cfg.enabled, tb, ETHTOOL_A_PLCA_ENABLED, &mod); plca_update_sint(&plca_cfg.node_id, tb, ETHTOOL_A_PLCA_NODE_ID, &mod); plca_update_sint(&plca_cfg.node_cnt, tb, ETHTOOL_A_PLCA_NODE_CNT, &mod); plca_update_sint(&plca_cfg.to_tmr, tb, ETHTOOL_A_PLCA_TO_TMR, &mod); plca_update_sint(&plca_cfg.burst_cnt, tb, ETHTOOL_A_PLCA_BURST_CNT, &mod); plca_update_sint(&plca_cfg.burst_tmr, tb, ETHTOOL_A_PLCA_BURST_TMR, &mod); if (!mod) return 0; ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { .request_cmd = ETHTOOL_MSG_PLCA_GET_CFG, .reply_cmd = ETHTOOL_MSG_PLCA_GET_CFG_REPLY, .hdr_attr = ETHTOOL_A_PLCA_HEADER, .req_info_size = sizeof(struct plca_req_info), .reply_data_size = sizeof(struct plca_reply_data), .prepare_data = plca_get_cfg_prepare_data, .reply_size = plca_get_cfg_reply_size, .fill_reply = plca_get_cfg_fill_reply, .set = ethnl_set_plca, .set_ntf_cmd = ETHTOOL_MSG_PLCA_NTF, }; // PLCA get status message -------------------------------------------------- // const struct nla_policy ethnl_plca_get_status_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } // note: rtnl_lock is held already by ethnl_default_doit ops = ethtool_phy_ops; if (!ops || !ops->get_plca_status) { ret = -EOPNOTSUPP; goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out; memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); ret = ops->get_plca_status(phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; } static int plca_get_status_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u8)); /* _STATUS */ } static int plca_get_status_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct plca_reply_data *data = PLCA_REPDATA(reply_base); const u8 status = data->plca_st.pst; if (nla_put_u8(skb, ETHTOOL_A_PLCA_STATUS, !!status)) return -EMSGSIZE; return 0; }; const struct ethnl_request_ops ethnl_plca_status_request_ops = { .request_cmd = ETHTOOL_MSG_PLCA_GET_STATUS, .reply_cmd = ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, .hdr_attr = ETHTOOL_A_PLCA_HEADER, .req_info_size = sizeof(struct plca_req_info), .reply_data_size = sizeof(struct plca_reply_data), .prepare_data = plca_get_status_prepare_data, .reply_size = plca_get_status_reply_size, .fill_reply = plca_get_status_fill_reply, }; |
| 106 8 300 300 293 293 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * KVM paravirt_ops implementation * * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright IBM Corporation, 2007 * Authors: Anthony Liguori <aliguori@us.ibm.com> */ #define pr_fmt(fmt) "kvm-guest: " fmt #include <linux/context_tracking.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/kernel.h> #include <linux/kvm_para.h> #include <linux/cpu.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/hardirq.h> #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/hash.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/kprobes.h> #include <linux/nmi.h> #include <linux/swait.h> #include <linux/syscore_ops.h> #include <linux/cc_platform.h> #include <linux/efi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> #include <asm/desc.h> #include <asm/tlbflush.h> #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> #include <asm/msr.h> #include <asm/ptrace.h> #include <asm/reboot.h> #include <asm/svm.h> #include <asm/e820/api.h> DEFINE_STATIC_KEY_FALSE_RO(kvm_async_pf_enabled); static int kvmapf = 1; static int __init parse_no_kvmapf(char *arg) { kvmapf = 0; return 0; } early_param("no-kvmapf", parse_no_kvmapf); static int steal_acc = 1; static int __init parse_no_stealacc(char *arg) { steal_acc = 0; return 0; } early_param("no-steal-acc", parse_no_stealacc); static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled); static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; static int has_guest_poll = 0; /* * No need for any "IO delay" on KVM */ static void kvm_io_delay(void) { } #define KVM_TASK_SLEEP_HASHBITS 8 #define KVM_TASK_SLEEP_HASHSIZE (1<<KVM_TASK_SLEEP_HASHBITS) struct kvm_task_sleep_node { struct hlist_node link; struct swait_queue_head wq; u32 token; int cpu; }; static struct kvm_task_sleep_head { raw_spinlock_t lock; struct hlist_head list; } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, u32 token) { struct hlist_node *p; hlist_for_each(p, &b->list) { struct kvm_task_sleep_node *n = hlist_entry(p, typeof(*n), link); if (n->token == token) return n; } return NULL; } static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node *e; raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { /* dummy entry exist -> wake up was delivered ahead of PF */ hlist_del(&e->link); raw_spin_unlock(&b->lock); kfree(e); return false; } n->token = token; n->cpu = smp_processor_id(); init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); return true; } /* * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled * @token: Token to identify the sleep node entry * * Invoked from the async pagefault handling code or from the VM exit page * fault handler. In both cases RCU is watching. */ void kvm_async_pf_task_wait_schedule(u32 token) { struct kvm_task_sleep_node n; DECLARE_SWAITQUEUE(wait); lockdep_assert_irqs_disabled(); if (!kvm_async_pf_queue_task(token, &n)) return; for (;;) { prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; local_irq_enable(); schedule(); local_irq_disable(); } finish_swait(&n.wq, &wait); } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule); static void apf_task_wake_one(struct kvm_task_sleep_node *n) { hlist_del_init(&n->link); if (swq_has_sleeper(&n->wq)) swake_up_one(&n->wq); } static void apf_task_wake_all(void) { int i; for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; struct kvm_task_sleep_node *n; struct hlist_node *p, *next; raw_spin_lock(&b->lock); hlist_for_each_safe(p, next, &b->list) { n = hlist_entry(p, typeof(*n), link); if (n->cpu == smp_processor_id()) apf_task_wake_one(n); } raw_spin_unlock(&b->lock); } } static void kvm_async_pf_task_wake(u32 token) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node *n, *dummy = NULL; if (token == ~0) { apf_task_wake_all(); return; } again: raw_spin_lock(&b->lock); n = _find_apf_task(b, token); if (!n) { /* * Async #PF not yet handled, add a dummy entry for the token. * Allocating the token must be down outside of the raw lock * as the allocator is preemptible on PREEMPT_RT kernels. */ if (!dummy) { raw_spin_unlock(&b->lock); dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC); /* * Continue looping on allocation failure, eventually * the async #PF will be handled and allocating a new * node will be unnecessary. */ if (!dummy) cpu_relax(); /* * Recheck for async #PF completion before enqueueing * the dummy token to avoid duplicate list entries. */ goto again; } dummy->token = token; dummy->cpu = smp_processor_id(); init_swait_queue_head(&dummy->wq); hlist_add_head(&dummy->link, &b->list); dummy = NULL; } else { apf_task_wake_one(n); } raw_spin_unlock(&b->lock); /* A dummy token might be allocated and ultimately not used. */ kfree(dummy); } noinstr u32 kvm_read_and_reset_apf_flags(void) { u32 flags = 0; if (__this_cpu_read(async_pf_enabled)) { flags = __this_cpu_read(apf_reason.flags); __this_cpu_write(apf_reason.flags, 0); } return flags; } EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags); noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token) { u32 flags = kvm_read_and_reset_apf_flags(); irqentry_state_t state; if (!flags) return false; state = irqentry_enter(regs); instrumentation_begin(); /* * If the host managed to inject an async #PF into an interrupt * disabled region, then die hard as this is not going to end well * and the host side is seriously broken. */ if (unlikely(!(regs->flags & X86_EFLAGS_IF))) panic("Host injected async #PF in interrupt disabled region\n"); if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { if (unlikely(!(user_mode(regs)))) panic("Host injected async #PF in kernel mode\n"); /* Page is swapped out by the host. */ kvm_async_pf_task_wait_schedule(token); } else { WARN_ONCE(1, "Unexpected async PF flags: %x\n", flags); } instrumentation_end(); irqentry_exit(regs, state); return true; } DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); u32 token; apic_eoi(); inc_irq_stat(irq_hv_callback_count); if (__this_cpu_read(async_pf_enabled)) { token = __this_cpu_read(apf_reason.token); kvm_async_pf_task_wake(token); __this_cpu_write(apf_reason.token, 0); wrmsrq(MSR_KVM_ASYNC_PF_ACK, 1); } set_irq_regs(old_regs); } static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_ops.cpu.io_delay = kvm_io_delay; #ifdef CONFIG_X86_IO_APIC no_timer_check = 1; #endif } static void kvm_register_steal_time(void) { int cpu = smp_processor_id(); struct kvm_steal_time *st = &per_cpu(steal_time, cpu); if (!has_steal_clock) return; wrmsrq(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED)); pr_debug("stealtime: cpu %d, msr %llx\n", cpu, (unsigned long long) slow_virt_to_phys(st)); } static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; static notrace __maybe_unused void kvm_guest_apic_eoi_write(void) { /** * This relies on __test_and_clear_bit to modify the memory * in a way that is atomic with respect to the local CPU. * The hypervisor only accesses this memory from the local CPU so * there's no need for lock or memory barriers. * An optimization barrier is implied in apic write. */ if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi))) return; apic_native_eoi(); } static void kvm_guest_cpu_init(void) { if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { u64 pa; WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled)); pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); pa |= KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; wrmsrq(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR); wrmsrq(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(async_pf_enabled, true); pr_debug("setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { unsigned long pa; /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); __this_cpu_write(kvm_apic_eoi, 0); pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi)) | KVM_MSR_ENABLED; wrmsrq(MSR_KVM_PV_EOI_EN, pa); } if (has_steal_clock) kvm_register_steal_time(); } static void kvm_pv_disable_apf(void) { if (!__this_cpu_read(async_pf_enabled)) return; wrmsrq(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(async_pf_enabled, false); pr_debug("disable async PF for cpu %d\n", smp_processor_id()); } static void kvm_disable_steal_time(void) { if (!has_steal_clock) return; wrmsrq(MSR_KVM_STEAL_TIME, 0); } static u64 kvm_steal_clock(int cpu) { u64 steal; struct kvm_steal_time *src; int version; src = &per_cpu(steal_time, cpu); do { version = src->version; virt_rmb(); steal = src->steal; virt_rmb(); } while ((version & 1) || (version != src->version)); return steal; } static inline __init void __set_percpu_decrypted(void *ptr, unsigned long size) { early_set_memory_decrypted((unsigned long) ptr, size); } /* * Iterate through all possible CPUs and map the memory region pointed * by apf_reason, steal_time and kvm_apic_eoi as decrypted at once. * * Note: we iterate through all possible CPUs to ensure that CPUs * hotplugged will have their per-cpu variable already mapped as * decrypted. */ static void __init sev_map_percpu_data(void) { int cpu; if (cc_vendor != CC_VENDOR_AMD || !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; for_each_possible_cpu(cpu) { __set_percpu_decrypted(&per_cpu(apf_reason, cpu), sizeof(apf_reason)); __set_percpu_decrypted(&per_cpu(steal_time, cpu), sizeof(steal_time)); __set_percpu_decrypted(&per_cpu(kvm_apic_eoi, cpu), sizeof(kvm_apic_eoi)); } } static void kvm_guest_cpu_offline(bool shutdown) { kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrq(MSR_KVM_PV_EOI_EN, 0); if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) wrmsrq(MSR_KVM_MIGRATION_CONTROL, 0); kvm_pv_disable_apf(); if (!shutdown) apf_task_wake_all(); kvmclock_disable(); } static int kvm_cpu_online(unsigned int cpu) { unsigned long flags; local_irq_save(flags); kvm_guest_cpu_init(); local_irq_restore(flags); return 0; } #ifdef CONFIG_SMP static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); static bool pv_tlb_flush_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && !boot_cpu_has(X86_FEATURE_MWAIT) && (num_possible_cpus() != 1)); } static bool pv_ipi_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) && (num_possible_cpus() != 1)); } static bool pv_sched_yield_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && !boot_cpu_has(X86_FEATURE_MWAIT) && (num_possible_cpus() != 1)); } #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) static void __send_ipi_mask(const struct cpumask *mask, int vector) { unsigned long flags; int cpu, min = 0, max = 0; #ifdef CONFIG_X86_64 __uint128_t ipi_bitmap = 0; #else u64 ipi_bitmap = 0; #endif u32 apic_id, icr; long ret; if (cpumask_empty(mask)) return; local_irq_save(flags); switch (vector) { default: icr = APIC_DM_FIXED | vector; break; case NMI_VECTOR: icr = APIC_DM_NMI; break; } for_each_cpu(cpu, mask) { apic_id = per_cpu(x86_cpu_to_apicid, cpu); if (!ipi_bitmap) { min = max = apic_id; } else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) { ipi_bitmap <<= min - apic_id; min = apic_id; } else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) { max = apic_id < max ? max : apic_id; } else { ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld", ret); min = max = apic_id; ipi_bitmap = 0; } __set_bit(apic_id - min, (unsigned long *)&ipi_bitmap); } if (ipi_bitmap) { ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld", ret); } local_irq_restore(flags); } static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) { __send_ipi_mask(mask, vector); } static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { unsigned int this_cpu = smp_processor_id(); struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); const struct cpumask *local_mask; cpumask_copy(new_mask, mask); cpumask_clear_cpu(this_cpu, new_mask); local_mask = new_mask; __send_ipi_mask(local_mask, vector); } static int __init setup_efi_kvm_sev_migration(void) { efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled"; efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID; efi_status_t status; unsigned long size; bool enabled; if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) || !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) return 0; if (!efi_enabled(EFI_BOOT)) return 0; if (!efi_enabled(EFI_RUNTIME_SERVICES)) { pr_info("%s : EFI runtime services are not enabled\n", __func__); return 0; } size = sizeof(enabled); /* Get variable contents into buffer */ status = efi.get_variable(efi_sev_live_migration_enabled, &efi_variable_guid, NULL, &size, &enabled); if (status == EFI_NOT_FOUND) { pr_info("%s : EFI live migration variable not found\n", __func__); return 0; } if (status != EFI_SUCCESS) { pr_info("%s : EFI variable retrieval failed\n", __func__); return 0; } if (enabled == 0) { pr_info("%s: live migration disabled in EFI\n", __func__); return 0; } pr_info("%s : live migration enabled in EFI\n", __func__); wrmsrq(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY); return 1; } late_initcall(setup_efi_kvm_sev_migration); /* * Set the IPI entry points */ static __init void kvm_setup_pv_ipi(void) { apic_update_callback(send_IPI_mask, kvm_send_ipi_mask); apic_update_callback(send_IPI_mask_allbutself, kvm_send_ipi_mask_allbutself); pr_info("setup PV IPIs\n"); } static void kvm_smp_send_call_func_ipi(const struct cpumask *mask) { int cpu; native_send_call_func_ipi(mask); /* Make sure other vCPUs get a chance to run if they need to. */ for_each_cpu(cpu, mask) { if (!idle_cpu(cpu) && vcpu_is_preempted(cpu)) { kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu)); break; } } } static void kvm_flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info) { u8 state; int cpu; struct kvm_steal_time *src; struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); cpumask_copy(flushmask, cpumask); /* * We have to call flush only on online vCPUs. And * queue flush_on_enter for pre-empted vCPUs */ for_each_cpu(cpu, flushmask) { /* * The local vCPU is never preempted, so we do not explicitly * skip check for local vCPU - it will never be cleared from * flushmask. */ src = &per_cpu(steal_time, cpu); state = READ_ONCE(src->preempted); if ((state & KVM_VCPU_PREEMPTED)) { if (try_cmpxchg(&src->preempted, &state, state | KVM_VCPU_FLUSH_TLB)) __cpumask_clear_cpu(cpu, flushmask); } } native_flush_tlb_multi(flushmask, info); } static __init int kvm_alloc_cpumask(void) { int cpu; if (!kvm_para_available() || nopv) return 0; if (pv_tlb_flush_supported() || pv_ipi_supported()) for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); } return 0; } arch_initcall(kvm_alloc_cpumask); static void __init kvm_smp_prepare_boot_cpu(void) { /* * Map the per-cpu variables as decrypted before kvm_guest_cpu_init() * shares the guest physical address with the hypervisor. */ sev_map_percpu_data(); kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); kvm_spinlock_init(); } static int kvm_cpu_down_prepare(unsigned int cpu) { unsigned long flags; local_irq_save(flags); kvm_guest_cpu_offline(false); local_irq_restore(flags); return 0; } #endif static int kvm_suspend(void) { u64 val = 0; kvm_guest_cpu_offline(false); #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) rdmsrq(MSR_KVM_POLL_CONTROL, val); has_guest_poll = !(val & 1); #endif return 0; } static void kvm_resume(void) { kvm_cpu_online(raw_smp_processor_id()); #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll) wrmsrq(MSR_KVM_POLL_CONTROL, 0); #endif } static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, }; static void kvm_pv_guest_cpu_reboot(void *unused) { kvm_guest_cpu_offline(true); } static int kvm_pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) { if (code == SYS_RESTART) on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); return NOTIFY_DONE; } static struct notifier_block kvm_pv_reboot_nb = { .notifier_call = kvm_pv_reboot_notify, }; /* * After a PV feature is registered, the host will keep writing to the * registered memory location. If the guest happens to shutdown, this memory * won't be valid. In cases like kexec, in which you install a new kernel, this * means a random memory location will be kept being written. */ #ifdef CONFIG_CRASH_DUMP static void kvm_crash_shutdown(struct pt_regs *regs) { kvm_guest_cpu_offline(true); native_machine_crash_shutdown(regs); } #endif #if defined(CONFIG_X86_32) || !defined(CONFIG_SMP) bool __kvm_vcpu_is_preempted(long cpu); __visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); return !!(src->preempted & KVM_VCPU_PREEMPTED); } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); #else #include <asm/asm-offsets.h> extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); /* * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and * restoring to/from the stack. */ #define PV_VCPU_PREEMPTED_ASM \ "movq __per_cpu_offset(,%rdi,8), %rax\n\t" \ "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \ "setne %al\n\t" DEFINE_ASM_FUNC(__raw_callee_save___kvm_vcpu_is_preempted, PV_VCPU_PREEMPTED_ASM, .text); #endif static void __init kvm_guest_init(void) { int i; paravirt_ops_setup(); register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) raw_spin_lock_init(&async_pf_sleepers[i].lock); if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; static_call_update(pv_steal_clock, kvm_steal_clock); pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_update_callback(eoi, kvm_guest_apic_eoi_write); if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { static_branch_enable(&kvm_async_pf_enabled); sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_kvm_asyncpf_interrupt); } #ifdef CONFIG_SMP if (pv_tlb_flush_supported()) { pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi; pr_info("KVM setup pv remote TLB flush\n"); } smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; if (pv_sched_yield_supported()) { smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; pr_info("setup PV sched yield\n"); } if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online", kvm_cpu_online, kvm_cpu_down_prepare) < 0) pr_err("failed to install cpu hotplug callbacks\n"); #else sev_map_percpu_data(); kvm_guest_cpu_init(); #endif #ifdef CONFIG_CRASH_DUMP machine_ops.crash_shutdown = kvm_crash_shutdown; #endif register_syscore_ops(&kvm_syscore_ops); /* * Hard lockup detection is enabled by default. Disable it, as guests * can get false positives too easily, for example if the host is * overcommitted. */ hardlockup_detector_disable(); } static noinline uint32_t __kvm_cpuid_base(void) { if (boot_cpu_data.cpuid_level < 0) return 0; /* So we don't blow up on old processors */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return cpuid_base_hypervisor(KVM_SIGNATURE, 0); return 0; } static inline uint32_t kvm_cpuid_base(void) { static int kvm_cpuid_base = -1; if (kvm_cpuid_base == -1) kvm_cpuid_base = __kvm_cpuid_base(); return kvm_cpuid_base; } bool kvm_para_available(void) { return kvm_cpuid_base() != 0; } EXPORT_SYMBOL_GPL(kvm_para_available); unsigned int kvm_arch_para_features(void) { return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES); } unsigned int kvm_arch_para_hints(void) { return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES); } EXPORT_SYMBOL_GPL(kvm_arch_para_hints); static uint32_t __init kvm_detect(void) { return kvm_cpuid_base(); } static void __init kvm_apic_init(void) { #ifdef CONFIG_SMP if (pv_ipi_supported()) kvm_setup_pv_ipi(); #endif } static bool __init kvm_msi_ext_dest_id(void) { return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID); } static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc) { kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages, KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); } static void __init kvm_init_platform(void) { u64 tolud = PFN_PHYS(e820__end_of_low_ram_pfn()); /* * Note, hardware requires variable MTRR ranges to be power-of-2 sized * and naturally aligned. But when forcing guest MTRR state, Linux * doesn't program the forced ranges into hardware. Don't bother doing * the math to generate a technically-legal range. */ struct mtrr_var_range pci_hole = { .base_lo = tolud | X86_MEMTYPE_UC, .mask_lo = (u32)(~(SZ_4G - tolud - 1)) | MTRR_PHYSMASK_V, .mask_hi = (BIT_ULL(boot_cpu_data.x86_phys_bits) - 1) >> 32, }; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) { unsigned long nr_pages; int i; pv_ops.mmu.notify_page_enc_status_changed = kvm_sev_hc_page_enc_status; /* * Reset the host's shared pages list related to kernel * specific page encryption status settings before we load a * new kernel by kexec. Reset the page encryption status * during early boot instead of just before kexec to avoid SMP * races during kvm_pv_guest_cpu_reboot(). * NOTE: We cannot reset the complete shared pages list * here as we need to retain the UEFI/OVMF firmware * specific settings. */ for (i = 0; i < e820_table->nr_entries; i++) { struct e820_entry *entry = &e820_table->entries[i]; if (entry->type != E820_TYPE_RAM) continue; nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE); kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr, nr_pages, KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); } /* * Ensure that _bss_decrypted section is marked as decrypted in the * shared pages list. */ early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, __end_bss_decrypted - __start_bss_decrypted, 0); /* * If not booted using EFI, enable Live migration support. */ if (!efi_enabled(EFI_BOOT)) wrmsrq(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY); } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; /* * Set WB as the default cache mode for SEV-SNP and TDX, with a single * UC range for the legacy PCI hole, e.g. so that devices that expect * to get UC/WC mappings don't get surprised with WB. */ guest_force_mtrr_state(&pci_hole, 1, MTRR_TYPE_WRBACK); } #if defined(CONFIG_AMD_MEM_ENCRYPT) static void kvm_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) { /* RAX and CPL are already in the GHCB */ ghcb_set_rbx(ghcb, regs->bx); ghcb_set_rcx(ghcb, regs->cx); ghcb_set_rdx(ghcb, regs->dx); ghcb_set_rsi(ghcb, regs->si); } static bool kvm_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) { /* No checking of the return state needed */ return true; } #endif const __initconst struct hypervisor_x86 x86_hyper_kvm = { .name = "KVM", .detect = kvm_detect, .type = X86_HYPER_KVM, .init.guest_late_init = kvm_guest_init, .init.x2apic_available = kvm_para_available, .init.msi_ext_dest_id = kvm_msi_ext_dest_id, .init.init_platform = kvm_init_platform, #if defined(CONFIG_AMD_MEM_ENCRYPT) .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare, .runtime.sev_es_hcall_finish = kvm_sev_es_hcall_finish, #endif }; static __init int activate_jump_labels(void) { if (has_steal_clock) { static_key_slow_inc(¶virt_steal_enabled); if (steal_acc) static_key_slow_inc(¶virt_steal_rq_enabled); } return 0; } arch_initcall(activate_jump_labels); #ifdef CONFIG_PARAVIRT_SPINLOCKS /* Kick a cpu by its apicid. Used to wake up a halted vcpu */ static void kvm_kick_cpu(int cpu) { unsigned long flags = 0; u32 apicid; apicid = per_cpu(x86_cpu_to_apicid, cpu); kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } #include <asm/qspinlock.h> static void kvm_wait(u8 *ptr, u8 val) { if (in_nmi()) return; /* * halt until it's our turn and kicked. Note that we do safe halt * for irq enabled case to avoid hang when lock info is overwritten * in irq spinlock slowpath and no spurious interrupt occur to save us. */ if (irqs_disabled()) { if (READ_ONCE(*ptr) == val) halt(); } else { local_irq_disable(); /* safe_halt() will enable IRQ */ if (READ_ONCE(*ptr) == val) safe_halt(); else local_irq_enable(); } } /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ void __init kvm_spinlock_init(void) { /* * Disable PV spinlocks and use native qspinlock when dedicated pCPUs * are available. */ if (kvm_para_has_hint(KVM_HINTS_REALTIME)) { pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints\n"); goto out; } if (num_possible_cpus() == 1) { pr_info("PV spinlocks disabled, single CPU\n"); goto out; } if (nopvspin) { pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter\n"); goto out; } /* * In case host doesn't support KVM_FEATURE_PV_UNHALT there is still an * advantage of keeping virt_spin_lock_key enabled: virt_spin_lock() is * preferred over native qspinlock when vCPU is preempted. */ if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) { pr_info("PV spinlocks disabled, no host support\n"); return; } pr_info("PV spinlocks enabled\n"); __pv_init_lock_hash(); pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; pv_ops.lock.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); pv_ops.lock.wait = kvm_wait; pv_ops.lock.kick = kvm_kick_cpu; /* * When PV spinlock is enabled which is preferred over * virt_spin_lock(), virt_spin_lock_key's value is meaningless. * Just disable it anyway. */ out: static_branch_disable(&virt_spin_lock_key); } #endif /* CONFIG_PARAVIRT_SPINLOCKS */ #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL static void kvm_disable_host_haltpoll(void *i) { wrmsrq(MSR_KVM_POLL_CONTROL, 0); } static void kvm_enable_host_haltpoll(void *i) { wrmsrq(MSR_KVM_POLL_CONTROL, 1); } void arch_haltpoll_enable(unsigned int cpu) { if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) { pr_err_once("host does not support poll control\n"); pr_err_once("host upgrade recommended\n"); return; } /* Enable guest halt poll disables host halt poll */ smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1); } EXPORT_SYMBOL_GPL(arch_haltpoll_enable); void arch_haltpoll_disable(unsigned int cpu) { if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) return; /* Disable guest halt poll enables host halt poll */ smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1); } EXPORT_SYMBOL_GPL(arch_haltpoll_disable); #endif |
| 25 354 351 14 4 15 26 16 11 170 19 1 3 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H #include <kvm/iodev.h> #include <asm/apic.h> #include <linux/kvm_host.h> #include "hyperv.h" #include "smm.h" #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 #define APIC_SHORT_MASK 0xc0000 #define APIC_DEST_NOSHORT 0x0 #define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS_DEFAULT 1 #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) enum lapic_mode { LAPIC_MODE_DISABLED = 0, LAPIC_MODE_INVALID = X2APIC_ENABLE, LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE, LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE, }; enum lapic_lvt_entry { LVT_TIMER, LVT_THERMAL_MONITOR, LVT_PERFORMANCE_COUNTER, LVT_LINT0, LVT_LINT1, LVT_ERROR, LVT_CMCI, KVM_APIC_MAX_NR_LVT_ENTRIES, }; #define APIC_LVTx(x) ((x) == LVT_CMCI ? APIC_LVTCMCI : APIC_LVTT + 0x10 * (x)) struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ ktime_t target_expiration; u32 timer_mode; u32 timer_mode_mask; u64 tscdeadline; u64 expired_tscdeadline; u32 timer_advance_ns; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; }; struct kvm_lapic { unsigned long base_address; struct kvm_io_device dev; struct kvm_timer lapic_timer; u32 divide_count; struct kvm_vcpu *vcpu; bool apicv_active; bool sw_enabled; bool irr_pending; bool lvt0_in_nmi_mode; /* Select registers in the vAPIC cannot be read/written. */ bool guest_apic_protected; /* Number of bits set in ISR. */ s16 isr_count; /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ int highest_isr_cache; /** * APIC register page. The layout matches the register layout seen by * the guest 1:1, because it is accessed by the vmx microcode. * Note: Only one register, the TPR, is used by the microcode. */ void *regs; gpa_t vapic_addr; struct gfn_to_hva_cache vapic_cache; unsigned long pending_events; unsigned int sipi_vector; int nr_lvt_entries; }; struct dest_map; int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode); void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); int kvm_alloc_apic_access_page(struct kvm *kvm); void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map); void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated); int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset); void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector); int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); int kvm_x2apic_icr_write_fast(struct kvm_lapic *apic, u64 data); int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic); static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic) { apic_set_vector(vec, apic->regs + APIC_IRR); /* * irr_pending must be true if any interrupt is pending; set it after * APIC_IRR to avoid race with apic_clear_irr */ apic->irr_pending = true; } static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off) { return apic_get_reg(apic->regs, reg_off); } DECLARE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) { if (static_branch_unlikely(&kvm_has_noapic_vcpu)) return vcpu->arch.apic; return true; } extern struct static_key_false_deferred apic_hw_disabled; static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; return true; } extern struct static_key_false_deferred apic_sw_disabled; static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_sw_disabled.key)) return apic->sw_enabled; return true; } static inline bool kvm_apic_present(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic); } static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu) { return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic); } static inline int apic_x2apic_mode(struct kvm_lapic *apic) { return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && vcpu->arch.apic->apicv_active; } static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events; } static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu) { return !is_smm(vcpu) && !kvm_x86_call(apic_init_signal_blocked)(vcpu); } static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, unsigned long *vcpu_bitmap); bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); static inline enum lapic_mode kvm_apic_mode(u64 apic_base) { return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); } static inline enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) { return kvm_apic_mode(vcpu->arch.apic_base); } static inline u8 kvm_xapic_id(struct kvm_lapic *apic) { return kvm_lapic_get_reg(apic, APIC_ID) >> 24; } #endif |
| 233 233 184 218 218 218 218 12 222 222 2 2 2 2 23 23 21 21 21 21 16 16 15 16 137 136 105 105 94 110 94 56 118 118 118 118 118 9 118 68 117 118 9 99 99 99 99 87 87 87 87 87 99 99 99 99 99 99 6 6 99 99 99 99 99 35 35 35 35 35 35 35 35 22 35 35 118 118 2 118 118 117 118 2 2 2 117 118 118 118 4 4 4 4 4 16 13 13 13 1 13 13 36 36 36 36 35 142 142 142 142 142 43 43 43 43 43 43 43 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 1 1 1 1 1 1 1 1 6 6 3 2 6 3 3 3 3 2 2 6 6 6 6 5 24 24 24 24 24 69 7 7 6 6 6 6 6 6 6 8 18 11 11 11 11 11 11 11 11 11 6 11 11 11 11 8 8 5 2 2 2 2 2 2 2 2 2 2 2 1 1 80 62 8 69 1 72 73 11 1 61 62 62 6 2 1 1 2 50 51 1 74 32 32 32 32 32 32 32 32 32 32 32 18 18 18 30 26 12 12 5 5 69 69 69 52 52 52 52 121 121 121 121 120 60 80 120 120 121 121 3 3 3 121 29 29 29 28 29 29 29 29 29 87 87 8 8 8 8 8 110 110 109 96 109 98 98 98 98 6 6 6 6 6 6 6 5 5 5 5 5 5 5 5 5 5 2 5 5 5 5 5 5 5 5 5 5 5 6 6 6 6 153 152 152 152 152 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Driver core for serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright 1999 ARM Limited * Copyright (C) 2000-2001 Deep Blue Solutions Ltd. */ #include <linux/module.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/init.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/pm_runtime.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/device.h> #include <linux/serial.h> /* for serial_state and serial_icounter_struct */ #include <linux/serial_core.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/math64.h> #include <linux/security.h> #include <linux/irq.h> #include <linux/uaccess.h> #include "serial_base.h" /* * This is used to lock changes in serial line configuration. */ static DEFINE_MUTEX(port_mutex); /* * lockdep: port->lock is initialized in two places, but we * want only one lock-class: */ static struct lock_class_key port_lock_key; #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) /* * Max time with active RTS before/after data is sent. */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); static void uart_port_shutdown(struct tty_port *port); static int uart_dcd_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_DCD_ENABLE); } static inline struct uart_port *uart_port_ref(struct uart_state *state) { if (atomic_add_unless(&state->refcount, 1, 0)) return state->uart_port; return NULL; } static inline void uart_port_deref(struct uart_port *uport) { if (atomic_dec_and_test(&uport->state->refcount)) wake_up(&uport->state->remove_wait); } static inline struct uart_port *uart_port_ref_lock(struct uart_state *state, unsigned long *flags) { struct uart_port *uport = uart_port_ref(state); if (uport) uart_port_lock_irqsave(uport, flags); return uport; } static inline void uart_port_unlock_deref(struct uart_port *uport, unsigned long flags) { if (uport) { uart_port_unlock_irqrestore(uport, flags); uart_port_deref(uport); } } static inline struct uart_port *uart_port_check(struct uart_state *state) { lockdep_assert_held(&state->port.mutex); return state->uart_port; } /** * uart_write_wakeup - schedule write processing * @port: port to be processed * * This routine is used by the interrupt handler to schedule processing in the * software interrupt portion of the driver. A driver is expected to call this * function when the number of characters in the transmit buffer have dropped * below a threshold. * * Locking: @port->lock should be held */ void uart_write_wakeup(struct uart_port *port) { struct uart_state *state = port->state; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ BUG_ON(!state); tty_port_tty_wakeup(&state->port); } EXPORT_SYMBOL(uart_write_wakeup); static void uart_stop(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_ref_lock(state, &flags); if (port) port->ops->stop_tx(port); uart_port_unlock_deref(port, flags); } static void __uart_start(struct uart_state *state) { struct uart_port *port = state->uart_port; struct serial_port_device *port_dev; int err; if (!port || port->flags & UPF_DEAD || uart_tx_stopped(port)) return; port_dev = port->port_dev; /* Increment the runtime PM usage count for the active check below */ err = pm_runtime_get(&port_dev->dev); if (err < 0 && err != -EINPROGRESS) { pm_runtime_put_noidle(&port_dev->dev); return; } /* * Start TX if enabled, and kick runtime PM. If the device is not * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); } static void uart_start(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_ref_lock(state, &flags); __uart_start(state); uart_port_unlock_deref(port, flags); } static void uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) { unsigned int old; guard(uart_port_lock_irqsave)(port); old = port->mctrl; port->mctrl = (old & ~clear) | set; if (old != port->mctrl && !(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) static void uart_port_dtr_rts(struct uart_port *uport, bool active) { if (active) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); else uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } /* Caller holds port mutex */ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state *state, const struct ktermios *old_termios) { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; bool old_hw_stopped; /* * If we have no tty, termios, or the port does not exist, * then we can't set the parameters for this port. */ if (!tty || uport->type == PORT_UNKNOWN) return; termios = &tty->termios; uport->ops->set_termios(uport, termios, old_termios); /* * Set modem status enables based on termios cflag */ guard(uart_port_lock_irq)(uport); if (termios->c_cflag & CRTSCTS) uport->status |= UPSTAT_CTS_ENABLE; else uport->status &= ~UPSTAT_CTS_ENABLE; if (termios->c_cflag & CLOCAL) uport->status &= ~UPSTAT_DCD_ENABLE; else uport->status |= UPSTAT_DCD_ENABLE; /* reset sw-assisted CTS flow control based on (possibly) new mode */ old_hw_stopped = uport->hw_stopped; uport->hw_stopped = uart_softcts_mode(uport) && !(uport->ops->get_mctrl(uport) & TIOCM_CTS); if (uport->hw_stopped != old_hw_stopped) { if (!old_hw_stopped) uport->ops->stop_tx(uport); else __uart_start(state); } } static int uart_alloc_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; unsigned long page; /* * Initialise and allocate the transmit and temporary * buffer. */ page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; uport = uart_port_ref_lock(state, &flags); if (!state->port.xmit_buf) { state->port.xmit_buf = (unsigned char *)page; kfifo_init(&state->port.xmit_fifo, state->port.xmit_buf, PAGE_SIZE); uart_port_unlock_deref(uport, flags); } else { uart_port_unlock_deref(uport, flags); /* * Do not free() the page under the port lock, see * uart_free_xmit_buf(). */ free_page(page); } return 0; } static void uart_free_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; char *xmit_buf; /* * Do not free() the transmit buffer page under the port lock since * this can create various circular locking scenarios. For instance, * console driver may need to allocate/free a debug object, which * can end up in printk() recursion. */ uport = uart_port_ref_lock(state, &flags); xmit_buf = port->xmit_buf; port->xmit_buf = NULL; INIT_KFIFO(port->xmit_fifo); uart_port_unlock_deref(uport, flags); free_page((unsigned long)xmit_buf); } /* * Startup the port. This will be called once per open. All calls * will be serialised by the per-port mutex. */ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct uart_port *uport = uart_port_check(state); int retval; if (uport->type == PORT_UNKNOWN) return 1; /* * Make sure the device is in D0 state. */ uart_change_pm(state, UART_PM_STATE_ON); retval = uart_alloc_xmit_buf(&state->port); if (retval) return retval; retval = uport->ops->startup(uport); if (retval == 0) { if (uart_console(uport) && uport->cons->cflag) { tty->termios.c_cflag = uport->cons->cflag; tty->termios.c_ispeed = uport->cons->ispeed; tty->termios.c_ospeed = uport->cons->ospeed; uport->cons->cflag = 0; uport->cons->ispeed = 0; uport->cons->ospeed = 0; } /* * Initialise the hardware port settings. */ uart_change_line_settings(tty, state, NULL); /* * Setup the RTS and DTR signals once the * port is open and ready to respond. */ if (init_hw && C_BAUD(tty)) uart_port_dtr_rts(uport, true); } /* * This is to allow setserial on this port. People may want to set * port/irq/type and then reconfigure the port properly if it failed * now. */ if (retval && capable(CAP_SYS_ADMIN)) return 1; return retval; } static int uart_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct tty_port *port = &state->port; struct uart_port *uport; int retval; if (tty_port_initialized(port)) goto out_base_port_startup; retval = uart_port_startup(tty, state, init_hw); if (retval) { set_bit(TTY_IO_ERROR, &tty->flags); return retval; } out_base_port_startup: uport = uart_port_check(state); if (!uport) return -EIO; serial_base_port_startup(uport); return 0; } /* * This routine will shutdown a serial port; interrupts are disabled, and * DTR is dropped if the hangup on close termio flag is on. Calls to * uart_shutdown are serialised by the per-port semaphore. * * uport == NULL if uart_port has already been removed */ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) { struct uart_port *uport = uart_port_check(state); struct tty_port *port = &state->port; /* * Set the TTY IO error marker */ if (tty) set_bit(TTY_IO_ERROR, &tty->flags); if (uport) serial_base_port_shutdown(uport); if (tty_port_initialized(port)) { tty_port_set_initialized(port, false); /* * Turn off DTR and RTS early. */ if (uport) { if (uart_console(uport) && tty) { uport->cons->cflag = tty->termios.c_cflag; uport->cons->ispeed = tty->termios.c_ispeed; uport->cons->ospeed = tty->termios.c_ospeed; } if (!tty || C_HUPCL(tty)) uart_port_dtr_rts(uport, false); } uart_port_shutdown(port); } /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); } /** * uart_update_timeout - update per-port frame timing information * @port: uart_port structure describing the port * @cflag: termios cflag value * @baud: speed of the port * * Set the @port frame timing information from which the FIFO timeout value is * derived. The @cflag value should reflect the actual hardware settings as * number of bits, parity, stop bits and baud rate is taken into account here. * * Locking: caller is expected to take @port->lock */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud) { u64 temp = tty_get_frame_size(cflag); temp *= NSEC_PER_SEC; port->frame_time = (unsigned int)DIV64_U64_ROUND_UP(temp, baud); } EXPORT_SYMBOL(uart_update_timeout); /** * uart_get_baud_rate - return baud rate for a particular port * @port: uart_port structure describing the port in question. * @termios: desired termios settings * @old: old termios (or %NULL) * @min: minimum acceptable baud rate * @max: maximum acceptable baud rate * * Decode the termios structure into a numeric baud rate, taking account of the * magic 38400 baud rate (with spd_* flags), and mapping the %B0 rate to 9600 * baud. * * If the new baud rate is invalid, try the @old termios setting. If it's still * invalid, we try 9600 baud. If that is also invalid 0 is returned. * * The @termios structure is updated to reflect the baud rate we're actually * going to be using. Don't do this for the case where B0 is requested ("hang * up"). * * Locking: caller dependent */ unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max) { unsigned int try; unsigned int baud; unsigned int altbaud; int hung_up = 0; upf_t flags = port->flags & UPF_SPD_MASK; switch (flags) { case UPF_SPD_HI: altbaud = 57600; break; case UPF_SPD_VHI: altbaud = 115200; break; case UPF_SPD_SHI: altbaud = 230400; break; case UPF_SPD_WARP: altbaud = 460800; break; default: altbaud = 38400; break; } for (try = 0; try < 2; try++) { baud = tty_termios_baud_rate(termios); /* * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ if (try == 0 && baud == 38400) baud = altbaud; /* * Special case: B0 rate. */ if (baud == 0) { hung_up = 1; baud = 9600; } if (baud >= min && baud <= max) return baud; /* * Oops, the quotient was zero. Try again with * the old baud rate if possible. */ termios->c_cflag &= ~CBAUD; if (old) { baud = tty_termios_baud_rate(old); if (!hung_up) tty_termios_encode_baud_rate(termios, baud, baud); old = NULL; continue; } /* * As a last resort, if the range cannot be met then clip to * the nearest chip supported rate. */ if (!hung_up) { if (baud <= min) tty_termios_encode_baud_rate(termios, min + 1, min + 1); else tty_termios_encode_baud_rate(termios, max - 1, max - 1); } } return 0; } EXPORT_SYMBOL(uart_get_baud_rate); /** * uart_get_divisor - return uart clock divisor * @port: uart_port structure describing the port * @baud: desired baud rate * * Calculate the divisor (baud_base / baud) for the specified @baud, * appropriately rounded. * * If 38400 baud and custom divisor is selected, return the custom divisor * instead. * * Locking: caller dependent */ unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud) { unsigned int quot; /* * Old custom speed handling. */ if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) quot = port->custom_divisor; else quot = DIV_ROUND_CLOSEST(port->uartclk, 16 * baud); return quot; } EXPORT_SYMBOL(uart_get_divisor); static int uart_put_char(struct tty_struct *tty, u8 c) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; port = uart_port_ref_lock(state, &flags); if (!state->port.xmit_buf) { uart_port_unlock_deref(port, flags); return 0; } if (port) ret = kfifo_put(&state->port.xmit_fifo, c); uart_port_unlock_deref(port, flags); return ret; } static void uart_flush_chars(struct tty_struct *tty) { uart_start(tty); } static ssize_t uart_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return -EL3HLT; port = uart_port_ref_lock(state, &flags); if (!state->port.xmit_buf) { uart_port_unlock_deref(port, flags); return 0; } if (port) ret = kfifo_in(&state->port.xmit_fifo, buf, count); __uart_start(state); uart_port_unlock_deref(port, flags); return ret; } static unsigned int uart_write_room(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_ref_lock(state, &flags); ret = kfifo_avail(&state->port.xmit_fifo); uart_port_unlock_deref(port, flags); return ret; } static unsigned int uart_chars_in_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_ref_lock(state, &flags); ret = kfifo_len(&state->port.xmit_fifo); uart_port_unlock_deref(port, flags); return ret; } static void uart_flush_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return; pr_debug("uart_flush_buffer(%d) called\n", tty->index); port = uart_port_ref_lock(state, &flags); if (!port) return; kfifo_reset(&state->port.xmit_fifo); if (port->ops->flush_buffer) port->ops->flush_buffer(port); uart_port_unlock_deref(port, flags); tty_port_tty_wakeup(&state->port); } /* * This function performs low-level write of high-priority XON/XOFF * character and accounting for it. * * Requires uart_port to implement .serial_out(). */ void uart_xchar_out(struct uart_port *uport, int offset) { serial_port_out(uport, offset, uport->x_char); uport->icount.tx++; uport->x_char = 0; } EXPORT_SYMBOL_GPL(uart_xchar_out); /* * This function is used to send a high-priority XON/XOFF character to * the device */ static void uart_send_xchar(struct tty_struct *tty, u8 ch) { struct uart_state *state = tty->driver_data; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (port->ops->send_xchar) port->ops->send_xchar(port, ch); else { guard(uart_port_lock_irqsave)(port); port->x_char = ch; if (ch) port->ops->start_tx(port); } uart_port_deref(port); } static void uart_throttle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->throttle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_clear_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, STOP_CHAR(tty)); uart_port_deref(port); } static void uart_unthrottle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->unthrottle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_set_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, START_CHAR(tty)); uart_port_deref(port); } static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; /* Initialize structure in case we error out later to prevent any stack info leakage. */ *retinfo = (struct serial_struct){}; /* * Ensure the state we copy is consistent and no hardware changes * occur as we go */ guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -ENODEV; retinfo->type = uport->type; retinfo->line = uport->line; retinfo->port = uport->iobase; if (HIGH_BITS_OFFSET) retinfo->port_high = (long) uport->iobase >> HIGH_BITS_OFFSET; retinfo->irq = uport->irq; retinfo->flags = (__force int)uport->flags; retinfo->xmit_fifo_size = uport->fifosize; retinfo->baud_base = uport->uartclk / 16; retinfo->close_delay = jiffies_to_msecs(port->close_delay) / 10; retinfo->closing_wait = port->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : jiffies_to_msecs(port->closing_wait) / 10; retinfo->custom_divisor = uport->custom_divisor; retinfo->hub6 = uport->hub6; retinfo->io_type = uport->iotype; retinfo->iomem_reg_shift = uport->regshift; retinfo->iomem_base = (void *)(unsigned long)uport->mapbase; return 0; } static int uart_get_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; return uart_get_info(port, ss) < 0 ? -EIO : 0; } static int uart_change_port(struct uart_port *uport, const struct serial_struct *new_info, unsigned long new_port) { unsigned long old_iobase, old_mapbase; unsigned int old_type, old_iotype, old_hub6, old_shift; int retval; old_iobase = uport->iobase; old_mapbase = uport->mapbase; old_type = uport->type; old_hub6 = uport->hub6; old_iotype = uport->iotype; old_shift = uport->regshift; if (old_type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); uport->iobase = new_port; uport->type = new_info->type; uport->hub6 = new_info->hub6; uport->iotype = new_info->io_type; uport->regshift = new_info->iomem_reg_shift; uport->mapbase = (unsigned long)new_info->iomem_base; if (uport->type == PORT_UNKNOWN || !uport->ops->request_port) return 0; retval = uport->ops->request_port(uport); if (retval == 0) return 0; /* succeeded => done */ /* * If we fail to request resources for the new port, try to restore the * old settings. */ uport->iobase = old_iobase; uport->type = old_type; uport->hub6 = old_hub6; uport->iotype = old_iotype; uport->regshift = old_shift; uport->mapbase = old_mapbase; if (old_type == PORT_UNKNOWN) return retval; retval = uport->ops->request_port(uport); /* If we failed to restore the old settings, we fail like this. */ if (retval) uport->type = PORT_UNKNOWN; /* We failed anyway. */ return -EBUSY; } static int uart_set_info(struct tty_struct *tty, struct tty_port *port, struct uart_state *state, struct serial_struct *new_info) { struct uart_port *uport = uart_port_check(state); unsigned long new_port; unsigned int old_custom_divisor, close_delay, closing_wait; bool change_irq, change_port; upf_t old_flags, new_flags; int retval; if (!uport) return -EIO; new_port = new_info->port; if (HIGH_BITS_OFFSET) new_port += (unsigned long) new_info->port_high << HIGH_BITS_OFFSET; new_info->irq = irq_canonicalize(new_info->irq); close_delay = msecs_to_jiffies(new_info->close_delay * 10); closing_wait = new_info->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : msecs_to_jiffies(new_info->closing_wait * 10); change_irq = !(uport->flags & UPF_FIXED_PORT) && new_info->irq != uport->irq; /* * Since changing the 'type' of the port changes its resource * allocations, we should treat type changes the same as * IO port changes. */ change_port = !(uport->flags & UPF_FIXED_PORT) && (new_port != uport->iobase || (unsigned long)new_info->iomem_base != uport->mapbase || new_info->hub6 != uport->hub6 || new_info->io_type != uport->iotype || new_info->iomem_reg_shift != uport->regshift || new_info->type != uport->type); old_flags = uport->flags; new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; if (!(uport->flags & UPF_FIXED_PORT)) { unsigned int uartclk = new_info->baud_base * 16; /* check needs to be done here before other settings made */ if (uartclk == 0) return -EINVAL; } if (!capable(CAP_SYS_ADMIN)) { if (change_irq || change_port || (new_info->baud_base != uport->uartclk / 16) || (close_delay != port->close_delay) || (closing_wait != port->closing_wait) || (new_info->xmit_fifo_size && new_info->xmit_fifo_size != uport->fifosize) || (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0)) return -EPERM; uport->flags = ((uport->flags & ~UPF_USR_MASK) | (new_flags & UPF_USR_MASK)); uport->custom_divisor = new_info->custom_divisor; goto check_and_exit; } if (change_irq || change_port) { retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); if (retval) return retval; } /* Ask the low level driver to verify the settings. */ if (uport->ops->verify_port) { retval = uport->ops->verify_port(uport, new_info); if (retval) return retval; } if ((new_info->irq >= irq_get_nr_irqs()) || (new_info->irq < 0) || (new_info->baud_base < 9600)) return -EINVAL; if (change_port || change_irq) { /* Make sure that we are the sole user of this port. */ if (tty_port_users(port) > 1) return -EBUSY; /* * We need to shutdown the serial port at the old * port/type/irq combination. */ uart_shutdown(tty, state); } if (change_port) { retval = uart_change_port(uport, new_info, new_port); if (retval) return retval; } if (change_irq) uport->irq = new_info->irq; if (!(uport->flags & UPF_FIXED_PORT)) uport->uartclk = new_info->baud_base * 16; uport->flags = (uport->flags & ~UPF_CHANGE_MASK) | (new_flags & UPF_CHANGE_MASK); uport->custom_divisor = new_info->custom_divisor; port->close_delay = close_delay; port->closing_wait = closing_wait; if (new_info->xmit_fifo_size) uport->fifosize = new_info->xmit_fifo_size; check_and_exit: if (uport->type == PORT_UNKNOWN) return 0; if (tty_port_initialized(port)) { if (((old_flags ^ uport->flags) & UPF_SPD_MASK) || old_custom_divisor != uport->custom_divisor) { /* * If they're setting up a custom divisor or speed, * instead of clearing it, then bitch about it. */ if (uport->flags & UPF_SPD_MASK) { dev_notice_ratelimited(uport->dev, "%s sets custom speed on %s. This is deprecated.\n", current->comm, tty_name(port->tty)); } uart_change_line_settings(tty, state, NULL); } return 0; } retval = uart_startup(tty, state, true); if (retval < 0) return retval; if (retval == 0) tty_port_set_initialized(port, true); return 0; } static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; int retval; down_write(&tty->termios_rwsem); /* * This semaphore protects port->count. It is also * very useful to prevent opens. Also, take the * port configuration semaphore to make sure that a * module insertion/removal doesn't change anything * under us. */ mutex_lock(&port->mutex); retval = uart_set_info(tty, port, state, ss); mutex_unlock(&port->mutex); up_write(&tty->termios_rwsem); return retval; } /** * uart_get_lsr_info - get line status register info * @tty: tty associated with the UART * @state: UART being queried * @value: returned modem value */ static int uart_get_lsr_info(struct tty_struct *tty, struct uart_state *state, unsigned int __user *value) { struct uart_port *uport = uart_port_check(state); unsigned int result; result = uport->ops->tx_empty(uport); /* * If we're about to load something into the transmit * register, we'll pretend the transmitter isn't empty to * avoid a race condition (depending on when the transmit * interrupt happens). */ if (uport->x_char || (!kfifo_is_empty(&state->port.xmit_fifo) && !uart_tx_stopped(uport))) result &= ~TIOCSER_TEMT; return put_user(result, value); } static int uart_tiocmget(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; guard(uart_port_lock_irq)(uport); return uport->mctrl | uport->ops->get_mctrl(uport); } static int uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; uart_update_mctrl(uport, set, clear); return 0; } static int uart_break_ctl(struct tty_struct *tty, int break_state) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -EIO; if (uport->type != PORT_UNKNOWN && uport->ops->break_ctl) uport->ops->break_ctl(uport, break_state); return 0; } static int uart_do_autoconfig(struct tty_struct *tty, struct uart_state *state) { struct tty_port *port = &state->port; struct uart_port *uport; int flags, ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Take the per-port semaphore. This prevents count from * changing, and hence any extra opens of the port while * we're auto-configuring. */ scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &port->mutex) { uport = uart_port_check(state); if (!uport) return -EIO; if (tty_port_users(port) != 1) return -EBUSY; uart_shutdown(tty, state); /* * If we already have a port type configured, * we must release its resources. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); flags = UART_CONFIG_TYPE; if (uport->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; /* * This will claim the ports resources if * a port is found. */ uport->ops->config_port(uport, flags); ret = uart_startup(tty, state, true); if (ret < 0) return ret; if (ret > 0) return 0; tty_port_set_initialized(port, true); } return 0; } static void uart_enable_ms(struct uart_port *uport) { /* * Force modem status interrupts on */ if (uport->ops->enable_ms) uport->ops->enable_ms(uport); } /* * Wait for any of the 4 modem inputs (DCD,RI,DSR,CTS) to change * - mask passed in arg for lines of interest * (use |'ed TIOCM_RNG/DSR/CD/CTS for masking) * Caller should use TIOCGICOUNT to see which one it was * * FIXME: This wants extracting into a common all driver implementation * of TIOCMWAIT using tty_port. */ static int uart_wait_modem_status(struct uart_state *state, unsigned long arg) { struct uart_port *uport; struct tty_port *port = &state->port; DECLARE_WAITQUEUE(wait, current); struct uart_icount cprev, cnow; int ret; /* * note the counters on entry */ uport = uart_port_ref(state); if (!uport) return -EIO; scoped_guard(uart_port_lock_irq, uport) { memcpy(&cprev, &uport->icount, sizeof(struct uart_icount)); uart_enable_ms(uport); } add_wait_queue(&port->delta_msr_wait, &wait); for (;;) { scoped_guard(uart_port_lock_irq, uport) memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd)) || ((arg & TIOCM_CTS) && (cnow.cts != cprev.cts))) { ret = 0; break; } schedule(); /* see if a signal did it */ if (signal_pending(current)) { ret = -ERESTARTSYS; break; } cprev = cnow; } __set_current_state(TASK_RUNNING); remove_wait_queue(&port->delta_msr_wait, &wait); uart_port_deref(uport); return ret; } /* * Get counter of input serial line interrupts (DCD,RI,DSR,CTS) * Return: write counters to the user passed counter struct * NB: both 1->0 and 0->1 transitions are counted except for * RI where only 0->1 is counted. */ static int uart_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { struct uart_state *state = tty->driver_data; struct uart_icount cnow; struct uart_port *uport; unsigned long flags; uport = uart_port_ref_lock(state, &flags); if (!uport) return -EIO; memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); uart_port_unlock_deref(uport, flags); icount->cts = cnow.cts; icount->dsr = cnow.dsr; icount->rng = cnow.rng; icount->dcd = cnow.dcd; icount->rx = cnow.rx; icount->tx = cnow.tx; icount->frame = cnow.frame; icount->overrun = cnow.overrun; icount->parity = cnow.parity; icount->brk = cnow.brk; icount->buf_overrun = cnow.buf_overrun; return 0; } #define SER_RS485_LEGACY_FLAGS (SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | \ SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX | \ SER_RS485_TERMINATE_BUS) static int uart_check_rs485_flags(struct uart_port *port, struct serial_rs485 *rs485) { u32 flags = rs485->flags; /* Don't return -EINVAL for unsupported legacy flags */ flags &= ~SER_RS485_LEGACY_FLAGS; /* * For any bit outside of the legacy ones that is not supported by * the driver, return -EINVAL. */ if (flags & ~port->rs485_supported.flags) return -EINVAL; /* Asking for address w/o addressing mode? */ if (!(rs485->flags & SER_RS485_ADDRB) && (rs485->flags & (SER_RS485_ADDR_RECV|SER_RS485_ADDR_DEST))) return -EINVAL; /* Address given but not enabled? */ if (!(rs485->flags & SER_RS485_ADDR_RECV) && rs485->addr_recv) return -EINVAL; if (!(rs485->flags & SER_RS485_ADDR_DEST) && rs485->addr_dest) return -EINVAL; return 0; } static void uart_sanitize_serial_rs485_delays(struct uart_port *port, struct serial_rs485 *rs485) { if (!port->rs485_supported.delay_rts_before_send) { if (rs485->delay_rts_before_send) { dev_warn_ratelimited(port->dev, "%s (%u): RTS delay before sending not supported\n", port->name, port->line); } rs485->delay_rts_before_send = 0; } else if (rs485->delay_rts_before_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_before_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%u): RTS delay before sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_before_send); } if (!port->rs485_supported.delay_rts_after_send) { if (rs485->delay_rts_after_send) { dev_warn_ratelimited(port->dev, "%s (%u): RTS delay after sending not supported\n", port->name, port->line); } rs485->delay_rts_after_send = 0; } else if (rs485->delay_rts_after_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_after_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%u): RTS delay after sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_after_send); } } static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs485 *rs485) { u32 supported_flags = port->rs485_supported.flags; if (!(rs485->flags & SER_RS485_ENABLED)) { memset(rs485, 0, sizeof(*rs485)); return; } /* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */ if (rs485->flags & SER_RS485_MODE_RS422) { rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS); return; } rs485->flags &= supported_flags; /* Pick sane settings if the user hasn't */ if (!(rs485->flags & SER_RS485_RTS_ON_SEND) == !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) { if (supported_flags & SER_RS485_RTS_ON_SEND) { rs485->flags |= SER_RS485_RTS_ON_SEND; rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; dev_warn_ratelimited(port->dev, "%s (%u): invalid RTS setting, using RTS_ON_SEND instead\n", port->name, port->line); } else { rs485->flags |= SER_RS485_RTS_AFTER_SEND; rs485->flags &= ~SER_RS485_RTS_ON_SEND; dev_warn_ratelimited(port->dev, "%s (%u): invalid RTS setting, using RTS_AFTER_SEND instead\n", port->name, port->line); } } uart_sanitize_serial_rs485_delays(port, rs485); /* Return clean padding area to userspace */ memset(rs485->padding0, 0, sizeof(rs485->padding0)); memset(rs485->padding1, 0, sizeof(rs485->padding1)); } static void uart_set_rs485_termination(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_term_gpio, !!(rs485->flags & SER_RS485_TERMINATE_BUS)); } static void uart_set_rs485_rx_during_tx(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(rs485->flags & SER_RS485_RX_DURING_TX)); } static int uart_rs485_config(struct uart_port *port) { struct serial_rs485 *rs485 = &port->rs485; int ret; if (!(rs485->flags & SER_RS485_ENABLED)) return 0; uart_sanitize_serial_rs485(port, rs485); uart_set_rs485_termination(port, rs485); uart_set_rs485_rx_during_tx(port, rs485); scoped_guard(uart_port_lock_irqsave, port) ret = port->rs485_config(port, NULL, rs485); if (ret) { memset(rs485, 0, sizeof(*rs485)); /* unset GPIOs */ gpiod_set_value_cansleep(port->rs485_term_gpio, 0); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, 0); } return ret; } static int uart_get_rs485_config(struct uart_port *port, struct serial_rs485 __user *rs485) { struct serial_rs485 aux; scoped_guard(uart_port_lock_irqsave, port) aux = port->rs485; if (copy_to_user(rs485, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port, struct serial_rs485 __user *rs485_user) { struct serial_rs485 rs485; int ret; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return -ENOTTY; if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) return -EFAULT; ret = uart_check_rs485_flags(port, &rs485); if (ret) return ret; uart_sanitize_serial_rs485(port, &rs485); uart_set_rs485_termination(port, &rs485); uart_set_rs485_rx_during_tx(port, &rs485); scoped_guard(uart_port_lock_irqsave, port) { ret = port->rs485_config(port, &tty->termios, &rs485); if (!ret) { port->rs485 = rs485; /* Reset RTS and other mctrl lines when disabling RS485 */ if (!(rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } } if (ret) { /* restore old GPIO settings */ gpiod_set_value_cansleep(port->rs485_term_gpio, !!(port->rs485.flags & SER_RS485_TERMINATE_BUS)); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(port->rs485.flags & SER_RS485_RX_DURING_TX)); return ret; } if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485))) return -EFAULT; return 0; } static int uart_get_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816) { struct serial_iso7816 aux; if (!port->iso7816_config) return -ENOTTY; scoped_guard(uart_port_lock_irqsave, port) aux = port->iso7816; if (copy_to_user(iso7816, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816_user) { struct serial_iso7816 iso7816; int i; if (!port->iso7816_config) return -ENOTTY; if (copy_from_user(&iso7816, iso7816_user, sizeof(*iso7816_user))) return -EFAULT; /* * There are 5 words reserved for future use. Check that userspace * doesn't put stuff in there to prevent breakages in the future. */ for (i = 0; i < ARRAY_SIZE(iso7816.reserved); i++) if (iso7816.reserved[i]) return -EINVAL; scoped_guard(uart_port_lock_irqsave, port) { int ret = port->iso7816_config(port, &iso7816); if (ret) return ret; } if (copy_to_user(iso7816_user, &port->iso7816, sizeof(port->iso7816))) return -EFAULT; return 0; } /* * Called via sys_ioctl. We can use spin_lock_irq() here. */ static int uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; void __user *uarg = (void __user *)arg; int ret = -ENOIOCTLCMD; /* * These ioctls don't rely on the hardware to be present. */ switch (cmd) { case TIOCSERCONFIG: down_write(&tty->termios_rwsem); ret = uart_do_autoconfig(tty, state); up_write(&tty->termios_rwsem); break; } if (ret != -ENOIOCTLCMD) goto out; if (tty_io_error(tty)) { ret = -EIO; goto out; } /* * The following should only be used when hardware is present. */ switch (cmd) { case TIOCMIWAIT: ret = uart_wait_modem_status(state, arg); break; } if (ret != -ENOIOCTLCMD) goto out; /* rs485_config requires more locking than others */ if (cmd == TIOCSRS485) down_write(&tty->termios_rwsem); mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) { ret = -EIO; goto out_up; } /* * All these rely on hardware being present and need to be * protected against the tty being hung up. */ switch (cmd) { case TIOCSERGETLSR: /* Get line status register */ ret = uart_get_lsr_info(tty, state, uarg); break; case TIOCGRS485: ret = uart_get_rs485_config(uport, uarg); break; case TIOCSRS485: ret = uart_set_rs485_config(tty, uport, uarg); break; case TIOCSISO7816: ret = uart_set_iso7816_config(state->uart_port, uarg); break; case TIOCGISO7816: ret = uart_get_iso7816_config(state->uart_port, uarg); break; default: if (uport->ops->ioctl) ret = uport->ops->ioctl(uport, cmd, arg); break; } out_up: mutex_unlock(&port->mutex); if (cmd == TIOCSRS485) up_write(&tty->termios_rwsem); out: return ret; } static void uart_set_ldisc(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *uport; struct tty_port *port = &state->port; if (!tty_port_initialized(port)) return; mutex_lock(&state->port.mutex); uport = uart_port_check(state); if (uport && uport->ops->set_ldisc) uport->ops->set_ldisc(uport, &tty->termios); mutex_unlock(&state->port.mutex); } static void uart_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { struct uart_state *state = tty->driver_data; struct uart_port *uport; unsigned int cflag = tty->termios.c_cflag; unsigned int iflag_mask = IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK; bool sw_changed = false; guard(mutex)(&state->port.mutex); uport = uart_port_check(state); if (!uport) return; /* * Drivers doing software flow control also need to know * about changes to these input settings. */ if (uport->flags & UPF_SOFT_FLOW) { iflag_mask |= IXANY|IXON|IXOFF; sw_changed = tty->termios.c_cc[VSTART] != old_termios->c_cc[VSTART] || tty->termios.c_cc[VSTOP] != old_termios->c_cc[VSTOP]; } /* * These are the bits that are used to setup various * flags in the low level driver. We can ignore the Bfoo * bits in c_cflag; c_[io]speed will always be set * appropriately by set_termios() in tty_ioctl.c */ if ((cflag ^ old_termios->c_cflag) == 0 && tty->termios.c_ospeed == old_termios->c_ospeed && tty->termios.c_ispeed == old_termios->c_ispeed && ((tty->termios.c_iflag ^ old_termios->c_iflag) & iflag_mask) == 0 && !sw_changed) return; uart_change_line_settings(tty, state, old_termios); /* reload cflag from termios; port driver may have overridden flags */ cflag = tty->termios.c_cflag; /* Handle transition to B0 status */ if (((old_termios->c_cflag & CBAUD) != B0) && ((cflag & CBAUD) == B0)) uart_clear_mctrl(uport, TIOCM_RTS | TIOCM_DTR); /* Handle transition away from B0 status */ else if (((old_termios->c_cflag & CBAUD) == B0) && ((cflag & CBAUD) != B0)) { unsigned int mask = TIOCM_DTR; if (!(cflag & CRTSCTS) || !tty_throttled(tty)) mask |= TIOCM_RTS; uart_set_mctrl(uport, mask); } } /* * Calls to uart_close() are serialised via the tty_lock in * drivers/tty/tty_io.c:tty_release() * drivers/tty/tty_io.c:do_tty_hangup() */ static void uart_close(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; if (!state) { struct uart_driver *drv = tty->driver->driver_state; struct tty_port *port; state = drv->state + tty->index; port = &state->port; spin_lock_irq(&port->lock); --port->count; spin_unlock_irq(&port->lock); return; } pr_debug("uart_close(%d) called\n", tty->index); tty_port_close(tty->port, tty, filp); } static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * At this point, we stop accepting input. To do this, we * disable the receive line status interrupts. */ if (WARN(!uport, "detached port still initialized!\n")) return; scoped_guard(uart_port_lock_irq, uport) uport->ops->stop_rx(uport); serial_base_port_shutdown(uport); uart_port_shutdown(port); /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long char_time, expire, fifo_timeout; port = uart_port_ref(state); if (!port) return; if (port->type == PORT_UNKNOWN || port->fifosize == 0) { uart_port_deref(port); return; } /* * Set the check interval to be 1/5 of the estimated time to * send a single character, and make it at least 1. The check * interval should also be less than the timeout. * * Note: we have to use pretty tight timings here to satisfy * the NIST-PCTS. */ char_time = max(nsecs_to_jiffies(port->frame_time / 5), 1UL); if (timeout && timeout < char_time) char_time = timeout; if (!uart_cts_enabled(port)) { /* * If the transmitter hasn't cleared in twice the approximate * amount of time to send the entire FIFO, it probably won't * ever clear. This assumes the UART isn't doing flow * control, which is currently the case. Hence, if it ever * takes longer than FIFO timeout, this is probably due to a * UART bug of some kind. So, we clamp the timeout parameter at * 2 * FIFO timeout. */ fifo_timeout = uart_fifo_timeout(port); if (timeout == 0 || timeout > 2 * fifo_timeout) timeout = 2 * fifo_timeout; } expire = jiffies + timeout; pr_debug("uart_wait_until_sent(%u), jiffies=%lu, expire=%lu...\n", port->line, jiffies, expire); /* * Check whether the transmitter is empty every 'char_time'. * 'timeout' / 'expire' give us the maximum amount of time * we wait. */ while (!port->ops->tx_empty(port)) { msleep_interruptible(jiffies_to_msecs(char_time)); if (signal_pending(current)) break; if (timeout && time_after(jiffies, expire)) break; } uart_port_deref(port); } /* * Calls to uart_hangup() are serialised by the tty_lock in * drivers/tty/tty_io.c:do_tty_hangup() * This runs from a workqueue and can sleep for a _short_ time only. */ static void uart_hangup(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; unsigned long flags; pr_debug("uart_hangup(%d)\n", tty->index); mutex_lock(&port->mutex); uport = uart_port_check(state); WARN(!uport, "hangup of detached port!\n"); if (tty_port_active(port)) { uart_flush_buffer(tty); uart_shutdown(tty, state); spin_lock_irqsave(&port->lock, flags); port->count = 0; spin_unlock_irqrestore(&port->lock, flags); tty_port_set_active(port, false); tty_port_tty_set(port, NULL); if (uport && !uart_console(uport)) uart_change_pm(state, UART_PM_STATE_OFF); wake_up_interruptible(&port->open_wait); wake_up_interruptible(&port->delta_msr_wait); } mutex_unlock(&port->mutex); } /* uport == NULL if uart_port has already been removed */ static void uart_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * clear delta_msr_wait queue to avoid mem leaks: we may free * the irq here so the queue might never be woken up. Note * that we won't end up waiting on delta_msr_wait again since * any outstanding file descriptors should be pointing at * hung_up_tty_fops now. */ wake_up_interruptible(&port->delta_msr_wait); if (uport) { /* Free the IRQ and disable the port. */ uport->ops->shutdown(uport); /* Ensure that the IRQ handler isn't running on another CPU. */ synchronize_irq(uport->irq); } } static bool uart_carrier_raised(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; int mctrl; uport = uart_port_ref_lock(state, &flags); /* * Should never observe uport == NULL since checks for hangup should * abort the tty_port_block_til_ready() loop before checking for carrier * raised -- but report carrier raised if it does anyway so open will * continue and not sleep */ if (WARN_ON(!uport)) return true; uart_enable_ms(uport); mctrl = uport->ops->get_mctrl(uport); uart_port_unlock_deref(uport, flags); return mctrl & TIOCM_CAR; } static void uart_dtr_rts(struct tty_port *port, bool active) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return; uart_port_dtr_rts(uport, active); uart_port_deref(uport); } static int uart_install(struct tty_driver *driver, struct tty_struct *tty) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + tty->index; tty->driver_data = state; return tty_standard_install(driver, tty); } /* * Calls to uart_open are serialised by the tty_lock in * drivers/tty/tty_io.c:tty_open() * Note that if this fails, then uart_close() _will_ be called. * * In time, we want to scrap the "opening nonpresent ports" * behaviour and implement an alternative way for setserial * to set base addresses/ports/types. This will allow us to * get rid of a certain amount of extra tests. */ static int uart_open(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; int retval; retval = tty_port_open(&state->port, tty, filp); if (retval > 0) retval = 0; return retval; } static int uart_port_activate(struct tty_port *port, struct tty_struct *tty) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret; uport = uart_port_check(state); if (!uport || uport->flags & UPF_DEAD) return -ENXIO; /* * Start up the serial port. */ ret = uart_startup(tty, state, false); if (ret > 0) tty_port_set_active(port, true); return ret; } static const char *uart_type(struct uart_port *port) { const char *str = NULL; if (port->ops->type) str = port->ops->type(port); if (!str) str = "unknown"; return str; } #ifdef CONFIG_PROC_FS static void uart_line_info(struct seq_file *m, struct uart_state *state) { struct tty_port *port = &state->port; enum uart_pm_state pm_state; struct uart_port *uport; char stat_buf[32]; unsigned int status; int mmio; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return; mmio = uport->iotype >= UPIO_MEM; seq_printf(m, "%u: uart:%s %s%08llX irq:%u", uport->line, uart_type(uport), mmio ? "mmio:0x" : "port:", mmio ? (unsigned long long)uport->mapbase : (unsigned long long)uport->iobase, uport->irq); if (uport->type == PORT_UNKNOWN) { seq_putc(m, '\n'); return; } if (capable(CAP_SYS_ADMIN)) { pm_state = state->pm_state; if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, UART_PM_STATE_ON); scoped_guard(uart_port_lock_irq, uport) status = uport->ops->get_mctrl(uport); if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, pm_state); seq_printf(m, " tx:%u rx:%u", uport->icount.tx, uport->icount.rx); if (uport->icount.frame) seq_printf(m, " fe:%u", uport->icount.frame); if (uport->icount.parity) seq_printf(m, " pe:%u", uport->icount.parity); if (uport->icount.brk) seq_printf(m, " brk:%u", uport->icount.brk); if (uport->icount.overrun) seq_printf(m, " oe:%u", uport->icount.overrun); if (uport->icount.buf_overrun) seq_printf(m, " bo:%u", uport->icount.buf_overrun); #define INFOBIT(bit, str) \ if (uport->mctrl & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) #define STATBIT(bit, str) \ if (status & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) stat_buf[0] = '\0'; stat_buf[1] = '\0'; INFOBIT(TIOCM_RTS, "|RTS"); STATBIT(TIOCM_CTS, "|CTS"); INFOBIT(TIOCM_DTR, "|DTR"); STATBIT(TIOCM_DSR, "|DSR"); STATBIT(TIOCM_CAR, "|CD"); STATBIT(TIOCM_RNG, "|RI"); if (stat_buf[0]) stat_buf[0] = ' '; seq_puts(m, stat_buf); } seq_putc(m, '\n'); #undef STATBIT #undef INFOBIT } static int uart_proc_show(struct seq_file *m, void *v) { struct tty_driver *ttydrv = m->private; struct uart_driver *drv = ttydrv->driver_state; int i; seq_printf(m, "serinfo:1.0 driver%s%s revision:%s\n", "", "", ""); for (i = 0; i < drv->nr; i++) uart_line_info(m, drv->state + i); return 0; } #endif static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); lockdep_set_class(&port->lock, &port_lock_key); } #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL) /** * uart_console_write - write a console message to a serial port * @port: the port to write the message * @s: array of characters * @count: number of characters in string to write * @putchar: function to write character to port */ void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)) { unsigned int i; for (i = 0; i < count; i++, s++) { if (*s == '\n') putchar(port, '\r'); putchar(port, *s); } } EXPORT_SYMBOL_GPL(uart_console_write); /** * uart_parse_earlycon - Parse earlycon options * @p: ptr to 2nd field (ie., just beyond '<name>,') * @iotype: ptr for decoded iotype (out) * @addr: ptr for decoded mapbase/iobase (out) * @options: ptr for <options> field; %NULL if not present (out) * * Decodes earlycon kernel command line parameters of the form: * * earlycon=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * console=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * The optional form: * * earlycon=<name>,0x<addr>,<options> * * console=<name>,0x<addr>,<options> * * is also accepted; the returned @iotype will be %UPIO_MEM. * * Returns: 0 on success or -%EINVAL on failure */ int uart_parse_earlycon(char *p, enum uart_iotype *iotype, resource_size_t *addr, char **options) { if (strncmp(p, "mmio,", 5) == 0) { *iotype = UPIO_MEM; p += 5; } else if (strncmp(p, "mmio16,", 7) == 0) { *iotype = UPIO_MEM16; p += 7; } else if (strncmp(p, "mmio32,", 7) == 0) { *iotype = UPIO_MEM32; p += 7; } else if (strncmp(p, "mmio32be,", 9) == 0) { *iotype = UPIO_MEM32BE; p += 9; } else if (strncmp(p, "mmio32native,", 13) == 0) { *iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ? UPIO_MEM32BE : UPIO_MEM32; p += 13; } else if (strncmp(p, "io,", 3) == 0) { *iotype = UPIO_PORT; p += 3; } else if (strncmp(p, "0x", 2) == 0) { *iotype = UPIO_MEM; } else { return -EINVAL; } /* * Before you replace it with kstrtoull(), think about options separator * (',') it will not tolerate */ *addr = simple_strtoull(p, NULL, 0); p = strchr(p, ','); if (p) p++; *options = p; return 0; } EXPORT_SYMBOL_GPL(uart_parse_earlycon); /** * uart_parse_options - Parse serial port baud/parity/bits/flow control. * @options: pointer to option string * @baud: pointer to an 'int' variable for the baud rate. * @parity: pointer to an 'int' variable for the parity. * @bits: pointer to an 'int' variable for the number of data bits. * @flow: pointer to an 'int' variable for the flow control character. * * uart_parse_options() decodes a string containing the serial console * options. The format of the string is <baud><parity><bits><flow>, * eg: 115200n8r */ void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow) { const char *s = options; *baud = simple_strtoul(s, NULL, 10); while (*s >= '0' && *s <= '9') s++; if (*s) *parity = *s++; if (*s) *bits = *s++ - '0'; if (*s) *flow = *s; } EXPORT_SYMBOL_GPL(uart_parse_options); /** * uart_set_options - setup the serial console parameters * @port: pointer to the serial ports uart_port structure * @co: console pointer * @baud: baud rate * @parity: parity character - 'n' (none), 'o' (odd), 'e' (even) * @bits: number of data bits * @flow: flow control character - 'r' (rts) * * Locking: Caller must hold console_list_lock in order to serialize * early initialization of the serial-console lock. */ int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow) { struct ktermios termios; static struct ktermios dummy; /* * Ensure that the serial-console lock is initialised early. * * Note that the console-registered check is needed because * kgdboc can call uart_set_options() for an already registered * console via tty_find_polling_driver() and uart_poll_init(). */ if (!uart_console_registered_locked(port) && !port->console_reinit) uart_port_spin_lock_init(port); memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag |= CREAD | HUPCL | CLOCAL; tty_termios_encode_baud_rate(&termios, baud, baud); if (bits == 7) termios.c_cflag |= CS7; else termios.c_cflag |= CS8; switch (parity) { case 'o': case 'O': termios.c_cflag |= PARODD; fallthrough; case 'e': case 'E': termios.c_cflag |= PARENB; break; } if (flow == 'r') termios.c_cflag |= CRTSCTS; /* * some uarts on other side don't support no flow control. * So we set * DTR in host uart to make them happy */ port->mctrl |= TIOCM_DTR; port->ops->set_termios(port, &termios, &dummy); /* * Allow the setting of the UART parameters with a NULL console * too: */ if (co) { co->cflag = termios.c_cflag; co->ispeed = termios.c_ispeed; co->ospeed = termios.c_ospeed; } return 0; } EXPORT_SYMBOL_GPL(uart_set_options); #endif /* CONFIG_SERIAL_CORE_CONSOLE */ /** * uart_change_pm - set power state of the port * * @state: port descriptor * @pm_state: new state * * Locking: port->mutex has to be held */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state) { struct uart_port *port = uart_port_check(state); if (state->pm_state != pm_state) { if (port && port->ops->pm) port->ops->pm(port, pm_state, state->pm_state); state->pm_state = pm_state; } } struct uart_match { struct uart_port *port; struct uart_driver *driver; }; static int serial_match_port(struct device *dev, const void *data) { const struct uart_match *match = data; struct tty_driver *tty_drv = match->driver->tty_driver; dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) + match->port->line; return dev->devt == devt; /* Actually, only one tty per port */ } int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (tty_dev && device_may_wakeup(tty_dev)) { enable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); /* * Nothing to do if the console is not suspending * except stop_rx to prevent any asynchronous data * over RX line. However ensure that we will be * able to Re-start_rx later. */ if (!console_suspend_enabled && uart_console(uport)) { if (uport->ops->start_rx) { guard(uart_port_lock_irq)(uport); uport->ops->stop_rx(uport); } device_set_awake_path(uport->dev); return 0; } uport->suspended = 1; if (tty_port_initialized(port)) { const struct uart_ops *ops = uport->ops; int tries; unsigned int mctrl; tty_port_set_suspended(port, true); tty_port_set_initialized(port, false); scoped_guard(uart_port_lock_irq, uport) { ops->stop_tx(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); /* save mctrl so it can be restored on resume */ mctrl = uport->mctrl; uport->mctrl = 0; ops->stop_rx(uport); } /* * Wait for the transmitter to empty. */ for (tries = 3; !ops->tx_empty(uport) && tries; tries--) msleep(10); if (!tries) dev_err(uport->dev, "%s: Unable to drain transmitter\n", uport->name); ops->shutdown(uport); uport->mctrl = mctrl; } /* * Suspend the console device before suspending the port. */ if (uart_console(uport)) console_suspend(uport->cons); uart_change_pm(state, UART_PM_STATE_OFF); return 0; } EXPORT_SYMBOL(uart_suspend_port); int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; struct ktermios termios; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (!uport->suspended && device_may_wakeup(tty_dev)) { if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq)))) disable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); uport->suspended = 0; /* * Re-enable the console device after suspending. */ if (uart_console(uport)) { /* * First try to use the console cflag setting. */ memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag = uport->cons->cflag; termios.c_ispeed = uport->cons->ispeed; termios.c_ospeed = uport->cons->ospeed; /* * If that's unset, use the tty termios setting. */ if (port->tty && termios.c_cflag == 0) termios = port->tty->termios; if (console_suspend_enabled) uart_change_pm(state, UART_PM_STATE_ON); uport->ops->set_termios(uport, &termios, NULL); if (!console_suspend_enabled && uport->ops->start_rx) { guard(uart_port_lock_irq)(uport); uport->ops->start_rx(uport); } if (console_suspend_enabled) console_resume(uport->cons); } if (tty_port_suspended(port)) { const struct uart_ops *ops = uport->ops; int ret; uart_change_pm(state, UART_PM_STATE_ON); scoped_guard(uart_port_lock_irq, uport) if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); if (console_suspend_enabled || !uart_console(uport)) { /* Protected by port mutex for now */ struct tty_struct *tty = port->tty; ret = ops->startup(uport); if (ret == 0) { if (tty) uart_change_line_settings(tty, state, NULL); uart_rs485_config(uport); scoped_guard(uart_port_lock_irq, uport) { if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); ops->start_tx(uport); } tty_port_set_initialized(port, true); } else { /* * Failed to resume - maybe hardware went away? * Clear the "initialized" flag so we won't try * to call the low level drivers shutdown method. */ uart_shutdown(tty, state); } } tty_port_set_suspended(port, false); } return 0; } EXPORT_SYMBOL(uart_resume_port); static inline void uart_report_port(struct uart_driver *drv, struct uart_port *port) { char address[64]; switch (port->iotype) { case UPIO_PORT: snprintf(address, sizeof(address), "I/O 0x%lx", port->iobase); break; case UPIO_HUB6: snprintf(address, sizeof(address), "I/O 0x%lx offset 0x%x", port->iobase, port->hub6); break; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: snprintf(address, sizeof(address), "MMIO 0x%llx", (unsigned long long)port->mapbase); break; default: strscpy(address, "*unknown*", sizeof(address)); break; } pr_info("%s%s%s at %s (irq = %u, base_baud = %u) is a %s\n", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, address, port->irq, port->uartclk / 16, uart_type(port)); /* The magic multiplier feature is a bit obscure, so report it too. */ if (port->flags & UPF_MAGIC_MULTIPLIER) pr_info("%s%s%s extra baud rates supported: %u, %u", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, port->uartclk / 8, port->uartclk / 4); } static void uart_configure_port(struct uart_driver *drv, struct uart_state *state, struct uart_port *port) { unsigned int flags; /* * If there isn't a port here, don't do anything further. */ if (!port->iobase && !port->mapbase && !port->membase) return; /* * Now do the auto configuration stuff. Note that config_port * is expected to claim the resources and map the port for us. */ flags = 0; if (port->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; if (port->flags & UPF_BOOT_AUTOCONF) { if (!(port->flags & UPF_FIXED_TYPE)) { port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); port->ops->config_port(port, flags); if (uart_console(port)) console_unlock(); } if (port->type != PORT_UNKNOWN) { uart_report_port(drv, port); /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); /* * Ensure that the modem control lines are de-activated. * keep the DTR setting that is set in uart_set_options() * We probably don't need a spinlock around this, but */ scoped_guard(uart_port_lock_irqsave, port) { port->mctrl &= TIOCM_DTR; if (!(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } uart_rs485_config(port); if (uart_console(port)) console_unlock(); /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. * It may be that the port was not available. */ if (port->cons && !console_is_registered(port->cons)) register_console(port->cons); /* * Power down all ports by default, except the * console if we have one. */ if (!uart_console(port)) uart_change_pm(state, UART_PM_STATE_OFF); } } #ifdef CONFIG_CONSOLE_POLL static int uart_poll_init(struct tty_driver *driver, int line, char *options) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; enum uart_pm_state pm_state; struct tty_port *tport; struct uart_port *port; int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret = 0; tport = &state->port; guard(mutex)(&tport->mutex); port = uart_port_check(state); if (!port || port->type == PORT_UNKNOWN || !(port->ops->poll_get_char && port->ops->poll_put_char)) return -1; pm_state = state->pm_state; uart_change_pm(state, UART_PM_STATE_ON); if (port->ops->poll_init) { /* * We don't set initialized as we only initialized the hw, * e.g. state->xmit is still uninitialized. */ if (!tty_port_initialized(tport)) ret = port->ops->poll_init(port); } if (!ret && options) { uart_parse_options(options, &baud, &parity, &bits, &flow); console_list_lock(); ret = uart_set_options(port, NULL, baud, parity, bits, flow); console_list_unlock(); } if (ret) uart_change_pm(state, pm_state); return ret; } static int uart_poll_get_char(struct tty_driver *driver, int line) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; int ret = -1; port = uart_port_ref(state); if (port) { ret = port->ops->poll_get_char(port); uart_port_deref(port); } return ret; } static void uart_poll_put_char(struct tty_driver *driver, int line, char ch) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (ch == '\n') port->ops->poll_put_char(port, '\r'); port->ops->poll_put_char(port, ch); uart_port_deref(port); } #endif static const struct tty_operations uart_ops = { .install = uart_install, .open = uart_open, .close = uart_close, .write = uart_write, .put_char = uart_put_char, .flush_chars = uart_flush_chars, .write_room = uart_write_room, .chars_in_buffer= uart_chars_in_buffer, .flush_buffer = uart_flush_buffer, .ioctl = uart_ioctl, .throttle = uart_throttle, .unthrottle = uart_unthrottle, .send_xchar = uart_send_xchar, .set_termios = uart_set_termios, .set_ldisc = uart_set_ldisc, .stop = uart_stop, .start = uart_start, .hangup = uart_hangup, .break_ctl = uart_break_ctl, .wait_until_sent= uart_wait_until_sent, #ifdef CONFIG_PROC_FS .proc_show = uart_proc_show, #endif .tiocmget = uart_tiocmget, .tiocmset = uart_tiocmset, .set_serial = uart_set_info_user, .get_serial = uart_get_info_user, .get_icount = uart_get_icount, #ifdef CONFIG_CONSOLE_POLL .poll_init = uart_poll_init, .poll_get_char = uart_poll_get_char, .poll_put_char = uart_poll_put_char, #endif }; static const struct tty_port_operations uart_port_ops = { .carrier_raised = uart_carrier_raised, .dtr_rts = uart_dtr_rts, .activate = uart_port_activate, .shutdown = uart_tty_port_shutdown, }; /** * uart_register_driver - register a driver with the uart core layer * @drv: low level driver structure * * Register a uart driver with the core driver. We in turn register with the * tty layer, and initialise the core driver per-port state. * * We have a proc file in /proc/tty/driver which is named after the normal * driver. * * @drv->port should be %NULL, and the per-port structures should be registered * using uart_add_one_port() after this call has succeeded. * * Locking: none, Interrupts: enabled */ int uart_register_driver(struct uart_driver *drv) { struct tty_driver *normal; int i, retval = -ENOMEM; BUG_ON(drv->state); /* * Maybe we should be using a slab cache for this, especially if * we have a large number of ports to handle. */ drv->state = kcalloc(drv->nr, sizeof(struct uart_state), GFP_KERNEL); if (!drv->state) goto out; normal = tty_alloc_driver(drv->nr, TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(normal)) { retval = PTR_ERR(normal); goto out_kfree; } drv->tty_driver = normal; normal->driver_name = drv->driver_name; normal->name = drv->dev_name; normal->major = drv->major; normal->minor_start = drv->minor; normal->type = TTY_DRIVER_TYPE_SERIAL; normal->subtype = SERIAL_TYPE_NORMAL; normal->init_termios = tty_std_termios; normal->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; normal->init_termios.c_ispeed = normal->init_termios.c_ospeed = 9600; normal->driver_state = drv; tty_set_operations(normal, &uart_ops); /* * Initialise the UART state(s). */ for (i = 0; i < drv->nr; i++) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; tty_port_init(port); port->ops = &uart_port_ops; } retval = tty_register_driver(normal); if (retval >= 0) return retval; for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); tty_driver_kref_put(normal); out_kfree: kfree(drv->state); out: return retval; } EXPORT_SYMBOL(uart_register_driver); /** * uart_unregister_driver - remove a driver from the uart core layer * @drv: low level driver structure * * Remove all references to a driver from the core driver. The low level * driver must have removed all its ports via the uart_remove_one_port() if it * registered them with uart_add_one_port(). (I.e. @drv->port is %NULL.) * * Locking: none, Interrupts: enabled */ void uart_unregister_driver(struct uart_driver *drv) { struct tty_driver *p = drv->tty_driver; unsigned int i; tty_unregister_driver(p); tty_driver_kref_put(p); for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); kfree(drv->state); drv->state = NULL; drv->tty_driver = NULL; } EXPORT_SYMBOL(uart_unregister_driver); struct tty_driver *uart_console_device(struct console *co, int *index) { struct uart_driver *p = co->data; *index = co->index; return p->tty_driver; } EXPORT_SYMBOL_GPL(uart_console_device); static ssize_t uartclk_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.baud_base * 16); } static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.type); } static ssize_t line_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.line); } static ssize_t port_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); unsigned long ioaddr; uart_get_info(port, &tmp); ioaddr = tmp.port; if (HIGH_BITS_OFFSET) ioaddr |= (unsigned long)tmp.port_high << HIGH_BITS_OFFSET; return sprintf(buf, "0x%lX\n", ioaddr); } static ssize_t irq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.irq); } static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%X\n", tmp.flags); } static ssize_t xmit_fifo_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.xmit_fifo_size); } static ssize_t close_delay_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%u\n", tmp.close_delay); } static ssize_t closing_wait_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%u\n", tmp.closing_wait); } static ssize_t custom_divisor_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.custom_divisor); } static ssize_t io_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%u\n", tmp.io_type); } static ssize_t iomem_base_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%lX\n", (unsigned long)tmp.iomem_base); } static ssize_t iomem_reg_shift_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%u\n", tmp.iomem_reg_shift); } static ssize_t console_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool console = false; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) console = uart_console_registered(uport); mutex_unlock(&port->mutex); return sprintf(buf, "%c\n", console ? 'Y' : 'N'); } static ssize_t console_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool oldconsole, newconsole; int ret; ret = kstrtobool(buf, &newconsole); if (ret) return ret; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -ENXIO; oldconsole = uart_console_registered(uport); if (oldconsole && !newconsole) { ret = unregister_console(uport->cons); if (ret < 0) return ret; } else if (!oldconsole && newconsole) { if (!uart_console(uport)) return -ENOENT; uport->console_reinit = 1; register_console(uport->cons); } return count; } static DEVICE_ATTR_RO(uartclk); static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(line); static DEVICE_ATTR_RO(port); static DEVICE_ATTR_RO(irq); static DEVICE_ATTR_RO(flags); static DEVICE_ATTR_RO(xmit_fifo_size); static DEVICE_ATTR_RO(close_delay); static DEVICE_ATTR_RO(closing_wait); static DEVICE_ATTR_RO(custom_divisor); static DEVICE_ATTR_RO(io_type); static DEVICE_ATTR_RO(iomem_base); static DEVICE_ATTR_RO(iomem_reg_shift); static DEVICE_ATTR_RW(console); static struct attribute *tty_dev_attrs[] = { &dev_attr_uartclk.attr, &dev_attr_type.attr, &dev_attr_line.attr, &dev_attr_port.attr, &dev_attr_irq.attr, &dev_attr_flags.attr, &dev_attr_xmit_fifo_size.attr, &dev_attr_close_delay.attr, &dev_attr_closing_wait.attr, &dev_attr_custom_divisor.attr, &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, &dev_attr_console.attr, NULL }; static const struct attribute_group tty_dev_attr_group = { .attrs = tty_dev_attrs, }; /** * serial_core_add_one_port - attach a driver-defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure to use for this port. * * Context: task context, might sleep * * This allows the driver @drv to register its own uart_port structure with the * core driver. The main purpose is to allow the low level uart drivers to * expand uart_port, rather than having yet more levels of structures. * Caller must hold port_mutex. */ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state; struct tty_port *port; struct device *tty_dev; int num_groups; if (uport->line >= drv->nr) return -EINVAL; state = drv->state + uport->line; port = &state->port; guard(mutex)(&port->mutex); if (state->uart_port) return -EINVAL; /* Link the port to the driver state table and vice versa */ atomic_set(&state->refcount, 1); init_waitqueue_head(&state->remove_wait); state->uart_port = uport; uport->state = state; /* * If this port is in use as a console then the spinlock is already * initialised. */ if (!uart_console_registered(uport)) uart_port_spin_lock_init(uport); state->pm_state = UART_PM_STATE_UNDEFINED; uart_port_set_cons(uport, drv->cons); uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%u", drv->dev_name, drv->tty_driver->name_base + uport->line); if (!uport->name) return -ENOMEM; if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); num_groups = 2; if (uport->attr_group) num_groups++; uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups), GFP_KERNEL); if (!uport->tty_groups) return -ENOMEM; uport->tty_groups[0] = &tty_dev_attr_group; if (uport->attr_group) uport->tty_groups[1] = uport->attr_group; /* Ensure serdev drivers can call serdev_device_open() right away */ uport->flags &= ~UPF_DEAD; /* * Register the port whether it's detected or not. This allows * setserial to be used to alter this port's parameters. */ tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver, uport->line, uport->dev, &uport->port_dev->dev, port, uport->tty_groups); if (!IS_ERR(tty_dev)) { device_set_wakeup_capable(tty_dev, 1); } else { uport->flags |= UPF_DEAD; dev_err(uport->dev, "Cannot register tty device on line %u\n", uport->line); } return 0; } /** * serial_core_remove_one_port - detach a driver defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure for this port * * Context: task context, might sleep * * This unhooks (and hangs up) the specified port structure from the core * driver. No further calls will be made to the low-level code for this port. * Caller must hold port_mutex. */ static void serial_core_remove_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct uart_port *uart_port; mutex_lock(&port->mutex); uart_port = uart_port_check(state); if (uart_port != uport) dev_alert(uport->dev, "Removing wrong port: %p != %p\n", uart_port, uport); if (!uart_port) { mutex_unlock(&port->mutex); return; } mutex_unlock(&port->mutex); /* * Remove the devices from the tty layer */ tty_port_unregister_device(port, drv->tty_driver, uport->line); tty_port_tty_vhangup(port); /* * If the port is used as a console, unregister it */ if (uart_console(uport)) unregister_console(uport->cons); /* * Free the port IO and memory resources, if any. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); kfree(uport->tty_groups); kfree(uport->name); /* * Indicate that there isn't a port here anymore. */ uport->type = PORT_UNKNOWN; uport->port_dev = NULL; mutex_lock(&port->mutex); WARN_ON(atomic_dec_return(&state->refcount) < 0); wait_event(state->remove_wait, !atomic_read(&state->refcount)); state->uart_port = NULL; mutex_unlock(&port->mutex); } /** * uart_match_port - are the two ports equivalent? * @port1: first port * @port2: second port * * This utility function can be used to determine whether two uart_port * structures describe the same port. */ bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2) { if (port1->iotype != port2->iotype) return false; switch (port1->iotype) { case UPIO_PORT: return port1->iobase == port2->iobase; case UPIO_HUB6: return port1->iobase == port2->iobase && port1->hub6 == port2->hub6; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: return port1->mapbase == port2->mapbase; default: return false; } } EXPORT_SYMBOL(uart_match_port); static struct serial_ctrl_device * serial_core_get_ctrl_dev(struct serial_port_device *port_dev) { struct device *dev = &port_dev->dev; return to_serial_base_ctrl_device(dev->parent); } /* * Find a registered serial core controller device if one exists. Returns * the first device matching the ctrl_id. Caller must hold port_mutex. */ static struct serial_ctrl_device *serial_core_ctrl_find(struct uart_driver *drv, struct device *phys_dev, int ctrl_id) { struct uart_state *state; int i; lockdep_assert_held(&port_mutex); for (i = 0; i < drv->nr; i++) { state = drv->state + i; if (!state->uart_port || !state->uart_port->port_dev) continue; if (state->uart_port->dev == phys_dev && state->uart_port->ctrl_id == ctrl_id) return serial_core_get_ctrl_dev(state->uart_port->port_dev); } return NULL; } static struct serial_ctrl_device *serial_core_ctrl_device_add(struct uart_port *port) { return serial_base_ctrl_add(port, port->dev); } static int serial_core_port_device_add(struct serial_ctrl_device *ctrl_dev, struct uart_port *port) { struct serial_port_device *port_dev; port_dev = serial_base_port_add(port, ctrl_dev); if (IS_ERR(port_dev)) return PTR_ERR(port_dev); port->port_dev = port_dev; return 0; } /* * Initialize a serial core port device, and a controller device if needed. */ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) { struct serial_ctrl_device *ctrl_dev, *new_ctrl_dev = NULL; int ret; guard(mutex)(&port_mutex); /* * Prevent serial_port_runtime_resume() from trying to use the port * until serial_core_add_one_port() has completed */ port->flags |= UPF_DEAD; /* Inititalize a serial core controller device if needed */ ctrl_dev = serial_core_ctrl_find(drv, port->dev, port->ctrl_id); if (!ctrl_dev) { new_ctrl_dev = serial_core_ctrl_device_add(port); if (IS_ERR(new_ctrl_dev)) return PTR_ERR(new_ctrl_dev); ctrl_dev = new_ctrl_dev; } /* * Initialize a serial core port device. Tag the port dead to prevent * serial_port_runtime_resume() trying to do anything until port has * been registered. It gets cleared by serial_core_add_one_port(). */ ret = serial_core_port_device_add(ctrl_dev, port); if (ret) goto err_unregister_ctrl_dev; ret = serial_base_match_and_update_preferred_console(drv, port); if (ret) goto err_unregister_port_dev; ret = serial_core_add_one_port(drv, port); if (ret) goto err_unregister_port_dev; return 0; err_unregister_port_dev: serial_base_port_device_remove(port->port_dev); err_unregister_ctrl_dev: serial_base_ctrl_device_remove(new_ctrl_dev); return ret; } /* * Removes a serial core port device, and the related serial core controller * device if the last instance. */ void serial_core_unregister_port(struct uart_driver *drv, struct uart_port *port) { struct device *phys_dev = port->dev; struct serial_port_device *port_dev = port->port_dev; struct serial_ctrl_device *ctrl_dev = serial_core_get_ctrl_dev(port_dev); int ctrl_id = port->ctrl_id; mutex_lock(&port_mutex); port->flags |= UPF_DEAD; serial_core_remove_one_port(drv, port); /* Note that struct uart_port *port is no longer valid at this point */ serial_base_port_device_remove(port_dev); /* Drop the serial core controller device if no ports are using it */ if (!serial_core_ctrl_find(drv, phys_dev, ctrl_id)) serial_base_ctrl_device_remove(ctrl_dev); mutex_unlock(&port_mutex); } /** * uart_handle_dcd_change - handle a change of carrier detect state * @uport: uart_port structure for the open port * @active: new carrier detect status * * Caller must hold uport->lock. */ void uart_handle_dcd_change(struct uart_port *uport, bool active) { struct tty_port *port = &uport->state->port; struct tty_struct *tty = port->tty; struct tty_ldisc *ld; lockdep_assert_held_once(&uport->lock); if (tty) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) ld->ops->dcd_change(tty, active); tty_ldisc_deref(ld); } } uport->icount.dcd++; if (uart_dcd_enabled(uport)) { if (active) wake_up_interruptible(&port->open_wait); else if (tty) tty_hangup(tty); } } EXPORT_SYMBOL_GPL(uart_handle_dcd_change); /** * uart_handle_cts_change - handle a change of clear-to-send state * @uport: uart_port structure for the open port * @active: new clear-to-send status * * Caller must hold uport->lock. */ void uart_handle_cts_change(struct uart_port *uport, bool active) { lockdep_assert_held_once(&uport->lock); uport->icount.cts++; if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { if (active) { uport->hw_stopped = false; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { if (!active) { uport->hw_stopped = true; uport->ops->stop_tx(uport); } } } } EXPORT_SYMBOL_GPL(uart_handle_cts_change); /** * uart_insert_char - push a char to the uart layer * * User is responsible to call tty_flip_buffer_push when they are done with * insertion. * * @port: corresponding port * @status: state of the serial port RX buffer (LSR for 8250) * @overrun: mask of overrun bits in @status * @ch: character to push * @flag: flag for the character (see TTY_NORMAL and friends) */ void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag) { struct tty_port *tport = &port->state->port; if ((status & port->ignore_status_mask & ~overrun) == 0) if (tty_insert_flip_char(tport, ch, flag) == 0) ++port->icount.buf_overrun; /* * Overrun is special. Since it's reported immediately, * it doesn't affect the current character. */ if (status & ~port->ignore_status_mask & overrun) if (tty_insert_flip_char(tport, 0, TTY_OVERRUN) == 0) ++port->icount.buf_overrun; } EXPORT_SYMBOL_GPL(uart_insert_char); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL static const u8 sysrq_toggle_seq[] = CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE; static void uart_sysrq_on(struct work_struct *w) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); sysrq_toggle_support(1); pr_info("SysRq is enabled by magic sequence '%*pE' on serial\n", sysrq_toggle_seq_len, sysrq_toggle_seq); } static DECLARE_WORK(sysrq_enable_work, uart_sysrq_on); /** * uart_try_toggle_sysrq - Enables SysRq from serial line * @port: uart_port structure where char(s) after BREAK met * @ch: new character in the sequence after received BREAK * * Enables magic SysRq when the required sequence is met on port * (see CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE). * * Returns: %false if @ch is out of enabling sequence and should be * handled some other way, %true if @ch was consumed. */ bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); if (!sysrq_toggle_seq_len) return false; BUILD_BUG_ON(ARRAY_SIZE(sysrq_toggle_seq) >= U8_MAX); if (sysrq_toggle_seq[port->sysrq_seq] != ch) { port->sysrq_seq = 0; return false; } if (++port->sysrq_seq < sysrq_toggle_seq_len) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return true; } schedule_work(&sysrq_enable_work); port->sysrq = 0; return true; } EXPORT_SYMBOL_GPL(uart_try_toggle_sysrq); #endif /** * uart_get_rs485_mode() - retrieve rs485 properties for given uart * @port: uart device's target port * * This function implements the device tree binding described in * Documentation/devicetree/bindings/serial/rs485.txt. */ int uart_get_rs485_mode(struct uart_port *port) { struct serial_rs485 *rs485conf = &port->rs485; struct device *dev = port->dev; enum gpiod_flags dflags; struct gpio_desc *desc; u32 rs485_delay[2]; int ret; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return 0; ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); if (!ret) { rs485conf->delay_rts_before_send = rs485_delay[0]; rs485conf->delay_rts_after_send = rs485_delay[1]; } else { rs485conf->delay_rts_before_send = 0; rs485conf->delay_rts_after_send = 0; } uart_sanitize_serial_rs485_delays(port, rs485conf); /* * Clear full-duplex and enabled flags, set RTS polarity to active high * to get to a defined state with the following properties: */ rs485conf->flags &= ~(SER_RS485_RX_DURING_TX | SER_RS485_ENABLED | SER_RS485_TERMINATE_BUS | SER_RS485_RTS_AFTER_SEND); rs485conf->flags |= SER_RS485_RTS_ON_SEND; if (device_property_read_bool(dev, "rs485-rx-during-tx")) rs485conf->flags |= SER_RS485_RX_DURING_TX; if (device_property_read_bool(dev, "linux,rs485-enabled-at-boot-time")) rs485conf->flags |= SER_RS485_ENABLED; if (device_property_read_bool(dev, "rs485-rts-active-low")) { rs485conf->flags &= ~SER_RS485_RTS_ON_SEND; rs485conf->flags |= SER_RS485_RTS_AFTER_SEND; } /* * Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. * Works fine for short cables and users may enable for longer cables. */ desc = devm_gpiod_get_optional(dev, "rs485-term", GPIOD_OUT_LOW); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-term-gpios\n"); port->rs485_term_gpio = desc; if (port->rs485_term_gpio) port->rs485_supported.flags |= SER_RS485_TERMINATE_BUS; dflags = (rs485conf->flags & SER_RS485_RX_DURING_TX) ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; desc = devm_gpiod_get_optional(dev, "rs485-rx-during-tx", dflags); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-rx-during-tx-gpios\n"); port->rs485_rx_during_tx_gpio = desc; if (port->rs485_rx_during_tx_gpio) port->rs485_supported.flags |= SER_RS485_RX_DURING_TX; return 0; } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); /* Compile-time assertions for serial_rs485 layout */ static_assert(offsetof(struct serial_rs485, padding) == (offsetof(struct serial_rs485, delay_rts_after_send) + sizeof(__u32))); static_assert(offsetof(struct serial_rs485, padding1) == offsetof(struct serial_rs485, padding[1])); static_assert((offsetof(struct serial_rs485, padding[4]) + sizeof(__u32)) == sizeof(struct serial_rs485)); MODULE_DESCRIPTION("Serial driver core"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 1 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/super.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/sched/mm.h> #include <linux/statfs.h> #include <linux/kthread.h> #include <linux/parser.h> #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/random.h> #include <linux/exportfs.h> #include <linux/blkdev.h> #include <linux/quotaops.h> #include <linux/f2fs_fs.h> #include <linux/sysfs.h> #include <linux/quota.h> #include <linux/unicode.h> #include <linux/part_stat.h> #include <linux/zstd.h> #include <linux/lz4.h> #include <linux/ctype.h> #include <linux/fs_parser.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "gc.h" #include "iostat.h" #define CREATE_TRACE_POINTS #include <trace/events/f2fs.h> static struct kmem_cache *f2fs_inode_cachep; #ifdef CONFIG_F2FS_FAULT_INJECTION const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_KMALLOC] = "kmalloc", [FAULT_KVMALLOC] = "kvmalloc", [FAULT_PAGE_ALLOC] = "page alloc", [FAULT_PAGE_GET] = "page get", [FAULT_ALLOC_BIO] = "alloc bio(obsolete)", [FAULT_ALLOC_NID] = "alloc nid", [FAULT_ORPHAN] = "orphan", [FAULT_BLOCK] = "no more block", [FAULT_DIR_DEPTH] = "too big dir depth", [FAULT_EVICT_INODE] = "evict_inode fail", [FAULT_TRUNCATE] = "truncate fail", [FAULT_READ_IO] = "read IO error", [FAULT_CHECKPOINT] = "checkpoint error", [FAULT_DISCARD] = "discard error", [FAULT_WRITE_IO] = "write IO error", [FAULT_SLAB_ALLOC] = "slab alloc", [FAULT_DQUOT_INIT] = "dquot initialize", [FAULT_LOCK_OP] = "lock_op", [FAULT_BLKADDR_VALIDITY] = "invalid blkaddr", [FAULT_BLKADDR_CONSISTENCE] = "inconsistent blkaddr", [FAULT_NO_SEGMENT] = "no free segment", [FAULT_INCONSISTENT_FOOTER] = "inconsistent footer", [FAULT_TIMEOUT] = "timeout", [FAULT_VMALLOC] = "vmalloc", }; int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate, unsigned long type, enum fault_option fo) { struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (fo & FAULT_ALL) { memset(ffi, 0, sizeof(struct f2fs_fault_info)); return 0; } if (fo & FAULT_RATE) { if (rate > INT_MAX) return -EINVAL; atomic_set(&ffi->inject_ops, 0); ffi->inject_rate = (int)rate; f2fs_info(sbi, "build fault injection rate: %lu", rate); } if (fo & FAULT_TYPE) { if (type >= BIT(FAULT_MAX)) return -EINVAL; ffi->inject_type = (unsigned int)type; f2fs_info(sbi, "build fault injection type: 0x%lx", type); } return 0; } #endif /* f2fs-wide shrinker description */ static struct shrinker *f2fs_shrinker_info; static int __init f2fs_init_shrinker(void) { f2fs_shrinker_info = shrinker_alloc(0, "f2fs-shrinker"); if (!f2fs_shrinker_info) return -ENOMEM; f2fs_shrinker_info->count_objects = f2fs_shrink_count; f2fs_shrinker_info->scan_objects = f2fs_shrink_scan; shrinker_register(f2fs_shrinker_info); return 0; } static void f2fs_exit_shrinker(void) { shrinker_free(f2fs_shrinker_info); } enum { Opt_gc_background, Opt_disable_roll_forward, Opt_norecovery, Opt_discard, Opt_noheap, Opt_heap, Opt_user_xattr, Opt_acl, Opt_active_logs, Opt_disable_ext_identify, Opt_inline_xattr, Opt_inline_xattr_size, Opt_inline_data, Opt_inline_dentry, Opt_flush_merge, Opt_barrier, Opt_fastboot, Opt_extent_cache, Opt_data_flush, Opt_reserve_root, Opt_reserve_node, Opt_resgid, Opt_resuid, Opt_mode, Opt_fault_injection, Opt_fault_type, Opt_lazytime, Opt_quota, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_usrjquota, Opt_grpjquota, Opt_prjjquota, Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_checkpoint_disable, Opt_checkpoint_disable_cap, Opt_checkpoint_disable_cap_perc, Opt_checkpoint_enable, Opt_checkpoint_merge, Opt_compress_algorithm, Opt_compress_log_size, Opt_nocompress_extension, Opt_compress_extension, Opt_compress_chksum, Opt_compress_mode, Opt_compress_cache, Opt_atgc, Opt_gc_merge, Opt_discard_unit, Opt_memory_mode, Opt_age_extent_cache, Opt_errors, Opt_nat_bits, Opt_jqfmt, Opt_checkpoint, Opt_lookup_mode, Opt_err, }; static const struct constant_table f2fs_param_background_gc[] = { {"on", BGGC_MODE_ON}, {"off", BGGC_MODE_OFF}, {"sync", BGGC_MODE_SYNC}, {} }; static const struct constant_table f2fs_param_mode[] = { {"adaptive", FS_MODE_ADAPTIVE}, {"lfs", FS_MODE_LFS}, {"fragment:segment", FS_MODE_FRAGMENT_SEG}, {"fragment:block", FS_MODE_FRAGMENT_BLK}, {} }; static const struct constant_table f2fs_param_jqfmt[] = { {"vfsold", QFMT_VFS_OLD}, {"vfsv0", QFMT_VFS_V0}, {"vfsv1", QFMT_VFS_V1}, {} }; static const struct constant_table f2fs_param_alloc_mode[] = { {"default", ALLOC_MODE_DEFAULT}, {"reuse", ALLOC_MODE_REUSE}, {} }; static const struct constant_table f2fs_param_fsync_mode[] = { {"posix", FSYNC_MODE_POSIX}, {"strict", FSYNC_MODE_STRICT}, {"nobarrier", FSYNC_MODE_NOBARRIER}, {} }; static const struct constant_table f2fs_param_compress_mode[] = { {"fs", COMPR_MODE_FS}, {"user", COMPR_MODE_USER}, {} }; static const struct constant_table f2fs_param_discard_unit[] = { {"block", DISCARD_UNIT_BLOCK}, {"segment", DISCARD_UNIT_SEGMENT}, {"section", DISCARD_UNIT_SECTION}, {} }; static const struct constant_table f2fs_param_memory_mode[] = { {"normal", MEMORY_MODE_NORMAL}, {"low", MEMORY_MODE_LOW}, {} }; static const struct constant_table f2fs_param_errors[] = { {"remount-ro", MOUNT_ERRORS_READONLY}, {"continue", MOUNT_ERRORS_CONTINUE}, {"panic", MOUNT_ERRORS_PANIC}, {} }; static const struct constant_table f2fs_param_lookup_mode[] = { {"perf", LOOKUP_PERF}, {"compat", LOOKUP_COMPAT}, {"auto", LOOKUP_AUTO}, {} }; static const struct fs_parameter_spec f2fs_param_specs[] = { fsparam_enum("background_gc", Opt_gc_background, f2fs_param_background_gc), fsparam_flag("disable_roll_forward", Opt_disable_roll_forward), fsparam_flag("norecovery", Opt_norecovery), fsparam_flag_no("discard", Opt_discard), fsparam_flag("no_heap", Opt_noheap), fsparam_flag("heap", Opt_heap), fsparam_flag_no("user_xattr", Opt_user_xattr), fsparam_flag_no("acl", Opt_acl), fsparam_s32("active_logs", Opt_active_logs), fsparam_flag("disable_ext_identify", Opt_disable_ext_identify), fsparam_flag_no("inline_xattr", Opt_inline_xattr), fsparam_s32("inline_xattr_size", Opt_inline_xattr_size), fsparam_flag_no("inline_data", Opt_inline_data), fsparam_flag_no("inline_dentry", Opt_inline_dentry), fsparam_flag_no("flush_merge", Opt_flush_merge), fsparam_flag_no("barrier", Opt_barrier), fsparam_flag("fastboot", Opt_fastboot), fsparam_flag_no("extent_cache", Opt_extent_cache), fsparam_flag("data_flush", Opt_data_flush), fsparam_u32("reserve_root", Opt_reserve_root), fsparam_u32("reserve_node", Opt_reserve_node), fsparam_gid("resgid", Opt_resgid), fsparam_uid("resuid", Opt_resuid), fsparam_enum("mode", Opt_mode, f2fs_param_mode), fsparam_s32("fault_injection", Opt_fault_injection), fsparam_u32("fault_type", Opt_fault_type), fsparam_flag_no("lazytime", Opt_lazytime), fsparam_flag_no("quota", Opt_quota), fsparam_flag("usrquota", Opt_usrquota), fsparam_flag("grpquota", Opt_grpquota), fsparam_flag("prjquota", Opt_prjquota), fsparam_string_empty("usrjquota", Opt_usrjquota), fsparam_string_empty("grpjquota", Opt_grpjquota), fsparam_string_empty("prjjquota", Opt_prjjquota), fsparam_flag("nat_bits", Opt_nat_bits), fsparam_enum("jqfmt", Opt_jqfmt, f2fs_param_jqfmt), fsparam_enum("alloc_mode", Opt_alloc, f2fs_param_alloc_mode), fsparam_enum("fsync_mode", Opt_fsync, f2fs_param_fsync_mode), fsparam_string("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag("inlinecrypt", Opt_inlinecrypt), fsparam_string("checkpoint", Opt_checkpoint), fsparam_flag_no("checkpoint_merge", Opt_checkpoint_merge), fsparam_string("compress_algorithm", Opt_compress_algorithm), fsparam_u32("compress_log_size", Opt_compress_log_size), fsparam_string("compress_extension", Opt_compress_extension), fsparam_string("nocompress_extension", Opt_nocompress_extension), fsparam_flag("compress_chksum", Opt_compress_chksum), fsparam_enum("compress_mode", Opt_compress_mode, f2fs_param_compress_mode), fsparam_flag("compress_cache", Opt_compress_cache), fsparam_flag("atgc", Opt_atgc), fsparam_flag_no("gc_merge", Opt_gc_merge), fsparam_enum("discard_unit", Opt_discard_unit, f2fs_param_discard_unit), fsparam_enum("memory", Opt_memory_mode, f2fs_param_memory_mode), fsparam_flag("age_extent_cache", Opt_age_extent_cache), fsparam_enum("errors", Opt_errors, f2fs_param_errors), fsparam_enum("lookup_mode", Opt_lookup_mode, f2fs_param_lookup_mode), {} }; /* Resort to a match_table for this interestingly formatted option */ static match_table_t f2fs_checkpoint_tokens = { {Opt_checkpoint_disable, "disable"}, {Opt_checkpoint_disable_cap, "disable:%u"}, {Opt_checkpoint_disable_cap_perc, "disable:%u%%"}, {Opt_checkpoint_enable, "enable"}, {Opt_err, NULL}, }; #define F2FS_SPEC_background_gc (1 << 0) #define F2FS_SPEC_inline_xattr_size (1 << 1) #define F2FS_SPEC_active_logs (1 << 2) #define F2FS_SPEC_reserve_root (1 << 3) #define F2FS_SPEC_resgid (1 << 4) #define F2FS_SPEC_resuid (1 << 5) #define F2FS_SPEC_mode (1 << 6) #define F2FS_SPEC_fault_injection (1 << 7) #define F2FS_SPEC_fault_type (1 << 8) #define F2FS_SPEC_jqfmt (1 << 9) #define F2FS_SPEC_alloc_mode (1 << 10) #define F2FS_SPEC_fsync_mode (1 << 11) #define F2FS_SPEC_checkpoint_disable_cap (1 << 12) #define F2FS_SPEC_checkpoint_disable_cap_perc (1 << 13) #define F2FS_SPEC_compress_level (1 << 14) #define F2FS_SPEC_compress_algorithm (1 << 15) #define F2FS_SPEC_compress_log_size (1 << 16) #define F2FS_SPEC_compress_extension (1 << 17) #define F2FS_SPEC_nocompress_extension (1 << 18) #define F2FS_SPEC_compress_chksum (1 << 19) #define F2FS_SPEC_compress_mode (1 << 20) #define F2FS_SPEC_discard_unit (1 << 21) #define F2FS_SPEC_memory_mode (1 << 22) #define F2FS_SPEC_errors (1 << 23) #define F2FS_SPEC_lookup_mode (1 << 24) #define F2FS_SPEC_reserve_node (1 << 25) struct f2fs_fs_context { struct f2fs_mount_info info; unsigned int opt_mask; /* Bits changed */ unsigned int spec_mask; unsigned short qname_mask; }; #define F2FS_CTX_INFO(ctx) ((ctx)->info) static inline void ctx_set_opt(struct f2fs_fs_context *ctx, unsigned int flag) { ctx->info.opt |= flag; ctx->opt_mask |= flag; } static inline void ctx_clear_opt(struct f2fs_fs_context *ctx, unsigned int flag) { ctx->info.opt &= ~flag; ctx->opt_mask |= flag; } static inline bool ctx_test_opt(struct f2fs_fs_context *ctx, unsigned int flag) { return ctx->info.opt & flag; } void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...) { struct va_format vaf; va_list args; int level; va_start(args, fmt); level = printk_get_level(fmt); vaf.fmt = printk_skip_level(fmt); vaf.va = &args; if (limit_rate) if (sbi) printk_ratelimited("%c%cF2FS-fs (%s): %pV\n", KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); else printk_ratelimited("%c%cF2FS-fs: %pV\n", KERN_SOH_ASCII, level, &vaf); else if (sbi) printk("%c%cF2FS-fs (%s): %pV\n", KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); else printk("%c%cF2FS-fs: %pV\n", KERN_SOH_ASCII, level, &vaf); va_end(args); } #if IS_ENABLED(CONFIG_UNICODE) static const struct f2fs_sb_encodings { __u16 magic; char *name; unsigned int version; } f2fs_sb_encoding_map[] = { {F2FS_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct f2fs_sb_encodings * f2fs_sb_read_encoding(const struct f2fs_super_block *sb) { __u16 magic = le16_to_cpu(sb->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(f2fs_sb_encoding_map); i++) if (magic == f2fs_sb_encoding_map[i].magic) return &f2fs_sb_encoding_map[i]; return NULL; } struct kmem_cache *f2fs_cf_name_slab; static int __init f2fs_create_casefold_cache(void) { f2fs_cf_name_slab = f2fs_kmem_cache_create("f2fs_casefolded_name", F2FS_NAME_LEN); return f2fs_cf_name_slab ? 0 : -ENOMEM; } static void f2fs_destroy_casefold_cache(void) { kmem_cache_destroy(f2fs_cf_name_slab); } #else static int __init f2fs_create_casefold_cache(void) { return 0; } static void f2fs_destroy_casefold_cache(void) { } #endif static inline void limit_reserve_root(struct f2fs_sb_info *sbi) { block_t block_limit = min((sbi->user_block_count >> 3), sbi->user_block_count - sbi->reserved_blocks); block_t node_limit = sbi->total_node_count >> 3; /* limit is 12.5% */ if (test_opt(sbi, RESERVE_ROOT) && F2FS_OPTION(sbi).root_reserved_blocks > block_limit) { F2FS_OPTION(sbi).root_reserved_blocks = block_limit; f2fs_info(sbi, "Reduce reserved blocks for root = %u", F2FS_OPTION(sbi).root_reserved_blocks); } if (test_opt(sbi, RESERVE_NODE) && F2FS_OPTION(sbi).root_reserved_nodes > node_limit) { F2FS_OPTION(sbi).root_reserved_nodes = node_limit; f2fs_info(sbi, "Reduce reserved nodes for root = %u", F2FS_OPTION(sbi).root_reserved_nodes); } if (!test_opt(sbi, RESERVE_ROOT) && !test_opt(sbi, RESERVE_NODE) && (!uid_eq(F2FS_OPTION(sbi).s_resuid, make_kuid(&init_user_ns, F2FS_DEF_RESUID)) || !gid_eq(F2FS_OPTION(sbi).s_resgid, make_kgid(&init_user_ns, F2FS_DEF_RESGID)))) f2fs_info(sbi, "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root" " and reserve_node", from_kuid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resuid), from_kgid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resgid)); } static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi) { if (!F2FS_OPTION(sbi).unusable_cap_perc) return; if (F2FS_OPTION(sbi).unusable_cap_perc == 100) F2FS_OPTION(sbi).unusable_cap = sbi->user_block_count; else F2FS_OPTION(sbi).unusable_cap = (sbi->user_block_count / 100) * F2FS_OPTION(sbi).unusable_cap_perc; f2fs_info(sbi, "Adjust unusable cap for checkpoint=disable = %u / %u%%", F2FS_OPTION(sbi).unusable_cap, F2FS_OPTION(sbi).unusable_cap_perc); } static void init_once(void *foo) { struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; inode_init_once(&fi->vfs_inode); #ifdef CONFIG_FS_ENCRYPTION fi->i_crypt_info = NULL; #endif #ifdef CONFIG_FS_VERITY fi->i_verity_info = NULL; #endif } #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) /* * Note the name of the specified quota file. */ static int f2fs_note_qf_name(struct fs_context *fc, int qtype, struct fs_parameter *param) { struct f2fs_fs_context *ctx = fc->fs_private; char *qname; if (param->size < 1) { f2fs_err(NULL, "Missing quota name"); return -EINVAL; } if (strchr(param->string, '/')) { f2fs_err(NULL, "quotafile must be on filesystem root"); return -EINVAL; } if (ctx->info.s_qf_names[qtype]) { if (strcmp(ctx->info.s_qf_names[qtype], param->string) != 0) { f2fs_err(NULL, "Quota file already specified"); return -EINVAL; } return 0; } qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); if (!qname) { f2fs_err(NULL, "Not enough memory for storing quotafile name"); return -ENOMEM; } F2FS_CTX_INFO(ctx).s_qf_names[qtype] = qname; ctx->qname_mask |= 1 << qtype; return 0; } /* * Clear the name of the specified quota file. */ static int f2fs_unnote_qf_name(struct fs_context *fc, int qtype) { struct f2fs_fs_context *ctx = fc->fs_private; kfree(ctx->info.s_qf_names[qtype]); ctx->info.s_qf_names[qtype] = NULL; ctx->qname_mask |= 1 << qtype; return 0; } static void f2fs_unnote_qf_name_all(struct fs_context *fc) { int i; for (i = 0; i < MAXQUOTAS; i++) f2fs_unnote_qf_name(fc, i); } #endif static int f2fs_parse_test_dummy_encryption(const struct fs_parameter *param, struct f2fs_fs_context *ctx) { int err; if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { f2fs_warn(NULL, "test_dummy_encryption option not supported"); return -EINVAL; } err = fscrypt_parse_test_dummy_encryption(param, &ctx->info.dummy_enc_policy); if (err) { if (err == -EINVAL) f2fs_warn(NULL, "Value of option \"%s\" is unrecognized", param->key); else if (err == -EEXIST) f2fs_warn(NULL, "Conflicting test_dummy_encryption options"); else f2fs_warn(NULL, "Error processing option \"%s\" [%d]", param->key, err); return -EINVAL; } return 0; } #ifdef CONFIG_F2FS_FS_COMPRESSION static bool is_compress_extension_exist(struct f2fs_mount_info *info, const char *new_ext, bool is_ext) { unsigned char (*ext)[F2FS_EXTENSION_LEN]; int ext_cnt; int i; if (is_ext) { ext = info->extensions; ext_cnt = info->compress_ext_cnt; } else { ext = info->noextensions; ext_cnt = info->nocompress_ext_cnt; } for (i = 0; i < ext_cnt; i++) { if (!strcasecmp(new_ext, ext[i])) return true; } return false; } /* * 1. The same extension name cannot not appear in both compress and non-compress extension * at the same time. * 2. If the compress extension specifies all files, the types specified by the non-compress * extension will be treated as special cases and will not be compressed. * 3. Don't allow the non-compress extension specifies all files. */ static int f2fs_test_compress_extension(unsigned char (*noext)[F2FS_EXTENSION_LEN], int noext_cnt, unsigned char (*ext)[F2FS_EXTENSION_LEN], int ext_cnt) { int index = 0, no_index = 0; if (!noext_cnt) return 0; for (no_index = 0; no_index < noext_cnt; no_index++) { if (strlen(noext[no_index]) == 0) continue; if (!strcasecmp("*", noext[no_index])) { f2fs_info(NULL, "Don't allow the nocompress extension specifies all files"); return -EINVAL; } for (index = 0; index < ext_cnt; index++) { if (strlen(ext[index]) == 0) continue; if (!strcasecmp(ext[index], noext[no_index])) { f2fs_info(NULL, "Don't allow the same extension %s appear in both compress and nocompress extension", ext[index]); return -EINVAL; } } } return 0; } #ifdef CONFIG_F2FS_FS_LZ4 static int f2fs_set_lz4hc_level(struct f2fs_fs_context *ctx, const char *str) { #ifdef CONFIG_F2FS_FS_LZ4HC unsigned int level; if (strlen(str) == 3) { F2FS_CTX_INFO(ctx).compress_level = 0; ctx->spec_mask |= F2FS_SPEC_compress_level; return 0; } str += 3; if (str[0] != ':') { f2fs_info(NULL, "wrong format, e.g. <alg_name>:<compr_level>"); return -EINVAL; } if (kstrtouint(str + 1, 10, &level)) return -EINVAL; if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) { f2fs_info(NULL, "invalid lz4hc compress level: %d", level); return -EINVAL; } F2FS_CTX_INFO(ctx).compress_level = level; ctx->spec_mask |= F2FS_SPEC_compress_level; return 0; #else if (strlen(str) == 3) { F2FS_CTX_INFO(ctx).compress_level = 0; ctx->spec_mask |= F2FS_SPEC_compress_level; return 0; } f2fs_info(NULL, "kernel doesn't support lz4hc compression"); return -EINVAL; #endif } #endif #ifdef CONFIG_F2FS_FS_ZSTD static int f2fs_set_zstd_level(struct f2fs_fs_context *ctx, const char *str) { int level; int len = 4; if (strlen(str) == len) { F2FS_CTX_INFO(ctx).compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; ctx->spec_mask |= F2FS_SPEC_compress_level; return 0; } str += len; if (str[0] != ':') { f2fs_info(NULL, "wrong format, e.g. <alg_name>:<compr_level>"); return -EINVAL; } if (kstrtoint(str + 1, 10, &level)) return -EINVAL; /* f2fs does not support negative compress level now */ if (level < 0) { f2fs_info(NULL, "do not support negative compress level: %d", level); return -ERANGE; } if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(NULL, "invalid zstd compress level: %d", level); return -EINVAL; } F2FS_CTX_INFO(ctx).compress_level = level; ctx->spec_mask |= F2FS_SPEC_compress_level; return 0; } #endif #endif static int f2fs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct f2fs_fs_context *ctx = fc->fs_private; #ifdef CONFIG_F2FS_FS_COMPRESSION unsigned char (*ext)[F2FS_EXTENSION_LEN]; unsigned char (*noext)[F2FS_EXTENSION_LEN]; int ext_cnt, noext_cnt; char *name; #endif substring_t args[MAX_OPT_ARGS]; struct fs_parse_result result; int token, ret, arg; token = fs_parse(fc, f2fs_param_specs, param, &result); if (token < 0) return token; switch (token) { case Opt_gc_background: F2FS_CTX_INFO(ctx).bggc_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_background_gc; break; case Opt_disable_roll_forward: ctx_set_opt(ctx, F2FS_MOUNT_DISABLE_ROLL_FORWARD); break; case Opt_norecovery: /* requires ro mount, checked in f2fs_validate_options */ ctx_set_opt(ctx, F2FS_MOUNT_NORECOVERY); break; case Opt_discard: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_DISCARD); else ctx_set_opt(ctx, F2FS_MOUNT_DISCARD); break; case Opt_noheap: case Opt_heap: f2fs_warn(NULL, "heap/no_heap options were deprecated"); break; #ifdef CONFIG_F2FS_FS_XATTR case Opt_user_xattr: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_XATTR_USER); else ctx_set_opt(ctx, F2FS_MOUNT_XATTR_USER); break; case Opt_inline_xattr: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_INLINE_XATTR); else ctx_set_opt(ctx, F2FS_MOUNT_INLINE_XATTR); break; case Opt_inline_xattr_size: if (result.int_32 < MIN_INLINE_XATTR_SIZE || result.int_32 > MAX_INLINE_XATTR_SIZE) { f2fs_err(NULL, "inline xattr size is out of range: %u ~ %u", (u32)MIN_INLINE_XATTR_SIZE, (u32)MAX_INLINE_XATTR_SIZE); return -EINVAL; } ctx_set_opt(ctx, F2FS_MOUNT_INLINE_XATTR_SIZE); F2FS_CTX_INFO(ctx).inline_xattr_size = result.int_32; ctx->spec_mask |= F2FS_SPEC_inline_xattr_size; break; #else case Opt_user_xattr: case Opt_inline_xattr: case Opt_inline_xattr_size: f2fs_info(NULL, "%s options not supported", param->key); break; #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL case Opt_acl: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_POSIX_ACL); else ctx_set_opt(ctx, F2FS_MOUNT_POSIX_ACL); break; #else case Opt_acl: f2fs_info(NULL, "%s options not supported", param->key); break; #endif case Opt_active_logs: if (result.int_32 != 2 && result.int_32 != 4 && result.int_32 != NR_CURSEG_PERSIST_TYPE) return -EINVAL; ctx->spec_mask |= F2FS_SPEC_active_logs; F2FS_CTX_INFO(ctx).active_logs = result.int_32; break; case Opt_disable_ext_identify: ctx_set_opt(ctx, F2FS_MOUNT_DISABLE_EXT_IDENTIFY); break; case Opt_inline_data: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_INLINE_DATA); else ctx_set_opt(ctx, F2FS_MOUNT_INLINE_DATA); break; case Opt_inline_dentry: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_INLINE_DENTRY); else ctx_set_opt(ctx, F2FS_MOUNT_INLINE_DENTRY); break; case Opt_flush_merge: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_FLUSH_MERGE); else ctx_set_opt(ctx, F2FS_MOUNT_FLUSH_MERGE); break; case Opt_barrier: if (result.negated) ctx_set_opt(ctx, F2FS_MOUNT_NOBARRIER); else ctx_clear_opt(ctx, F2FS_MOUNT_NOBARRIER); break; case Opt_fastboot: ctx_set_opt(ctx, F2FS_MOUNT_FASTBOOT); break; case Opt_extent_cache: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_READ_EXTENT_CACHE); else ctx_set_opt(ctx, F2FS_MOUNT_READ_EXTENT_CACHE); break; case Opt_data_flush: ctx_set_opt(ctx, F2FS_MOUNT_DATA_FLUSH); break; case Opt_reserve_root: ctx_set_opt(ctx, F2FS_MOUNT_RESERVE_ROOT); F2FS_CTX_INFO(ctx).root_reserved_blocks = result.uint_32; ctx->spec_mask |= F2FS_SPEC_reserve_root; break; case Opt_reserve_node: ctx_set_opt(ctx, F2FS_MOUNT_RESERVE_NODE); F2FS_CTX_INFO(ctx).root_reserved_nodes = result.uint_32; ctx->spec_mask |= F2FS_SPEC_reserve_node; break; case Opt_resuid: F2FS_CTX_INFO(ctx).s_resuid = result.uid; ctx->spec_mask |= F2FS_SPEC_resuid; break; case Opt_resgid: F2FS_CTX_INFO(ctx).s_resgid = result.gid; ctx->spec_mask |= F2FS_SPEC_resgid; break; case Opt_mode: F2FS_CTX_INFO(ctx).fs_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_mode; break; #ifdef CONFIG_F2FS_FAULT_INJECTION case Opt_fault_injection: F2FS_CTX_INFO(ctx).fault_info.inject_rate = result.int_32; ctx->spec_mask |= F2FS_SPEC_fault_injection; ctx_set_opt(ctx, F2FS_MOUNT_FAULT_INJECTION); break; case Opt_fault_type: if (result.uint_32 > BIT(FAULT_MAX)) return -EINVAL; F2FS_CTX_INFO(ctx).fault_info.inject_type = result.uint_32; ctx->spec_mask |= F2FS_SPEC_fault_type; ctx_set_opt(ctx, F2FS_MOUNT_FAULT_INJECTION); break; #else case Opt_fault_injection: case Opt_fault_type: f2fs_info(NULL, "%s options not supported", param->key); break; #endif case Opt_lazytime: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_LAZYTIME); else ctx_set_opt(ctx, F2FS_MOUNT_LAZYTIME); break; #ifdef CONFIG_QUOTA case Opt_quota: if (result.negated) { ctx_clear_opt(ctx, F2FS_MOUNT_QUOTA); ctx_clear_opt(ctx, F2FS_MOUNT_USRQUOTA); ctx_clear_opt(ctx, F2FS_MOUNT_GRPQUOTA); ctx_clear_opt(ctx, F2FS_MOUNT_PRJQUOTA); } else ctx_set_opt(ctx, F2FS_MOUNT_USRQUOTA); break; case Opt_usrquota: ctx_set_opt(ctx, F2FS_MOUNT_USRQUOTA); break; case Opt_grpquota: ctx_set_opt(ctx, F2FS_MOUNT_GRPQUOTA); break; case Opt_prjquota: ctx_set_opt(ctx, F2FS_MOUNT_PRJQUOTA); break; case Opt_usrjquota: if (!*param->string) ret = f2fs_unnote_qf_name(fc, USRQUOTA); else ret = f2fs_note_qf_name(fc, USRQUOTA, param); if (ret) return ret; break; case Opt_grpjquota: if (!*param->string) ret = f2fs_unnote_qf_name(fc, GRPQUOTA); else ret = f2fs_note_qf_name(fc, GRPQUOTA, param); if (ret) return ret; break; case Opt_prjjquota: if (!*param->string) ret = f2fs_unnote_qf_name(fc, PRJQUOTA); else ret = f2fs_note_qf_name(fc, PRJQUOTA, param); if (ret) return ret; break; case Opt_jqfmt: F2FS_CTX_INFO(ctx).s_jquota_fmt = result.int_32; ctx->spec_mask |= F2FS_SPEC_jqfmt; break; #else case Opt_quota: case Opt_usrquota: case Opt_grpquota: case Opt_prjquota: case Opt_usrjquota: case Opt_grpjquota: case Opt_prjjquota: f2fs_info(NULL, "quota operations not supported"); break; #endif case Opt_alloc: F2FS_CTX_INFO(ctx).alloc_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_alloc_mode; break; case Opt_fsync: F2FS_CTX_INFO(ctx).fsync_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_fsync_mode; break; case Opt_test_dummy_encryption: ret = f2fs_parse_test_dummy_encryption(param, ctx); if (ret) return ret; break; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_opt(ctx, F2FS_MOUNT_INLINECRYPT); #else f2fs_info(NULL, "inline encryption not supported"); #endif break; case Opt_checkpoint: /* * Initialize args struct so we know whether arg was * found; some options take optional arguments. */ args[0].from = args[0].to = NULL; arg = 0; /* revert to match_table for checkpoint= options */ token = match_token(param->string, f2fs_checkpoint_tokens, args); switch (token) { case Opt_checkpoint_disable_cap_perc: if (args->from && match_int(args, &arg)) return -EINVAL; if (arg < 0 || arg > 100) return -EINVAL; F2FS_CTX_INFO(ctx).unusable_cap_perc = arg; ctx->spec_mask |= F2FS_SPEC_checkpoint_disable_cap_perc; ctx_set_opt(ctx, F2FS_MOUNT_DISABLE_CHECKPOINT); break; case Opt_checkpoint_disable_cap: if (args->from && match_int(args, &arg)) return -EINVAL; F2FS_CTX_INFO(ctx).unusable_cap = arg; ctx->spec_mask |= F2FS_SPEC_checkpoint_disable_cap; ctx_set_opt(ctx, F2FS_MOUNT_DISABLE_CHECKPOINT); break; case Opt_checkpoint_disable: ctx_set_opt(ctx, F2FS_MOUNT_DISABLE_CHECKPOINT); break; case Opt_checkpoint_enable: F2FS_CTX_INFO(ctx).unusable_cap_perc = 0; ctx->spec_mask |= F2FS_SPEC_checkpoint_disable_cap_perc; F2FS_CTX_INFO(ctx).unusable_cap = 0; ctx->spec_mask |= F2FS_SPEC_checkpoint_disable_cap; ctx_clear_opt(ctx, F2FS_MOUNT_DISABLE_CHECKPOINT); break; default: return -EINVAL; } break; case Opt_checkpoint_merge: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_MERGE_CHECKPOINT); else ctx_set_opt(ctx, F2FS_MOUNT_MERGE_CHECKPOINT); break; #ifdef CONFIG_F2FS_FS_COMPRESSION case Opt_compress_algorithm: name = param->string; if (!strcmp(name, "lzo")) { #ifdef CONFIG_F2FS_FS_LZO F2FS_CTX_INFO(ctx).compress_level = 0; F2FS_CTX_INFO(ctx).compress_algorithm = COMPRESS_LZO; ctx->spec_mask |= F2FS_SPEC_compress_level; ctx->spec_mask |= F2FS_SPEC_compress_algorithm; #else f2fs_info(NULL, "kernel doesn't support lzo compression"); #endif } else if (!strncmp(name, "lz4", 3)) { #ifdef CONFIG_F2FS_FS_LZ4 ret = f2fs_set_lz4hc_level(ctx, name); if (ret) return -EINVAL; F2FS_CTX_INFO(ctx).compress_algorithm = COMPRESS_LZ4; ctx->spec_mask |= F2FS_SPEC_compress_algorithm; #else f2fs_info(NULL, "kernel doesn't support lz4 compression"); #endif } else if (!strncmp(name, "zstd", 4)) { #ifdef CONFIG_F2FS_FS_ZSTD ret = f2fs_set_zstd_level(ctx, name); if (ret) return -EINVAL; F2FS_CTX_INFO(ctx).compress_algorithm = COMPRESS_ZSTD; ctx->spec_mask |= F2FS_SPEC_compress_algorithm; #else f2fs_info(NULL, "kernel doesn't support zstd compression"); #endif } else if (!strcmp(name, "lzo-rle")) { #ifdef CONFIG_F2FS_FS_LZORLE F2FS_CTX_INFO(ctx).compress_level = 0; F2FS_CTX_INFO(ctx).compress_algorithm = COMPRESS_LZORLE; ctx->spec_mask |= F2FS_SPEC_compress_level; ctx->spec_mask |= F2FS_SPEC_compress_algorithm; #else f2fs_info(NULL, "kernel doesn't support lzorle compression"); #endif } else return -EINVAL; break; case Opt_compress_log_size: if (result.uint_32 < MIN_COMPRESS_LOG_SIZE || result.uint_32 > MAX_COMPRESS_LOG_SIZE) { f2fs_err(NULL, "Compress cluster log size is out of range"); return -EINVAL; } F2FS_CTX_INFO(ctx).compress_log_size = result.uint_32; ctx->spec_mask |= F2FS_SPEC_compress_log_size; break; case Opt_compress_extension: name = param->string; ext = F2FS_CTX_INFO(ctx).extensions; ext_cnt = F2FS_CTX_INFO(ctx).compress_ext_cnt; if (strlen(name) >= F2FS_EXTENSION_LEN || ext_cnt >= COMPRESS_EXT_NUM) { f2fs_err(NULL, "invalid extension length/number"); return -EINVAL; } if (is_compress_extension_exist(&ctx->info, name, true)) break; ret = strscpy(ext[ext_cnt], name, F2FS_EXTENSION_LEN); if (ret < 0) return ret; F2FS_CTX_INFO(ctx).compress_ext_cnt++; ctx->spec_mask |= F2FS_SPEC_compress_extension; break; case Opt_nocompress_extension: name = param->string; noext = F2FS_CTX_INFO(ctx).noextensions; noext_cnt = F2FS_CTX_INFO(ctx).nocompress_ext_cnt; if (strlen(name) >= F2FS_EXTENSION_LEN || noext_cnt >= COMPRESS_EXT_NUM) { f2fs_err(NULL, "invalid extension length/number"); return -EINVAL; } if (is_compress_extension_exist(&ctx->info, name, false)) break; ret = strscpy(noext[noext_cnt], name, F2FS_EXTENSION_LEN); if (ret < 0) return ret; F2FS_CTX_INFO(ctx).nocompress_ext_cnt++; ctx->spec_mask |= F2FS_SPEC_nocompress_extension; break; case Opt_compress_chksum: F2FS_CTX_INFO(ctx).compress_chksum = true; ctx->spec_mask |= F2FS_SPEC_compress_chksum; break; case Opt_compress_mode: F2FS_CTX_INFO(ctx).compress_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_compress_mode; break; case Opt_compress_cache: ctx_set_opt(ctx, F2FS_MOUNT_COMPRESS_CACHE); break; #else case Opt_compress_algorithm: case Opt_compress_log_size: case Opt_compress_extension: case Opt_nocompress_extension: case Opt_compress_chksum: case Opt_compress_mode: case Opt_compress_cache: f2fs_info(NULL, "compression options not supported"); break; #endif case Opt_atgc: ctx_set_opt(ctx, F2FS_MOUNT_ATGC); break; case Opt_gc_merge: if (result.negated) ctx_clear_opt(ctx, F2FS_MOUNT_GC_MERGE); else ctx_set_opt(ctx, F2FS_MOUNT_GC_MERGE); break; case Opt_discard_unit: F2FS_CTX_INFO(ctx).discard_unit = result.uint_32; ctx->spec_mask |= F2FS_SPEC_discard_unit; break; case Opt_memory_mode: F2FS_CTX_INFO(ctx).memory_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_memory_mode; break; case Opt_age_extent_cache: ctx_set_opt(ctx, F2FS_MOUNT_AGE_EXTENT_CACHE); break; case Opt_errors: F2FS_CTX_INFO(ctx).errors = result.uint_32; ctx->spec_mask |= F2FS_SPEC_errors; break; case Opt_nat_bits: ctx_set_opt(ctx, F2FS_MOUNT_NAT_BITS); break; case Opt_lookup_mode: F2FS_CTX_INFO(ctx).lookup_mode = result.uint_32; ctx->spec_mask |= F2FS_SPEC_lookup_mode; break; } return 0; } /* * Check quota settings consistency. */ static int f2fs_check_quota_consistency(struct fs_context *fc, struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); #ifdef CONFIG_QUOTA struct f2fs_fs_context *ctx = fc->fs_private; bool quota_feature = f2fs_sb_has_quota_ino(sbi); bool quota_turnon = sb_any_quota_loaded(sb); char *old_qname, *new_qname; bool usr_qf_name, grp_qf_name, prj_qf_name, usrquota, grpquota, prjquota; int i; /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ if (ctx_test_opt(ctx, F2FS_MOUNT_PRJQUOTA) && !f2fs_sb_has_project_quota(sbi)) { f2fs_err(sbi, "Project quota feature not enabled. Cannot enable project quota enforcement."); return -EINVAL; } if (ctx->qname_mask) { for (i = 0; i < MAXQUOTAS; i++) { if (!(ctx->qname_mask & (1 << i))) continue; old_qname = F2FS_OPTION(sbi).s_qf_names[i]; new_qname = F2FS_CTX_INFO(ctx).s_qf_names[i]; if (quota_turnon && !!old_qname != !!new_qname) goto err_jquota_change; if (old_qname) { if (!new_qname) { f2fs_info(sbi, "remove qf_name %s", old_qname); continue; } else if (strcmp(old_qname, new_qname) == 0) { ctx->qname_mask &= ~(1 << i); continue; } goto err_jquota_specified; } if (quota_feature) { f2fs_info(sbi, "QUOTA feature is enabled, so ignore qf_name"); ctx->qname_mask &= ~(1 << i); kfree(F2FS_CTX_INFO(ctx).s_qf_names[i]); F2FS_CTX_INFO(ctx).s_qf_names[i] = NULL; } } } /* Make sure we don't mix old and new quota format */ usr_qf_name = F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || F2FS_CTX_INFO(ctx).s_qf_names[USRQUOTA]; grp_qf_name = F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || F2FS_CTX_INFO(ctx).s_qf_names[GRPQUOTA]; prj_qf_name = F2FS_OPTION(sbi).s_qf_names[PRJQUOTA] || F2FS_CTX_INFO(ctx).s_qf_names[PRJQUOTA]; usrquota = test_opt(sbi, USRQUOTA) || ctx_test_opt(ctx, F2FS_MOUNT_USRQUOTA); grpquota = test_opt(sbi, GRPQUOTA) || ctx_test_opt(ctx, F2FS_MOUNT_GRPQUOTA); prjquota = test_opt(sbi, PRJQUOTA) || ctx_test_opt(ctx, F2FS_MOUNT_PRJQUOTA); if (usr_qf_name) { ctx_clear_opt(ctx, F2FS_MOUNT_USRQUOTA); usrquota = false; } if (grp_qf_name) { ctx_clear_opt(ctx, F2FS_MOUNT_GRPQUOTA); grpquota = false; } if (prj_qf_name) { ctx_clear_opt(ctx, F2FS_MOUNT_PRJQUOTA); prjquota = false; } if (usr_qf_name || grp_qf_name || prj_qf_name) { if (grpquota || usrquota || prjquota) { f2fs_err(sbi, "old and new quota format mixing"); return -EINVAL; } if (!(ctx->spec_mask & F2FS_SPEC_jqfmt || F2FS_OPTION(sbi).s_jquota_fmt)) { f2fs_err(sbi, "journaled quota format not specified"); return -EINVAL; } } return 0; err_jquota_change: f2fs_err(sbi, "Cannot change journaled quota options when quota turned on"); return -EINVAL; err_jquota_specified: f2fs_err(sbi, "%s quota file already specified", QTYPE2NAME(i)); return -EINVAL; #else if (f2fs_readonly(sbi->sb)) return 0; if (f2fs_sb_has_quota_ino(sbi)) { f2fs_info(sbi, "Filesystem with quota feature cannot be mounted RDWR without CONFIG_QUOTA"); return -EINVAL; } if (f2fs_sb_has_project_quota(sbi)) { f2fs_err(sbi, "Filesystem with project quota feature cannot be mounted RDWR without CONFIG_QUOTA"); return -EINVAL; } return 0; #endif } static int f2fs_check_test_dummy_encryption(struct fs_context *fc, struct super_block *sb) { struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); if (!fscrypt_is_dummy_policy_set(&F2FS_CTX_INFO(ctx).dummy_enc_policy)) return 0; if (!f2fs_sb_has_encrypt(sbi)) { f2fs_err(sbi, "Encrypt feature is off"); return -EINVAL; } /* * This mount option is just for testing, and it's not worthwhile to * implement the extra complexity (e.g. RCU protection) that would be * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { if (fscrypt_dummy_policies_equal(&F2FS_OPTION(sbi).dummy_enc_policy, &F2FS_CTX_INFO(ctx).dummy_enc_policy)) return 0; f2fs_warn(sbi, "Can't set or change test_dummy_encryption on remount"); return -EINVAL; } return 0; } static inline bool test_compression_spec(unsigned int mask) { return mask & (F2FS_SPEC_compress_algorithm | F2FS_SPEC_compress_log_size | F2FS_SPEC_compress_extension | F2FS_SPEC_nocompress_extension | F2FS_SPEC_compress_chksum | F2FS_SPEC_compress_mode); } static inline void clear_compression_spec(struct f2fs_fs_context *ctx) { ctx->spec_mask &= ~(F2FS_SPEC_compress_algorithm | F2FS_SPEC_compress_log_size | F2FS_SPEC_compress_extension | F2FS_SPEC_nocompress_extension | F2FS_SPEC_compress_chksum | F2FS_SPEC_compress_mode); } static int f2fs_check_compression(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_F2FS_FS_COMPRESSION struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); int i, cnt; if (!f2fs_sb_has_compression(sbi)) { if (test_compression_spec(ctx->spec_mask) || ctx_test_opt(ctx, F2FS_MOUNT_COMPRESS_CACHE)) f2fs_info(sbi, "Image doesn't support compression"); clear_compression_spec(ctx); ctx->opt_mask &= ~F2FS_MOUNT_COMPRESS_CACHE; return 0; } if (ctx->spec_mask & F2FS_SPEC_compress_extension) { cnt = F2FS_CTX_INFO(ctx).compress_ext_cnt; for (i = 0; i < F2FS_CTX_INFO(ctx).compress_ext_cnt; i++) { if (is_compress_extension_exist(&F2FS_OPTION(sbi), F2FS_CTX_INFO(ctx).extensions[i], true)) { F2FS_CTX_INFO(ctx).extensions[i][0] = '\0'; cnt--; } } if (F2FS_OPTION(sbi).compress_ext_cnt + cnt > COMPRESS_EXT_NUM) { f2fs_err(sbi, "invalid extension length/number"); return -EINVAL; } } if (ctx->spec_mask & F2FS_SPEC_nocompress_extension) { cnt = F2FS_CTX_INFO(ctx).nocompress_ext_cnt; for (i = 0; i < F2FS_CTX_INFO(ctx).nocompress_ext_cnt; i++) { if (is_compress_extension_exist(&F2FS_OPTION(sbi), F2FS_CTX_INFO(ctx).noextensions[i], false)) { F2FS_CTX_INFO(ctx).noextensions[i][0] = '\0'; cnt--; } } if (F2FS_OPTION(sbi).nocompress_ext_cnt + cnt > COMPRESS_EXT_NUM) { f2fs_err(sbi, "invalid noextension length/number"); return -EINVAL; } } if (f2fs_test_compress_extension(F2FS_CTX_INFO(ctx).noextensions, F2FS_CTX_INFO(ctx).nocompress_ext_cnt, F2FS_CTX_INFO(ctx).extensions, F2FS_CTX_INFO(ctx).compress_ext_cnt)) { f2fs_err(sbi, "new noextensions conflicts with new extensions"); return -EINVAL; } if (f2fs_test_compress_extension(F2FS_CTX_INFO(ctx).noextensions, F2FS_CTX_INFO(ctx).nocompress_ext_cnt, F2FS_OPTION(sbi).extensions, F2FS_OPTION(sbi).compress_ext_cnt)) { f2fs_err(sbi, "new noextensions conflicts with old extensions"); return -EINVAL; } if (f2fs_test_compress_extension(F2FS_OPTION(sbi).noextensions, F2FS_OPTION(sbi).nocompress_ext_cnt, F2FS_CTX_INFO(ctx).extensions, F2FS_CTX_INFO(ctx).compress_ext_cnt)) { f2fs_err(sbi, "new extensions conflicts with old noextensions"); return -EINVAL; } #endif return 0; } static int f2fs_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); int err; if (ctx_test_opt(ctx, F2FS_MOUNT_NORECOVERY) && !f2fs_readonly(sb)) return -EINVAL; if (f2fs_hw_should_discard(sbi) && (ctx->opt_mask & F2FS_MOUNT_DISCARD) && !ctx_test_opt(ctx, F2FS_MOUNT_DISCARD)) { f2fs_warn(sbi, "discard is required for zoned block devices"); return -EINVAL; } if (!f2fs_hw_support_discard(sbi) && (ctx->opt_mask & F2FS_MOUNT_DISCARD) && ctx_test_opt(ctx, F2FS_MOUNT_DISCARD)) { f2fs_warn(sbi, "device does not support discard"); ctx_clear_opt(ctx, F2FS_MOUNT_DISCARD); ctx->opt_mask &= ~F2FS_MOUNT_DISCARD; } if (f2fs_sb_has_device_alias(sbi) && (ctx->opt_mask & F2FS_MOUNT_READ_EXTENT_CACHE) && !ctx_test_opt(ctx, F2FS_MOUNT_READ_EXTENT_CACHE)) { f2fs_err(sbi, "device aliasing requires extent cache"); return -EINVAL; } if (test_opt(sbi, RESERVE_ROOT) && (ctx->opt_mask & F2FS_MOUNT_RESERVE_ROOT) && ctx_test_opt(ctx, F2FS_MOUNT_RESERVE_ROOT)) { f2fs_info(sbi, "Preserve previous reserve_root=%u", F2FS_OPTION(sbi).root_reserved_blocks); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_ROOT); ctx->opt_mask &= ~F2FS_MOUNT_RESERVE_ROOT; } if (test_opt(sbi, RESERVE_NODE) && (ctx->opt_mask & F2FS_MOUNT_RESERVE_NODE) && ctx_test_opt(ctx, F2FS_MOUNT_RESERVE_NODE)) { f2fs_info(sbi, "Preserve previous reserve_node=%u", F2FS_OPTION(sbi).root_reserved_nodes); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_NODE); ctx->opt_mask &= ~F2FS_MOUNT_RESERVE_NODE; } err = f2fs_check_test_dummy_encryption(fc, sb); if (err) return err; err = f2fs_check_compression(fc, sb); if (err) return err; err = f2fs_check_quota_consistency(fc, sb); if (err) return err; if (!IS_ENABLED(CONFIG_UNICODE) && f2fs_sb_has_casefold(sbi)) { f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); return -EINVAL; } /* * The BLKZONED feature indicates that the drive was formatted with * zone alignment optimization. This is optional for host-aware * devices, but mandatory for host-managed zoned block devices. */ if (f2fs_sb_has_blkzoned(sbi)) { if (F2FS_CTX_INFO(ctx).bggc_mode == BGGC_MODE_OFF) { f2fs_warn(sbi, "zoned devices need bggc"); return -EINVAL; } #ifdef CONFIG_BLK_DEV_ZONED if ((ctx->spec_mask & F2FS_SPEC_discard_unit) && F2FS_CTX_INFO(ctx).discard_unit != DISCARD_UNIT_SECTION) { f2fs_info(sbi, "Zoned block device doesn't need small discard, set discard_unit=section by default"); F2FS_CTX_INFO(ctx).discard_unit = DISCARD_UNIT_SECTION; } if ((ctx->spec_mask & F2FS_SPEC_mode) && F2FS_CTX_INFO(ctx).fs_mode != FS_MODE_LFS) { f2fs_info(sbi, "Only lfs mode is allowed with zoned block device feature"); return -EINVAL; } #else f2fs_err(sbi, "Zoned block device support is not enabled"); return -EINVAL; #endif } if (ctx_test_opt(ctx, F2FS_MOUNT_INLINE_XATTR_SIZE)) { if (!f2fs_sb_has_extra_attr(sbi) || !f2fs_sb_has_flexible_inline_xattr(sbi)) { f2fs_err(sbi, "extra_attr or flexible_inline_xattr feature is off"); return -EINVAL; } if (!ctx_test_opt(ctx, F2FS_MOUNT_INLINE_XATTR) && !test_opt(sbi, INLINE_XATTR)) { f2fs_err(sbi, "inline_xattr_size option should be set with inline_xattr option"); return -EINVAL; } } if (ctx_test_opt(ctx, F2FS_MOUNT_ATGC) && F2FS_CTX_INFO(ctx).fs_mode == FS_MODE_LFS) { f2fs_err(sbi, "LFS is not compatible with ATGC"); return -EINVAL; } if (f2fs_is_readonly(sbi) && ctx_test_opt(ctx, F2FS_MOUNT_FLUSH_MERGE)) { f2fs_err(sbi, "FLUSH_MERGE not compatible with readonly mode"); return -EINVAL; } if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; } return 0; } static void f2fs_apply_quota_options(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); bool quota_feature = f2fs_sb_has_quota_ino(sbi); char *qname; int i; if (quota_feature) return; for (i = 0; i < MAXQUOTAS; i++) { if (!(ctx->qname_mask & (1 << i))) continue; qname = F2FS_CTX_INFO(ctx).s_qf_names[i]; if (qname) { qname = kstrdup(F2FS_CTX_INFO(ctx).s_qf_names[i], GFP_KERNEL | __GFP_NOFAIL); set_opt(sbi, QUOTA); } F2FS_OPTION(sbi).s_qf_names[i] = qname; } if (ctx->spec_mask & F2FS_SPEC_jqfmt) F2FS_OPTION(sbi).s_jquota_fmt = F2FS_CTX_INFO(ctx).s_jquota_fmt; if (quota_feature && F2FS_OPTION(sbi).s_jquota_fmt) { f2fs_info(sbi, "QUOTA feature is enabled, so ignore jquota_fmt"); F2FS_OPTION(sbi).s_jquota_fmt = 0; } #endif } static void f2fs_apply_test_dummy_encryption(struct fs_context *fc, struct super_block *sb) { struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); if (!fscrypt_is_dummy_policy_set(&F2FS_CTX_INFO(ctx).dummy_enc_policy) || /* if already set, it was already verified to be the same */ fscrypt_is_dummy_policy_set(&F2FS_OPTION(sbi).dummy_enc_policy)) return; swap(F2FS_OPTION(sbi).dummy_enc_policy, F2FS_CTX_INFO(ctx).dummy_enc_policy); f2fs_warn(sbi, "Test dummy encryption mode enabled"); } static void f2fs_apply_compression(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_F2FS_FS_COMPRESSION struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); unsigned char (*ctx_ext)[F2FS_EXTENSION_LEN]; unsigned char (*sbi_ext)[F2FS_EXTENSION_LEN]; int ctx_cnt, sbi_cnt, i; if (ctx->spec_mask & F2FS_SPEC_compress_level) F2FS_OPTION(sbi).compress_level = F2FS_CTX_INFO(ctx).compress_level; if (ctx->spec_mask & F2FS_SPEC_compress_algorithm) F2FS_OPTION(sbi).compress_algorithm = F2FS_CTX_INFO(ctx).compress_algorithm; if (ctx->spec_mask & F2FS_SPEC_compress_log_size) F2FS_OPTION(sbi).compress_log_size = F2FS_CTX_INFO(ctx).compress_log_size; if (ctx->spec_mask & F2FS_SPEC_compress_chksum) F2FS_OPTION(sbi).compress_chksum = F2FS_CTX_INFO(ctx).compress_chksum; if (ctx->spec_mask & F2FS_SPEC_compress_mode) F2FS_OPTION(sbi).compress_mode = F2FS_CTX_INFO(ctx).compress_mode; if (ctx->spec_mask & F2FS_SPEC_compress_extension) { ctx_ext = F2FS_CTX_INFO(ctx).extensions; ctx_cnt = F2FS_CTX_INFO(ctx).compress_ext_cnt; sbi_ext = F2FS_OPTION(sbi).extensions; sbi_cnt = F2FS_OPTION(sbi).compress_ext_cnt; for (i = 0; i < ctx_cnt; i++) { if (strlen(ctx_ext[i]) == 0) continue; strscpy(sbi_ext[sbi_cnt], ctx_ext[i]); sbi_cnt++; } F2FS_OPTION(sbi).compress_ext_cnt = sbi_cnt; } if (ctx->spec_mask & F2FS_SPEC_nocompress_extension) { ctx_ext = F2FS_CTX_INFO(ctx).noextensions; ctx_cnt = F2FS_CTX_INFO(ctx).nocompress_ext_cnt; sbi_ext = F2FS_OPTION(sbi).noextensions; sbi_cnt = F2FS_OPTION(sbi).nocompress_ext_cnt; for (i = 0; i < ctx_cnt; i++) { if (strlen(ctx_ext[i]) == 0) continue; strscpy(sbi_ext[sbi_cnt], ctx_ext[i]); sbi_cnt++; } F2FS_OPTION(sbi).nocompress_ext_cnt = sbi_cnt; } #endif } static void f2fs_apply_options(struct fs_context *fc, struct super_block *sb) { struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi = F2FS_SB(sb); F2FS_OPTION(sbi).opt &= ~ctx->opt_mask; F2FS_OPTION(sbi).opt |= F2FS_CTX_INFO(ctx).opt; if (ctx->spec_mask & F2FS_SPEC_background_gc) F2FS_OPTION(sbi).bggc_mode = F2FS_CTX_INFO(ctx).bggc_mode; if (ctx->spec_mask & F2FS_SPEC_inline_xattr_size) F2FS_OPTION(sbi).inline_xattr_size = F2FS_CTX_INFO(ctx).inline_xattr_size; if (ctx->spec_mask & F2FS_SPEC_active_logs) F2FS_OPTION(sbi).active_logs = F2FS_CTX_INFO(ctx).active_logs; if (ctx->spec_mask & F2FS_SPEC_reserve_root) F2FS_OPTION(sbi).root_reserved_blocks = F2FS_CTX_INFO(ctx).root_reserved_blocks; if (ctx->spec_mask & F2FS_SPEC_reserve_node) F2FS_OPTION(sbi).root_reserved_nodes = F2FS_CTX_INFO(ctx).root_reserved_nodes; if (ctx->spec_mask & F2FS_SPEC_resgid) F2FS_OPTION(sbi).s_resgid = F2FS_CTX_INFO(ctx).s_resgid; if (ctx->spec_mask & F2FS_SPEC_resuid) F2FS_OPTION(sbi).s_resuid = F2FS_CTX_INFO(ctx).s_resuid; if (ctx->spec_mask & F2FS_SPEC_mode) F2FS_OPTION(sbi).fs_mode = F2FS_CTX_INFO(ctx).fs_mode; #ifdef CONFIG_F2FS_FAULT_INJECTION if (ctx->spec_mask & F2FS_SPEC_fault_injection) (void)f2fs_build_fault_attr(sbi, F2FS_CTX_INFO(ctx).fault_info.inject_rate, 0, FAULT_RATE); if (ctx->spec_mask & F2FS_SPEC_fault_type) (void)f2fs_build_fault_attr(sbi, 0, F2FS_CTX_INFO(ctx).fault_info.inject_type, FAULT_TYPE); #endif if (ctx->spec_mask & F2FS_SPEC_alloc_mode) F2FS_OPTION(sbi).alloc_mode = F2FS_CTX_INFO(ctx).alloc_mode; if (ctx->spec_mask & F2FS_SPEC_fsync_mode) F2FS_OPTION(sbi).fsync_mode = F2FS_CTX_INFO(ctx).fsync_mode; if (ctx->spec_mask & F2FS_SPEC_checkpoint_disable_cap) F2FS_OPTION(sbi).unusable_cap = F2FS_CTX_INFO(ctx).unusable_cap; if (ctx->spec_mask & F2FS_SPEC_checkpoint_disable_cap_perc) F2FS_OPTION(sbi).unusable_cap_perc = F2FS_CTX_INFO(ctx).unusable_cap_perc; if (ctx->spec_mask & F2FS_SPEC_discard_unit) F2FS_OPTION(sbi).discard_unit = F2FS_CTX_INFO(ctx).discard_unit; if (ctx->spec_mask & F2FS_SPEC_memory_mode) F2FS_OPTION(sbi).memory_mode = F2FS_CTX_INFO(ctx).memory_mode; if (ctx->spec_mask & F2FS_SPEC_errors) F2FS_OPTION(sbi).errors = F2FS_CTX_INFO(ctx).errors; if (ctx->spec_mask & F2FS_SPEC_lookup_mode) F2FS_OPTION(sbi).lookup_mode = F2FS_CTX_INFO(ctx).lookup_mode; f2fs_apply_compression(fc, sb); f2fs_apply_test_dummy_encryption(fc, sb); f2fs_apply_quota_options(fc, sb); } static int f2fs_sanity_check_options(struct f2fs_sb_info *sbi, bool remount) { if (f2fs_sb_has_device_alias(sbi) && !test_opt(sbi, READ_EXTENT_CACHE)) { f2fs_err(sbi, "device aliasing requires extent cache"); return -EINVAL; } if (!remount) return 0; #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) { f2fs_err(sbi, "zoned: max open zones %u is too small, need at least %u open zones", sbi->max_open_zones, F2FS_OPTION(sbi).active_logs); return -EINVAL; } #endif if (f2fs_lfs_mode(sbi) && !IS_F2FS_IPU_DISABLE(sbi)) { f2fs_warn(sbi, "LFS is not compatible with IPU"); return -EINVAL; } return 0; } static struct inode *f2fs_alloc_inode(struct super_block *sb) { struct f2fs_inode_info *fi; if (time_to_inject(F2FS_SB(sb), FAULT_SLAB_ALLOC)) return NULL; fi = alloc_inode_sb(sb, f2fs_inode_cachep, GFP_F2FS_ZERO); if (!fi) return NULL; init_once((void *) fi); /* Initialize f2fs-specific inode info */ atomic_set(&fi->dirty_pages, 0); atomic_set(&fi->i_compr_blocks, 0); atomic_set(&fi->open_count, 0); init_f2fs_rwsem(&fi->i_sem); spin_lock_init(&fi->i_size_lock); INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->gdirty_list); INIT_LIST_HEAD(&fi->gdonate_list); init_f2fs_rwsem(&fi->i_gc_rwsem[READ]); init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]); init_f2fs_rwsem(&fi->i_xattr_sem); /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; return &fi->vfs_inode; } static int f2fs_drop_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; /* * during filesystem shutdown, if checkpoint is disabled, * drop useless meta/node dirty pages. */ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (inode->i_ino == F2FS_NODE_INO(sbi) || inode->i_ino == F2FS_META_INO(sbi)) { trace_f2fs_drop_inode(inode, 1); return 1; } } /* * This is to avoid a deadlock condition like below. * writeback_single_inode(inode) * - f2fs_write_data_page * - f2fs_gc -> iput -> evict * - inode_wait_for_writeback(inode) */ if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) { if (!inode->i_nlink && !is_bad_inode(inode)) { /* to avoid evict_inode call simultaneously */ __iget(inode); spin_unlock(&inode->i_lock); /* should remain fi->extent_tree for writepage */ f2fs_destroy_extent_node(inode); sb_start_intwrite(inode->i_sb); f2fs_i_size_write(inode, 0); f2fs_submit_merged_write_cond(F2FS_I_SB(inode), inode, NULL, 0, DATA); truncate_inode_pages_final(inode->i_mapping); if (F2FS_HAS_BLOCKS(inode)) f2fs_truncate(inode); sb_end_intwrite(inode->i_sb); spin_lock(&inode->i_lock); atomic_dec(&inode->i_count); } trace_f2fs_drop_inode(inode, 0); return 0; } ret = inode_generic_drop(inode); if (!ret) ret = fscrypt_drop_inode(inode); trace_f2fs_drop_inode(inode, ret); return ret; } int f2fs_inode_dirtied(struct inode *inode, bool sync) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret = 0; spin_lock(&sbi->inode_lock[DIRTY_META]); if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { ret = 1; } else { set_inode_flag(inode, FI_DIRTY_INODE); stat_inc_dirty_inode(sbi, DIRTY_META); } if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) { list_add_tail(&F2FS_I(inode)->gdirty_list, &sbi->inode_list[DIRTY_META]); inc_page_count(sbi, F2FS_DIRTY_IMETA); } spin_unlock(&sbi->inode_lock[DIRTY_META]); /* if atomic write is not committed, set inode w/ atomic dirty */ if (!ret && f2fs_is_atomic_file(inode) && !is_inode_flag_set(inode, FI_ATOMIC_COMMITTED)) set_inode_flag(inode, FI_ATOMIC_DIRTIED); return ret; } void f2fs_inode_synced(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); spin_lock(&sbi->inode_lock[DIRTY_META]); if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) { spin_unlock(&sbi->inode_lock[DIRTY_META]); return; } if (!list_empty(&F2FS_I(inode)->gdirty_list)) { list_del_init(&F2FS_I(inode)->gdirty_list); dec_page_count(sbi, F2FS_DIRTY_IMETA); } clear_inode_flag(inode, FI_DIRTY_INODE); clear_inode_flag(inode, FI_AUTO_RECOVER); stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META); spin_unlock(&sbi->inode_lock[DIRTY_META]); } /* * f2fs_dirty_inode() is called from __mark_inode_dirty() * * We should call set_dirty_inode to write the dirty inode through write_inode. */ static void f2fs_dirty_inode(struct inode *inode, int flags) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); if (inode->i_ino == F2FS_NODE_INO(sbi) || inode->i_ino == F2FS_META_INO(sbi)) return; if (is_inode_flag_set(inode, FI_AUTO_RECOVER)) clear_inode_flag(inode, FI_AUTO_RECOVER); f2fs_inode_dirtied(inode, false); } static void f2fs_free_inode(struct inode *inode) { fscrypt_free_inode(inode); kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode)); } static void destroy_percpu_info(struct f2fs_sb_info *sbi) { percpu_counter_destroy(&sbi->total_valid_inode_count); percpu_counter_destroy(&sbi->rf_node_block_count); percpu_counter_destroy(&sbi->alloc_valid_block_count); } static void destroy_device_list(struct f2fs_sb_info *sbi) { int i; for (i = 0; i < sbi->s_ndevs; i++) { if (i > 0) bdev_fput(FDEV(i).bdev_file); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif } kvfree(sbi->devs); } static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int i; int err = 0; bool done; /* unregister procfs/sysfs entries in advance to avoid race case */ f2fs_unregister_sysfs(sbi); f2fs_quota_off_umount(sb); /* prevent remaining shrinker jobs */ mutex_lock(&sbi->umount_mutex); /* * flush all issued checkpoints and stop checkpoint issue thread. * after then, all checkpoints should be done by each process context. */ f2fs_stop_ckpt_thread(sbi); /* * We don't need to do checkpoint when superblock is clean. * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. */ if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) || !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) { struct cp_control cpc = { .reason = CP_UMOUNT, }; stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); } /* be sure to wait for any on-going discard commands */ done = f2fs_issue_discard_timeout(sbi); if (f2fs_realtime_discard_enable(sbi) && !sbi->discard_blks && done) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); } /* * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. */ f2fs_release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); mutex_unlock(&sbi->umount_mutex); /* our cp_error case, we can wait for any writeback page */ f2fs_flush_merged_writes(sbi); f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); if (err || f2fs_cp_error(sbi)) { truncate_inode_pages_final(NODE_MAPPING(sbi)); truncate_inode_pages_final(META_MAPPING(sbi)); } for (i = 0; i < NR_COUNT_TYPE; i++) { if (!get_pages(sbi, i)) continue; f2fs_err(sbi, "detect filesystem reference count leak during " "umount, type: %d, count: %lld", i, get_pages(sbi, i)); f2fs_bug_on(sbi, 1); } f2fs_bug_on(sbi, sbi->fsync_node_num); f2fs_destroy_compress_inode(sbi); iput(sbi->node_inode); sbi->node_inode = NULL; iput(sbi->meta_inode); sbi->meta_inode = NULL; /* * iput() can update stat information, if f2fs_write_checkpoint() * above failed with error. */ f2fs_destroy_stats(sbi); /* destroy f2fs internal modules */ f2fs_destroy_node_manager(sbi); f2fs_destroy_segment_manager(sbi); /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); f2fs_destroy_post_read_wq(sbi); kvfree(sbi->ckpt); kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); f2fs_destroy_xattr_caches(sbi); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif fscrypt_free_dummy_policy(&F2FS_OPTION(sbi).dummy_enc_policy); destroy_percpu_info(sbi); f2fs_destroy_iostat(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kfree(sbi->write_io[i]); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif } int f2fs_sync_fs(struct super_block *sb, int sync) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int err = 0; if (unlikely(f2fs_cp_error(sbi))) return 0; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; trace_f2fs_sync_fs(sb, sync); if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return -EAGAIN; if (sync) { stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_issue_checkpoint(sbi); } return err; } static int f2fs_freeze(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); if (f2fs_readonly(sb)) return 0; /* IO error happened before */ if (unlikely(f2fs_cp_error(sbi))) return -EIO; /* must be clean, since sync_filesystem() was already called */ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY)) return -EINVAL; sbi->umount_lock_holder = current; /* Let's flush checkpoints and stop the thread. */ f2fs_flush_ckpt_thread(sbi); sbi->umount_lock_holder = NULL; /* to avoid deadlock on f2fs_evict_inode->SB_FREEZE_FS */ set_sbi_flag(sbi, SBI_IS_FREEZING); return 0; } static int f2fs_unfreeze(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); /* * It will update discard_max_bytes of mounted lvm device to zero * after creating snapshot on this lvm device, let's drop all * remained discards. * We don't need to disable real-time discard because discard_max_bytes * will recover after removal of snapshot. */ if (test_opt(sbi, DISCARD) && !f2fs_hw_support_discard(sbi)) f2fs_issue_discard_timeout(sbi); clear_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING); return 0; } #ifdef CONFIG_QUOTA static int f2fs_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) { struct kqid qid; struct dquot *dquot; u64 limit; u64 curblock; qid = make_kqid_projid(projid); dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit) { uint64_t remaining = 0; curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; if (limit > curblock) remaining = limit - curblock; buf->f_blocks = min(buf->f_blocks, limit); buf->f_bfree = min(buf->f_bfree, remaining); buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); if (limit) { uint64_t remaining = 0; if (limit > dquot->dq_dqb.dqb_curinodes) remaining = limit - dquot->dq_dqb.dqb_curinodes; buf->f_files = min(buf->f_files, limit); buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } #endif static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct f2fs_sb_info *sbi = F2FS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); block_t total_count, user_block_count, start_count; u64 avail_node_count; unsigned int total_valid_node_count; total_count = le64_to_cpu(sbi->raw_super->block_count); start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr); buf->f_type = F2FS_SUPER_MAGIC; buf->f_bsize = sbi->blocksize; buf->f_blocks = total_count - start_count; spin_lock(&sbi->stat_lock); if (sbi->carve_out) buf->f_blocks -= sbi->current_reserved_blocks; user_block_count = sbi->user_block_count; total_valid_node_count = valid_node_count(sbi); avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) buf->f_bfree = 0; else buf->f_bfree -= sbi->unusable_block_count; spin_unlock(&sbi->stat_lock); if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - F2FS_OPTION(sbi).root_reserved_blocks; else buf->f_bavail = 0; if (avail_node_count > user_block_count) { buf->f_files = user_block_count; buf->f_ffree = buf->f_bavail; } else { buf->f_files = avail_node_count; buf->f_ffree = min(avail_node_count - total_valid_node_count, buf->f_bavail); } buf->f_namelen = F2FS_NAME_LEN; buf->f_fsid = u64_to_fsid(id); #ifdef CONFIG_QUOTA if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) { f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf); } #endif return 0; } static inline void f2fs_show_quota_options(struct seq_file *seq, struct super_block *sb) { #ifdef CONFIG_QUOTA struct f2fs_sb_info *sbi = F2FS_SB(sb); if (F2FS_OPTION(sbi).s_jquota_fmt) { char *fmtname = ""; switch (F2FS_OPTION(sbi).s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA]) seq_show_option(seq, "usrjquota", F2FS_OPTION(sbi).s_qf_names[USRQUOTA]); if (F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]) seq_show_option(seq, "grpjquota", F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]); if (F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) seq_show_option(seq, "prjjquota", F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]); #endif } #ifdef CONFIG_F2FS_FS_COMPRESSION static inline void f2fs_show_compress_options(struct seq_file *seq, struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); char *algtype = ""; int i; if (!f2fs_sb_has_compression(sbi)) return; switch (F2FS_OPTION(sbi).compress_algorithm) { case COMPRESS_LZO: algtype = "lzo"; break; case COMPRESS_LZ4: algtype = "lz4"; break; case COMPRESS_ZSTD: algtype = "zstd"; break; case COMPRESS_LZORLE: algtype = "lzo-rle"; break; } seq_printf(seq, ",compress_algorithm=%s", algtype); if (F2FS_OPTION(sbi).compress_level) seq_printf(seq, ":%d", F2FS_OPTION(sbi).compress_level); seq_printf(seq, ",compress_log_size=%u", F2FS_OPTION(sbi).compress_log_size); for (i = 0; i < F2FS_OPTION(sbi).compress_ext_cnt; i++) { seq_printf(seq, ",compress_extension=%s", F2FS_OPTION(sbi).extensions[i]); } for (i = 0; i < F2FS_OPTION(sbi).nocompress_ext_cnt; i++) { seq_printf(seq, ",nocompress_extension=%s", F2FS_OPTION(sbi).noextensions[i]); } if (F2FS_OPTION(sbi).compress_chksum) seq_puts(seq, ",compress_chksum"); if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_FS) seq_printf(seq, ",compress_mode=%s", "fs"); else if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER) seq_printf(seq, ",compress_mode=%s", "user"); if (test_opt(sbi, COMPRESS_CACHE)) seq_puts(seq, ",compress_cache"); } #endif static int f2fs_show_options(struct seq_file *seq, struct dentry *root) { struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) seq_printf(seq, ",background_gc=%s", "sync"); else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_ON) seq_printf(seq, ",background_gc=%s", "on"); else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) seq_printf(seq, ",background_gc=%s", "off"); if (test_opt(sbi, GC_MERGE)) seq_puts(seq, ",gc_merge"); else seq_puts(seq, ",nogc_merge"); if (test_opt(sbi, DISABLE_ROLL_FORWARD)) seq_puts(seq, ",disable_roll_forward"); if (test_opt(sbi, NORECOVERY)) seq_puts(seq, ",norecovery"); if (test_opt(sbi, DISCARD)) { seq_puts(seq, ",discard"); if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK) seq_printf(seq, ",discard_unit=%s", "block"); else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT) seq_printf(seq, ",discard_unit=%s", "segment"); else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) seq_printf(seq, ",discard_unit=%s", "section"); } else { seq_puts(seq, ",nodiscard"); } #ifdef CONFIG_F2FS_FS_XATTR if (test_opt(sbi, XATTR_USER)) seq_puts(seq, ",user_xattr"); else seq_puts(seq, ",nouser_xattr"); if (test_opt(sbi, INLINE_XATTR)) seq_puts(seq, ",inline_xattr"); else seq_puts(seq, ",noinline_xattr"); if (test_opt(sbi, INLINE_XATTR_SIZE)) seq_printf(seq, ",inline_xattr_size=%u", F2FS_OPTION(sbi).inline_xattr_size); #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL if (test_opt(sbi, POSIX_ACL)) seq_puts(seq, ",acl"); else seq_puts(seq, ",noacl"); #endif if (test_opt(sbi, DISABLE_EXT_IDENTIFY)) seq_puts(seq, ",disable_ext_identify"); if (test_opt(sbi, INLINE_DATA)) seq_puts(seq, ",inline_data"); else seq_puts(seq, ",noinline_data"); if (test_opt(sbi, INLINE_DENTRY)) seq_puts(seq, ",inline_dentry"); else seq_puts(seq, ",noinline_dentry"); if (test_opt(sbi, FLUSH_MERGE)) seq_puts(seq, ",flush_merge"); else seq_puts(seq, ",noflush_merge"); if (test_opt(sbi, NOBARRIER)) seq_puts(seq, ",nobarrier"); else seq_puts(seq, ",barrier"); if (test_opt(sbi, FASTBOOT)) seq_puts(seq, ",fastboot"); if (test_opt(sbi, READ_EXTENT_CACHE)) seq_puts(seq, ",extent_cache"); else seq_puts(seq, ",noextent_cache"); if (test_opt(sbi, AGE_EXTENT_CACHE)) seq_puts(seq, ",age_extent_cache"); if (test_opt(sbi, DATA_FLUSH)) seq_puts(seq, ",data_flush"); seq_puts(seq, ",mode="); if (F2FS_OPTION(sbi).fs_mode == FS_MODE_ADAPTIVE) seq_puts(seq, "adaptive"); else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS) seq_puts(seq, "lfs"); else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG) seq_puts(seq, "fragment:segment"); else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) seq_puts(seq, "fragment:block"); seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT) || test_opt(sbi, RESERVE_NODE)) seq_printf(seq, ",reserve_root=%u,reserve_node=%u,resuid=%u," "resgid=%u", F2FS_OPTION(sbi).root_reserved_blocks, F2FS_OPTION(sbi).root_reserved_nodes, from_kuid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resuid), from_kgid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resgid)); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) { seq_printf(seq, ",fault_injection=%u", F2FS_OPTION(sbi).fault_info.inject_rate); seq_printf(seq, ",fault_type=%u", F2FS_OPTION(sbi).fault_info.inject_type); } #endif #ifdef CONFIG_QUOTA if (test_opt(sbi, QUOTA)) seq_puts(seq, ",quota"); if (test_opt(sbi, USRQUOTA)) seq_puts(seq, ",usrquota"); if (test_opt(sbi, GRPQUOTA)) seq_puts(seq, ",grpquota"); if (test_opt(sbi, PRJQUOTA)) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); if (sbi->sb->s_flags & SB_INLINECRYPT) seq_puts(seq, ",inlinecrypt"); if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT) seq_printf(seq, ",alloc_mode=%s", "default"); else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) seq_printf(seq, ",alloc_mode=%s", "reuse"); if (test_opt(sbi, DISABLE_CHECKPOINT)) seq_printf(seq, ",checkpoint=disable:%u", F2FS_OPTION(sbi).unusable_cap); if (test_opt(sbi, MERGE_CHECKPOINT)) seq_puts(seq, ",checkpoint_merge"); else seq_puts(seq, ",nocheckpoint_merge"); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) seq_printf(seq, ",fsync_mode=%s", "strict"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER) seq_printf(seq, ",fsync_mode=%s", "nobarrier"); #ifdef CONFIG_F2FS_FS_COMPRESSION f2fs_show_compress_options(seq, sbi->sb); #endif if (test_opt(sbi, ATGC)) seq_puts(seq, ",atgc"); if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_NORMAL) seq_printf(seq, ",memory=%s", "normal"); else if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW) seq_printf(seq, ",memory=%s", "low"); if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) seq_printf(seq, ",errors=%s", "remount-ro"); else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE) seq_printf(seq, ",errors=%s", "continue"); else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC) seq_printf(seq, ",errors=%s", "panic"); if (test_opt(sbi, NAT_BITS)) seq_puts(seq, ",nat_bits"); if (F2FS_OPTION(sbi).lookup_mode == LOOKUP_PERF) seq_show_option(seq, "lookup_mode", "perf"); else if (F2FS_OPTION(sbi).lookup_mode == LOOKUP_COMPAT) seq_show_option(seq, "lookup_mode", "compat"); else if (F2FS_OPTION(sbi).lookup_mode == LOOKUP_AUTO) seq_show_option(seq, "lookup_mode", "auto"); return 0; } static void default_options(struct f2fs_sb_info *sbi, bool remount) { /* init some FS parameters */ if (!remount) { set_opt(sbi, READ_EXTENT_CACHE); clear_opt(sbi, DISABLE_CHECKPOINT); if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; else F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; } if (f2fs_sb_has_readonly(sbi)) F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE; else F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE; F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_main) <= SMALL_VOLUME_SEGMENTS) F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; else F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); if (f2fs_sb_has_compression(sbi)) { F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4; F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE; F2FS_OPTION(sbi).compress_ext_cnt = 0; F2FS_OPTION(sbi).compress_mode = COMPR_MODE_FS; } F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL; F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE; set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); set_opt(sbi, MERGE_CHECKPOINT); set_opt(sbi, LAZYTIME); F2FS_OPTION(sbi).unusable_cap = 0; if (!f2fs_is_readonly(sbi)) set_opt(sbi, FLUSH_MERGE); if (f2fs_sb_has_blkzoned(sbi)) F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; else F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL set_opt(sbi, POSIX_ACL); #endif f2fs_build_fault_attr(sbi, 0, 0, FAULT_ALL); F2FS_OPTION(sbi).lookup_mode = LOOKUP_PERF; } #ifdef CONFIG_QUOTA static int f2fs_enable_quotas(struct super_block *sb); #endif static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) { unsigned int s_flags = sbi->sb->s_flags; struct cp_control cpc; unsigned int gc_mode = sbi->gc_mode; int err = 0; int ret; block_t unusable; if (s_flags & SB_RDONLY) { f2fs_err(sbi, "checkpoint=disable on readonly fs"); return -EINVAL; } sbi->sb->s_flags |= SB_ACTIVE; /* check if we need more GC first */ unusable = f2fs_get_unusable_blocks(sbi); if (!f2fs_disable_cp_again(sbi, unusable)) goto skip_gc; f2fs_update_time(sbi, DISABLE_TIME); sbi->gc_mode = GC_URGENT_HIGH; while (!f2fs_time_over(sbi, DISABLE_TIME)) { struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, .init_gc_type = FG_GC, .should_migrate_blocks = false, .err_gc_skipped = true, .no_bg_gc = true, .nr_free_secs = 1 }; f2fs_down_write(&sbi->gc_lock); stat_inc_gc_call_count(sbi, FOREGROUND); err = f2fs_gc(sbi, &gc_control); if (err == -ENODATA) { err = 0; break; } if (err && err != -EAGAIN) break; } ret = sync_filesystem(sbi->sb); if (ret || err) { err = ret ? ret : err; goto restore_flag; } unusable = f2fs_get_unusable_blocks(sbi); if (f2fs_disable_cp_again(sbi, unusable)) { err = -EAGAIN; goto restore_flag; } skip_gc: f2fs_down_write(&sbi->gc_lock); cpc.reason = CP_PAUSE; set_sbi_flag(sbi, SBI_CP_DISABLED); stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); if (err) goto out_unlock; spin_lock(&sbi->stat_lock); sbi->unusable_block_count = unusable; spin_unlock(&sbi->stat_lock); out_unlock: f2fs_up_write(&sbi->gc_lock); restore_flag: sbi->gc_mode = gc_mode; sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */ f2fs_info(sbi, "f2fs_disable_checkpoint() finish, err:%d", err); return err; } static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) { unsigned int nr_pages = get_pages(sbi, F2FS_DIRTY_DATA) / 16; long long start, writeback, end; f2fs_info(sbi, "f2fs_enable_checkpoint() starts, meta: %lld, node: %lld, data: %lld", get_pages(sbi, F2FS_DIRTY_META), get_pages(sbi, F2FS_DIRTY_NODES), get_pages(sbi, F2FS_DIRTY_DATA)); f2fs_update_time(sbi, ENABLE_TIME); start = ktime_get(); /* we should flush all the data to keep data consistency */ while (get_pages(sbi, F2FS_DIRTY_DATA)) { writeback_inodes_sb_nr(sbi->sb, nr_pages, WB_REASON_SYNC); f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); if (f2fs_time_over(sbi, ENABLE_TIME)) break; } writeback = ktime_get(); sync_inodes_sb(sbi->sb); if (unlikely(get_pages(sbi, F2FS_DIRTY_DATA))) f2fs_warn(sbi, "checkpoint=enable has some unwritten data: %lld", get_pages(sbi, F2FS_DIRTY_DATA)); f2fs_down_write(&sbi->gc_lock); f2fs_dirty_to_prefree(sbi); clear_sbi_flag(sbi, SBI_CP_DISABLED); set_sbi_flag(sbi, SBI_IS_DIRTY); f2fs_up_write(&sbi->gc_lock); f2fs_sync_fs(sbi->sb, 1); /* Let's ensure there's no pending checkpoint anymore */ f2fs_flush_ckpt_thread(sbi); end = ktime_get(); f2fs_info(sbi, "f2fs_enable_checkpoint() finishes, writeback:%llu, sync:%llu", ktime_ms_delta(writeback, start), ktime_ms_delta(end, writeback)); } static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); struct f2fs_mount_info org_mount_opt; unsigned long old_sb_flags; unsigned int flags = fc->sb_flags; int err; bool need_restart_gc = false, need_stop_gc = false; bool need_restart_flush = false, need_stop_flush = false; bool need_restart_discard = false, need_stop_discard = false; bool need_enable_checkpoint = false, need_disable_checkpoint = false; bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE); bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE); bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT); bool no_atgc = !test_opt(sbi, ATGC); bool no_discard = !test_opt(sbi, DISCARD); bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE); bool block_unit_discard = f2fs_block_unit_discard(sbi); bool no_nat_bits = !test_opt(sbi, NAT_BITS); #ifdef CONFIG_QUOTA int i, j; #endif /* * Save the old mount options in case we * need to restore them. */ org_mount_opt = sbi->mount_opt; old_sb_flags = sb->s_flags; sbi->umount_lock_holder = current; #ifdef CONFIG_QUOTA org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { if (F2FS_OPTION(sbi).s_qf_names[i]) { org_mount_opt.s_qf_names[i] = kstrdup(F2FS_OPTION(sbi).s_qf_names[i], GFP_KERNEL); if (!org_mount_opt.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(org_mount_opt.s_qf_names[j]); return -ENOMEM; } } else { org_mount_opt.s_qf_names[i] = NULL; } } #endif /* recover superblocks we couldn't write due to previous RO mount */ if (!(flags & SB_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { err = f2fs_commit_super(sbi, false); f2fs_info(sbi, "Try to recover all the superblocks, ret: %d", err); if (!err) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } default_options(sbi, true); err = f2fs_check_opt_consistency(fc, sb); if (err) goto restore_opts; f2fs_apply_options(fc, sb); err = f2fs_sanity_check_options(sbi, true); if (err) goto restore_opts; /* flush outstanding errors before changing fs state */ flush_work(&sbi->s_error_work); /* * Previous and new state of filesystem is RO, * so skip checking GC and FLUSH_MERGE conditions. */ if (f2fs_readonly(sb) && (flags & SB_RDONLY)) goto skip; if (f2fs_dev_is_readonly(sbi) && !(flags & SB_RDONLY)) { err = -EROFS; goto restore_opts; } #ifdef CONFIG_QUOTA if (!f2fs_readonly(sb) && (flags & SB_RDONLY)) { err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; } else if (f2fs_readonly(sb) && !(flags & SB_RDONLY)) { /* dquot_resume needs RW */ sb->s_flags &= ~SB_RDONLY; if (sb_any_quota_suspended(sb)) { dquot_resume(sb, -1); } else if (f2fs_sb_has_quota_ino(sbi)) { err = f2fs_enable_quotas(sb); if (err) goto restore_opts; } } #endif /* disallow enable atgc dynamically */ if (no_atgc == !!test_opt(sbi, ATGC)) { err = -EINVAL; f2fs_warn(sbi, "switch atgc option is not allowed"); goto restore_opts; } /* disallow enable/disable extent_cache dynamically */ if (no_read_extent_cache == !!test_opt(sbi, READ_EXTENT_CACHE)) { err = -EINVAL; f2fs_warn(sbi, "switch extent_cache option is not allowed"); goto restore_opts; } /* disallow enable/disable age extent_cache dynamically */ if (no_age_extent_cache == !!test_opt(sbi, AGE_EXTENT_CACHE)) { err = -EINVAL; f2fs_warn(sbi, "switch age_extent_cache option is not allowed"); goto restore_opts; } if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) { err = -EINVAL; f2fs_warn(sbi, "switch compress_cache option is not allowed"); goto restore_opts; } if (block_unit_discard != f2fs_block_unit_discard(sbi)) { err = -EINVAL; f2fs_warn(sbi, "switch discard_unit option is not allowed"); goto restore_opts; } if (no_nat_bits == !!test_opt(sbi, NAT_BITS)) { err = -EINVAL; f2fs_warn(sbi, "switch nat_bits option is not allowed"); goto restore_opts; } if ((flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { err = -EINVAL; f2fs_warn(sbi, "disabling checkpoint not compatible with read-only"); goto restore_opts; } /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount * option. Also sync the filesystem. */ if ((flags & SB_RDONLY) || (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF && !test_opt(sbi, GC_MERGE))) { if (sbi->gc_thread) { f2fs_stop_gc_thread(sbi); need_restart_gc = true; } } else if (!sbi->gc_thread) { err = f2fs_start_gc_thread(sbi); if (err) goto restore_opts; need_stop_gc = true; } if (flags & SB_RDONLY) { sync_inodes_sb(sb); set_sbi_flag(sbi, SBI_IS_DIRTY); set_sbi_flag(sbi, SBI_IS_CLOSE); f2fs_sync_fs(sb, 1); clear_sbi_flag(sbi, SBI_IS_CLOSE); } /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. */ if ((flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { clear_opt(sbi, FLUSH_MERGE); f2fs_destroy_flush_cmd_control(sbi, false); need_restart_flush = true; } else { err = f2fs_create_flush_cmd_control(sbi); if (err) goto restore_gc; need_stop_flush = true; } if (no_discard == !!test_opt(sbi, DISCARD)) { if (test_opt(sbi, DISCARD)) { err = f2fs_start_discard_thread(sbi); if (err) goto restore_flush; need_stop_discard = true; } else { f2fs_stop_discard_thread(sbi); f2fs_issue_discard_timeout(sbi); need_restart_discard = true; } } adjust_unusable_cap_perc(sbi); if (enable_checkpoint == !!test_opt(sbi, DISABLE_CHECKPOINT)) { if (test_opt(sbi, DISABLE_CHECKPOINT)) { err = f2fs_disable_checkpoint(sbi); if (err) goto restore_discard; need_enable_checkpoint = true; } else { f2fs_enable_checkpoint(sbi); need_disable_checkpoint = true; } } /* * Place this routine at the end, since a new checkpoint would be * triggered while remount and we need to take care of it before * returning from remount. */ if ((flags & SB_RDONLY) || test_opt(sbi, DISABLE_CHECKPOINT) || !test_opt(sbi, MERGE_CHECKPOINT)) { f2fs_stop_ckpt_thread(sbi); } else { /* Flush if the previous checkpoint, if exists. */ f2fs_flush_ckpt_thread(sbi); err = f2fs_start_ckpt_thread(sbi); if (err) { f2fs_err(sbi, "Failed to start F2FS issue_checkpoint_thread (%d)", err); goto restore_checkpoint; } } skip: #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) kfree(org_mount_opt.s_qf_names[i]); #endif /* Update the POSIXACL Flag */ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); limit_reserve_root(sbi); fc->sb_flags = (flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); sbi->umount_lock_holder = NULL; return 0; restore_checkpoint: if (need_enable_checkpoint) { f2fs_enable_checkpoint(sbi); } else if (need_disable_checkpoint) { if (f2fs_disable_checkpoint(sbi)) f2fs_warn(sbi, "checkpoint has not been disabled"); } restore_discard: if (need_restart_discard) { if (f2fs_start_discard_thread(sbi)) f2fs_warn(sbi, "discard has been stopped"); } else if (need_stop_discard) { f2fs_stop_discard_thread(sbi); } restore_flush: if (need_restart_flush) { if (f2fs_create_flush_cmd_control(sbi)) f2fs_warn(sbi, "background flush thread has stopped"); } else if (need_stop_flush) { clear_opt(sbi, FLUSH_MERGE); f2fs_destroy_flush_cmd_control(sbi, false); } restore_gc: if (need_restart_gc) { if (f2fs_start_gc_thread(sbi)) f2fs_warn(sbi, "background gc thread has stopped"); } else if (need_stop_gc) { f2fs_stop_gc_thread(sbi); } restore_opts: #ifdef CONFIG_QUOTA F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { kfree(F2FS_OPTION(sbi).s_qf_names[i]); F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i]; } #endif sbi->mount_opt = org_mount_opt; sb->s_flags = old_sb_flags; sbi->umount_lock_holder = NULL; return err; } static void f2fs_shutdown(struct super_block *sb) { f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false, false); } #ifdef CONFIG_QUOTA static bool f2fs_need_recovery(struct f2fs_sb_info *sbi) { /* need to recovery orphan */ if (is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return true; /* need to recovery data */ if (test_opt(sbi, DISABLE_ROLL_FORWARD)) return false; if (test_opt(sbi, NORECOVERY)) return false; return !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG); } static bool f2fs_recover_quota_begin(struct f2fs_sb_info *sbi) { bool readonly = f2fs_readonly(sbi->sb); if (!f2fs_need_recovery(sbi)) return false; /* it doesn't need to check f2fs_sb_has_readonly() */ if (f2fs_hw_is_readonly(sbi)) return false; if (readonly) { sbi->sb->s_flags &= ~SB_RDONLY; set_sbi_flag(sbi, SBI_IS_WRITABLE); } /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. */ return f2fs_enable_quota_files(sbi, readonly); } static void f2fs_recover_quota_end(struct f2fs_sb_info *sbi, bool quota_enabled) { if (quota_enabled) f2fs_quota_off_umount(sbi->sb); if (is_sbi_flag_set(sbi, SBI_IS_WRITABLE)) { clear_sbi_flag(sbi, SBI_IS_WRITABLE); sbi->sb->s_flags |= SB_RDONLY; } } /* Read data from quotafile */ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; struct address_space *mapping = inode->i_mapping; int tocopy; size_t toread; loff_t i_size = i_size_read(inode); if (off > i_size) return 0; if (off + len > i_size) len = i_size - off; toread = len; while (toread > 0) { struct folio *folio; size_t offset; repeat: folio = mapping_read_folio_gfp(mapping, off >> PAGE_SHIFT, GFP_NOFS); if (IS_ERR(folio)) { if (PTR_ERR(folio) == -ENOMEM) { memalloc_retry_wait(GFP_NOFS); goto repeat; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return PTR_ERR(folio); } offset = offset_in_folio(folio, off); tocopy = min(folio_size(folio) - offset, toread); folio_lock(folio); if (unlikely(folio->mapping != mapping)) { f2fs_folio_put(folio, true); goto repeat; } /* * should never happen, just leave f2fs_bug_on() here to catch * any potential bug. */ f2fs_bug_on(F2FS_SB(sb), !folio_test_uptodate(folio)); memcpy_from_folio(data, folio, offset, tocopy); f2fs_folio_put(folio, true); toread -= tocopy; data += tocopy; off += tocopy; } return len; } /* Write to quotafile */ static ssize_t f2fs_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; struct address_space *mapping = inode->i_mapping; const struct address_space_operations *a_ops = mapping->a_ops; int offset = off & (sb->s_blocksize - 1); size_t towrite = len; struct folio *folio; void *fsdata = NULL; int err = 0; int tocopy; while (towrite > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, towrite); retry: err = a_ops->write_begin(NULL, mapping, off, tocopy, &folio, &fsdata); if (unlikely(err)) { if (err == -ENOMEM) { f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); break; } memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, folio, fsdata); offset = 0; towrite -= tocopy; off += tocopy; data += tocopy; cond_resched(); } if (len == towrite) return err; inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); return len - towrite; } int f2fs_dquot_initialize(struct inode *inode) { if (time_to_inject(F2FS_I_SB(inode), FAULT_DQUOT_INIT)) return -ESRCH; return dquot_initialize(inode); } static struct dquot __rcu **f2fs_get_dquots(struct inode *inode) { return F2FS_I(inode)->i_dquot; } static qsize_t *f2fs_get_reserved_space(struct inode *inode) { return &F2FS_I(inode)->i_reserved_quota; } static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { f2fs_err(sbi, "quota sysfile may be corrupted, skip loading it"); return 0; } return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], F2FS_OPTION(sbi).s_jquota_fmt, type); } int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) { int enabled = 0; int i, err; if (f2fs_sb_has_quota_ino(sbi) && rdonly) { err = f2fs_enable_quotas(sbi->sb); if (err) { f2fs_err(sbi, "Cannot turn on quota_ino: %d", err); return 0; } return 1; } for (i = 0; i < MAXQUOTAS; i++) { if (F2FS_OPTION(sbi).s_qf_names[i]) { err = f2fs_quota_on_mount(sbi, i); if (!err) { enabled = 1; continue; } f2fs_err(sbi, "Cannot turn on quotas: %d on %d", err, i); } } return enabled; } static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { struct inode *qf_inode; unsigned long qf_inum; unsigned long qf_flag = F2FS_QUOTA_DEFAULT_FL; int err; BUG_ON(!f2fs_sb_has_quota_ino(F2FS_SB(sb))); qf_inum = f2fs_qf_ino(sb, type); if (!qf_inum) return -EPERM; qf_inode = f2fs_iget(sb, qf_inum); if (IS_ERR(qf_inode)) { f2fs_err(F2FS_SB(sb), "Bad quota inode %u:%lu", type, qf_inum); return PTR_ERR(qf_inode); } /* Don't account quota for quota files to avoid recursion */ inode_lock(qf_inode); qf_inode->i_flags |= S_NOQUOTA; if ((F2FS_I(qf_inode)->i_flags & qf_flag) != qf_flag) { F2FS_I(qf_inode)->i_flags |= qf_flag; f2fs_set_inode_flags(qf_inode); } inode_unlock(qf_inode); err = dquot_load_quota_inode(qf_inode, type, format_id, flags); iput(qf_inode); return err; } static int f2fs_enable_quotas(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int type, err = 0; unsigned long qf_inum; bool quota_mopt[MAXQUOTAS] = { test_opt(sbi, USRQUOTA), test_opt(sbi, GRPQUOTA), test_opt(sbi, PRJQUOTA), }; if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { f2fs_err(sbi, "quota file may be corrupted, skip loading it"); return 0; } sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; for (type = 0; type < MAXQUOTAS; type++) { qf_inum = f2fs_qf_ino(sb, type); if (qf_inum) { err = f2fs_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { f2fs_err(sbi, "Failed to enable quota tracking (type=%d, err=%d). Please run fsck to fix.", type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return err; } } } return 0; } static int f2fs_quota_sync_file(struct f2fs_sb_info *sbi, int type) { struct quota_info *dqopt = sb_dqopt(sbi->sb); struct address_space *mapping = dqopt->files[type]->i_mapping; int ret = 0; ret = dquot_writeback_dquots(sbi->sb, type); if (ret) goto out; ret = filemap_fdatawrite(mapping); if (ret) goto out; /* if we are using journalled quota */ if (is_journalled_quota(sbi)) goto out; ret = filemap_fdatawait(mapping); truncate_inode_pages(&dqopt->files[type]->i_data, 0); out: if (ret) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); return ret; } int f2fs_do_quota_sync(struct super_block *sb, int type) { struct f2fs_sb_info *sbi = F2FS_SB(sb); struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret = 0; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; if (!f2fs_sb_has_quota_ino(sbi)) inode_lock(dqopt->files[cnt]); /* * do_quotactl * f2fs_quota_sync * f2fs_down_read(quota_sem) * dquot_writeback_dquots() * f2fs_dquot_commit * block_operation * f2fs_down_read(quota_sem) */ f2fs_lock_op(sbi); f2fs_down_read(&sbi->quota_sem); ret = f2fs_quota_sync_file(sbi, cnt); f2fs_up_read(&sbi->quota_sem); f2fs_unlock_op(sbi); if (!f2fs_sb_has_quota_ino(sbi)) inode_unlock(dqopt->files[cnt]); if (ret) break; } return ret; } static int f2fs_quota_sync(struct super_block *sb, int type) { int ret; F2FS_SB(sb)->umount_lock_holder = current; ret = f2fs_do_quota_sync(sb, type); F2FS_SB(sb)->umount_lock_holder = NULL; return ret; } static int f2fs_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { struct inode *inode; int err = 0; /* if quota sysfile exists, deny enabling quota with specific file */ if (f2fs_sb_has_quota_ino(F2FS_SB(sb))) { f2fs_err(F2FS_SB(sb), "quota sysfile already exists"); return -EBUSY; } if (path->dentry->d_sb != sb) return -EXDEV; F2FS_SB(sb)->umount_lock_holder = current; err = f2fs_do_quota_sync(sb, type); if (err) goto out; inode = d_inode(path->dentry); err = filemap_fdatawrite(inode->i_mapping); if (err) goto out; err = filemap_fdatawait(inode->i_mapping); if (err) goto out; err = dquot_quota_on(sb, type, format_id, path); if (err) goto out; inode_lock(inode); F2FS_I(inode)->i_flags |= F2FS_QUOTA_DEFAULT_FL; f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out: F2FS_SB(sb)->umount_lock_holder = NULL; return err; } static int __f2fs_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; int err; if (!inode || !igrab(inode)) return dquot_quota_off(sb, type); err = f2fs_do_quota_sync(sb, type); if (err) goto out_put; err = dquot_quota_off(sb, type); if (err || f2fs_sb_has_quota_ino(F2FS_SB(sb))) goto out_put; inode_lock(inode); F2FS_I(inode)->i_flags &= ~F2FS_QUOTA_DEFAULT_FL; f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out_put: iput(inode); return err; } static int f2fs_quota_off(struct super_block *sb, int type) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int err; F2FS_SB(sb)->umount_lock_holder = current; err = __f2fs_quota_off(sb, type); /* * quotactl can shutdown journalled quota, result in inconsistence * between quota record and fs data by following updates, tag the * flag to let fsck be aware of it. */ if (is_journalled_quota(sbi)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); F2FS_SB(sb)->umount_lock_holder = NULL; return err; } void f2fs_quota_off_umount(struct super_block *sb) { int type; int err; for (type = 0; type < MAXQUOTAS; type++) { err = __f2fs_quota_off(sb, type); if (err) { int ret = dquot_quota_off(sb, type); f2fs_err(F2FS_SB(sb), "Fail to turn off disk quota (type: %d, err: %d, ret:%d), Please run fsck to fix it.", type, err, ret); set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } /* * In case of checkpoint=disable, we must flush quota blocks. * This can cause NULL exception for node_inode in end_io, since * put_super already dropped it. */ sync_filesystem(sb); } static void f2fs_truncate_quota_inode_pages(struct super_block *sb) { struct quota_info *dqopt = sb_dqopt(sb); int type; for (type = 0; type < MAXQUOTAS; type++) { if (!dqopt->files[type]) continue; f2fs_inode_synced(dqopt->files[type]); } } static int f2fs_dquot_commit(struct dquot *dquot) { struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret; f2fs_down_read_nested(&sbi->quota_sem, SINGLE_DEPTH_NESTING); ret = dquot_commit(dquot); if (ret < 0) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); f2fs_up_read(&sbi->quota_sem); return ret; } static int f2fs_dquot_acquire(struct dquot *dquot) { struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret; f2fs_down_read(&sbi->quota_sem); ret = dquot_acquire(dquot); if (ret < 0) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); f2fs_up_read(&sbi->quota_sem); return ret; } static int f2fs_dquot_release(struct dquot *dquot) { struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret = dquot_release(dquot); if (ret < 0) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); return ret; } static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; struct f2fs_sb_info *sbi = F2FS_SB(sb); int ret = dquot_mark_dquot_dirty(dquot); /* if we are using journalled quota */ if (is_journalled_quota(sbi)) set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); return ret; } static int f2fs_dquot_commit_info(struct super_block *sb, int type) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int ret = dquot_commit_info(sb, type); if (ret < 0) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); return ret; } static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) { *projid = F2FS_I(inode)->i_projid; return 0; } static const struct dquot_operations f2fs_quota_operations = { .get_reserved_space = f2fs_get_reserved_space, .write_dquot = f2fs_dquot_commit, .acquire_dquot = f2fs_dquot_acquire, .release_dquot = f2fs_dquot_release, .mark_dirty = f2fs_dquot_mark_dquot_dirty, .write_info = f2fs_dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = f2fs_get_projid, .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops f2fs_quotactl_ops = { .quota_on = f2fs_quota_on, .quota_off = f2fs_quota_off, .quota_sync = f2fs_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, .get_nextdqblk = dquot_get_next_dqblk, }; #else int f2fs_dquot_initialize(struct inode *inode) { return 0; } int f2fs_do_quota_sync(struct super_block *sb, int type) { return 0; } void f2fs_quota_off_umount(struct super_block *sb) { } #endif static const struct super_operations f2fs_sops = { .alloc_inode = f2fs_alloc_inode, .free_inode = f2fs_free_inode, .drop_inode = f2fs_drop_inode, .write_inode = f2fs_write_inode, .dirty_inode = f2fs_dirty_inode, .show_options = f2fs_show_options, #ifdef CONFIG_QUOTA .quota_read = f2fs_quota_read, .quota_write = f2fs_quota_write, .get_dquots = f2fs_get_dquots, #endif .evict_inode = f2fs_evict_inode, .put_super = f2fs_put_super, .sync_fs = f2fs_sync_fs, .freeze_fs = f2fs_freeze, .unfreeze_fs = f2fs_unfreeze, .statfs = f2fs_statfs, .shutdown = f2fs_shutdown, }; #ifdef CONFIG_FS_ENCRYPTION static int f2fs_get_context(struct inode *inode, void *ctx, size_t len) { return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, NULL); } static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); /* * Encrypting the root directory is not allowed because fsck * expects lost+found directory to exist and remain unencrypted * if LOST_FOUND feature is enabled. * */ if (f2fs_sb_has_lost_found(sbi) && inode->i_ino == F2FS_ROOT_INO(sbi)) return -EPERM; return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, fs_data, XATTR_CREATE); } static const union fscrypt_policy *f2fs_get_dummy_policy(struct super_block *sb) { return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_policy.policy; } static bool f2fs_has_stable_inodes(struct super_block *sb) { return true; } static struct block_device **f2fs_get_devices(struct super_block *sb, unsigned int *num_devs) { struct f2fs_sb_info *sbi = F2FS_SB(sb); struct block_device **devs; int i; if (!f2fs_is_multi_device(sbi)) return NULL; devs = kmalloc_array(sbi->s_ndevs, sizeof(*devs), GFP_KERNEL); if (!devs) return ERR_PTR(-ENOMEM); for (i = 0; i < sbi->s_ndevs; i++) devs[i] = FDEV(i).bdev; *num_devs = sbi->s_ndevs; return devs; } static const struct fscrypt_operations f2fs_cryptops = { .inode_info_offs = (int)offsetof(struct f2fs_inode_info, i_crypt_info) - (int)offsetof(struct f2fs_inode_info, vfs_inode), .needs_bounce_pages = 1, .has_32bit_inodes = 1, .supports_subblock_data_units = 1, .legacy_key_prefix = "f2fs:", .get_context = f2fs_get_context, .set_context = f2fs_set_context, .get_dummy_policy = f2fs_get_dummy_policy, .empty_dir = f2fs_empty_dir, .has_stable_inodes = f2fs_has_stable_inodes, .get_devices = f2fs_get_devices, }; #endif /* CONFIG_FS_ENCRYPTION */ static struct inode *f2fs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct f2fs_sb_info *sbi = F2FS_SB(sb); struct inode *inode; if (f2fs_check_nid_range(sbi, ino)) return ERR_PTR(-ESTALE); /* * f2fs_iget isn't quite right if the inode is currently unallocated! * However f2fs_iget currently does appropriate checks to handle stale * inodes so everything is OK. */ inode = f2fs_iget(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (unlikely(generation && inode->i_generation != generation)) { /* we didn't find the right inode.. */ iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, f2fs_nfs_get_inode); } static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, f2fs_nfs_get_inode); } static const struct export_operations f2fs_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = f2fs_fh_to_dentry, .fh_to_parent = f2fs_fh_to_parent, .get_parent = f2fs_get_parent, }; loff_t max_file_blocks(struct inode *inode) { loff_t result = 0; loff_t leaf_count; /* * note: previously, result is equal to (DEF_ADDRS_PER_INODE - * DEFAULT_INLINE_XATTR_ADDRS), but now f2fs try to reserve more * space in inode.i_addr, it will be more safe to reassign * result as zero. */ if (inode && f2fs_compressed_file(inode)) leaf_count = ADDRS_PER_BLOCK(inode); else leaf_count = DEF_ADDRS_PER_BLOCK; /* two direct node blocks */ result += (leaf_count * 2); /* two indirect node blocks */ leaf_count *= NIDS_PER_BLOCK; result += (leaf_count * 2); /* one double indirect node block */ leaf_count *= NIDS_PER_BLOCK; result += leaf_count; /* * For compatibility with FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{64,32} with * a 4K crypto data unit, we must restrict the max filesize to what can * fit within U32_MAX + 1 data units. */ result = umin(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096)); return result; } static int __f2fs_commit_super(struct f2fs_sb_info *sbi, struct folio *folio, pgoff_t index, bool update) { struct bio *bio; /* it's rare case, we can do fua all the time */ blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA; int ret; folio_lock(folio); folio_wait_writeback(folio); if (update) memcpy(F2FS_SUPER_BLOCK(folio, index), F2FS_RAW_SUPER(sbi), sizeof(struct f2fs_super_block)); folio_mark_dirty(folio); folio_clear_dirty_for_io(folio); folio_start_writeback(folio); folio_unlock(folio); bio = bio_alloc(sbi->sb->s_bdev, 1, opf, GFP_NOFS); /* it doesn't need to set crypto context for superblock update */ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(folio->index); if (!bio_add_folio(bio, folio, folio_size(folio), 0)) f2fs_bug_on(sbi, 1); ret = submit_bio_wait(bio); bio_put(bio); folio_end_writeback(folio); return ret; } static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi, struct folio *folio, pgoff_t index) { struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index); struct super_block *sb = sbi->sb; u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr); u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr); u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr); u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt); u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit); u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat); u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa); u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main); u32 segment_count = le32_to_cpu(raw_super->segment_count); u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); u64 main_end_blkaddr = main_blkaddr + ((u64)segment_count_main << log_blocks_per_seg); u64 seg_end_blkaddr = segment0_blkaddr + ((u64)segment_count << log_blocks_per_seg); if (segment0_blkaddr != cp_blkaddr) { f2fs_info(sbi, "Mismatch start address, segment0(%u) cp_blkaddr(%u)", segment0_blkaddr, cp_blkaddr); return true; } if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) != sit_blkaddr) { f2fs_info(sbi, "Wrong CP boundary, start(%u) end(%u) blocks(%u)", cp_blkaddr, sit_blkaddr, segment_count_ckpt << log_blocks_per_seg); return true; } if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) != nat_blkaddr) { f2fs_info(sbi, "Wrong SIT boundary, start(%u) end(%u) blocks(%u)", sit_blkaddr, nat_blkaddr, segment_count_sit << log_blocks_per_seg); return true; } if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) != ssa_blkaddr) { f2fs_info(sbi, "Wrong NAT boundary, start(%u) end(%u) blocks(%u)", nat_blkaddr, ssa_blkaddr, segment_count_nat << log_blocks_per_seg); return true; } if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) != main_blkaddr) { f2fs_info(sbi, "Wrong SSA boundary, start(%u) end(%u) blocks(%u)", ssa_blkaddr, main_blkaddr, segment_count_ssa << log_blocks_per_seg); return true; } if (main_end_blkaddr > seg_end_blkaddr) { f2fs_info(sbi, "Wrong MAIN_AREA boundary, start(%u) end(%llu) block(%u)", main_blkaddr, seg_end_blkaddr, segment_count_main << log_blocks_per_seg); return true; } else if (main_end_blkaddr < seg_end_blkaddr) { int err = 0; char *res; /* fix in-memory information all the time */ raw_super->segment_count = cpu_to_le32((main_end_blkaddr - segment0_blkaddr) >> log_blocks_per_seg); if (f2fs_readonly(sb) || f2fs_hw_is_readonly(sbi)) { set_sbi_flag(sbi, SBI_NEED_SB_WRITE); res = "internally"; } else { err = __f2fs_commit_super(sbi, folio, index, false); res = err ? "failed" : "done"; } f2fs_info(sbi, "Fix alignment : %s, start(%u) end(%llu) block(%u)", res, main_blkaddr, seg_end_blkaddr, segment_count_main << log_blocks_per_seg); if (err) return true; } return false; } static int sanity_check_raw_super(struct f2fs_sb_info *sbi, struct folio *folio, pgoff_t index) { block_t segment_count, segs_per_sec, secs_per_zone, segment_count_main; block_t total_sections, blocks_per_seg; struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index); size_t crc_offset = 0; __u32 crc = 0; if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); return -EINVAL; } /* Check checksum_offset and crc in superblock */ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { crc_offset = le32_to_cpu(raw_super->checksum_offset); if (crc_offset != offsetof(struct f2fs_super_block, crc)) { f2fs_info(sbi, "Invalid SB checksum offset: %zu", crc_offset); return -EFSCORRUPTED; } crc = le32_to_cpu(raw_super->crc); if (crc != f2fs_crc32(raw_super, crc_offset)) { f2fs_info(sbi, "Invalid SB checksum value: %u", crc); return -EFSCORRUPTED; } } /* only support block_size equals to PAGE_SIZE */ if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) { f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u", le32_to_cpu(raw_super->log_blocksize), F2FS_BLKSIZE_BITS); return -EFSCORRUPTED; } /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_info(sbi, "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); return -EFSCORRUPTED; } /* Currently, support 512/1024/2048/4096/16K bytes sector size */ if (le32_to_cpu(raw_super->log_sectorsize) > F2FS_MAX_LOG_SECTOR_SIZE || le32_to_cpu(raw_super->log_sectorsize) < F2FS_MIN_LOG_SECTOR_SIZE) { f2fs_info(sbi, "Invalid log sectorsize (%u)", le32_to_cpu(raw_super->log_sectorsize)); return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->log_sectors_per_block) + le32_to_cpu(raw_super->log_sectorsize) != F2FS_MAX_LOG_SECTOR_SIZE) { f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)", le32_to_cpu(raw_super->log_sectors_per_block), le32_to_cpu(raw_super->log_sectorsize)); return -EFSCORRUPTED; } segment_count = le32_to_cpu(raw_super->segment_count); segment_count_main = le32_to_cpu(raw_super->segment_count_main); segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); total_sections = le32_to_cpu(raw_super->section_count); /* blocks_per_seg should be 512, given the above check */ blocks_per_seg = BIT(le32_to_cpu(raw_super->log_blocks_per_seg)); if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { f2fs_info(sbi, "Invalid segment count (%u)", segment_count); return -EFSCORRUPTED; } if (total_sections > segment_count_main || total_sections < 1 || segs_per_sec > segment_count || !segs_per_sec) { f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)", segment_count, total_sections, segs_per_sec); return -EFSCORRUPTED; } if (segment_count_main != total_sections * segs_per_sec) { f2fs_info(sbi, "Invalid segment/section count (%u != %u * %u)", segment_count_main, total_sections, segs_per_sec); return -EFSCORRUPTED; } if ((segment_count / segs_per_sec) < total_sections) { f2fs_info(sbi, "Small segment_count (%u < %u * %u)", segment_count, segs_per_sec, total_sections); return -EFSCORRUPTED; } if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)", segment_count, le64_to_cpu(raw_super->block_count)); return -EFSCORRUPTED; } if (RDEV(0).path[0]) { block_t dev_seg_count = le32_to_cpu(RDEV(0).total_segments); int i = 1; while (i < MAX_DEVICES && RDEV(i).path[0]) { dev_seg_count += le32_to_cpu(RDEV(i).total_segments); i++; } if (segment_count != dev_seg_count) { f2fs_info(sbi, "Segment count (%u) mismatch with total segments from devices (%u)", segment_count, dev_seg_count); return -EFSCORRUPTED; } } else { if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_BLKZONED) && !bdev_is_zoned(sbi->sb->s_bdev)) { f2fs_info(sbi, "Zoned block device path is missing"); return -EFSCORRUPTED; } } if (secs_per_zone > total_sections || !secs_per_zone) { f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)", secs_per_zone, total_sections); return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || raw_super->hot_ext_count > F2FS_MAX_EXTENSION || (le32_to_cpu(raw_super->extension_count) + raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) { f2fs_info(sbi, "Corrupted extension count (%u + %u > %u)", le32_to_cpu(raw_super->extension_count), raw_super->hot_ext_count, F2FS_MAX_EXTENSION); return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->cp_payload) >= (blocks_per_seg - F2FS_CP_PACKS - NR_CURSEG_PERSIST_TYPE)) { f2fs_info(sbi, "Insane cp_payload (%u >= %u)", le32_to_cpu(raw_super->cp_payload), blocks_per_seg - F2FS_CP_PACKS - NR_CURSEG_PERSIST_TYPE); return -EFSCORRUPTED; } /* check reserved ino info */ if (le32_to_cpu(raw_super->node_ino) != 1 || le32_to_cpu(raw_super->meta_ino) != 2 || le32_to_cpu(raw_super->root_ino) != 3) { f2fs_info(sbi, "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)", le32_to_cpu(raw_super->node_ino), le32_to_cpu(raw_super->meta_ino), le32_to_cpu(raw_super->root_ino)); return -EFSCORRUPTED; } /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, folio, index)) return -EFSCORRUPTED; return 0; } int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) { unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned int ovp_segments, reserved_segments; unsigned int main_segs, blocks_per_seg; unsigned int sit_segs, nat_segs; unsigned int sit_bitmap_size, nat_bitmap_size; unsigned int log_blocks_per_seg; unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count, valid_user_blocks; block_t avail_node_count, valid_node_count; unsigned int nat_blocks, nat_bits_bytes, nat_bits_blocks; unsigned int sit_blk_cnt; int i, j; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); sit_segs = le32_to_cpu(raw_super->segment_count_sit); fsmeta += sit_segs; nat_segs = le32_to_cpu(raw_super->segment_count_nat); fsmeta += nat_segs; fsmeta += le32_to_cpu(ckpt->rsvd_segment_count); fsmeta += le32_to_cpu(raw_super->segment_count_ssa); if (unlikely(fsmeta >= total)) return 1; ovp_segments = le32_to_cpu(ckpt->overprov_segment_count); reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count); if (!f2fs_sb_has_readonly(sbi) && unlikely(fsmeta < F2FS_MIN_META_SEGMENTS || ovp_segments == 0 || reserved_segments == 0)) { f2fs_err(sbi, "Wrong layout: check mkfs.f2fs version"); return 1; } user_block_count = le64_to_cpu(ckpt->user_block_count); segment_count_main = le32_to_cpu(raw_super->segment_count_main) + (f2fs_sb_has_readonly(sbi) ? 1 : 0); log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); if (!user_block_count || user_block_count >= segment_count_main << log_blocks_per_seg) { f2fs_err(sbi, "Wrong user_block_count: %u", user_block_count); return 1; } valid_user_blocks = le64_to_cpu(ckpt->valid_block_count); if (valid_user_blocks > user_block_count) { f2fs_err(sbi, "Wrong valid_user_blocks: %u, user_block_count: %u", valid_user_blocks, user_block_count); return 1; } valid_node_count = le32_to_cpu(ckpt->valid_node_count); avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; if (valid_node_count > avail_node_count) { f2fs_err(sbi, "Wrong valid_node_count: %u, avail_node_count: %u", valid_node_count, avail_node_count); return 1; } main_segs = le32_to_cpu(raw_super->segment_count_main); blocks_per_seg = BLKS_PER_SEG(sbi); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; if (f2fs_sb_has_readonly(sbi)) goto check_data; for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) == le32_to_cpu(ckpt->cur_node_segno[j])) { f2fs_err(sbi, "Node segment (%u, %u) has the same segno: %u", i, j, le32_to_cpu(ckpt->cur_node_segno[i])); return 1; } } } check_data: for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; if (f2fs_sb_has_readonly(sbi)) goto skip_cross; for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) == le32_to_cpu(ckpt->cur_data_segno[j])) { f2fs_err(sbi, "Data segment (%u, %u) has the same segno: %u", i, j, le32_to_cpu(ckpt->cur_data_segno[i])); return 1; } } } for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { for (j = 0; j < NR_CURSEG_DATA_TYPE; j++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) == le32_to_cpu(ckpt->cur_data_segno[j])) { f2fs_err(sbi, "Node segment (%u) and Data segment (%u) has the same segno: %u", i, j, le32_to_cpu(ckpt->cur_node_segno[i])); return 1; } } } skip_cross: sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 || nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) { f2fs_err(sbi, "Wrong bitmap size: sit: %u, nat:%u", sit_bitmap_size, nat_bitmap_size); return 1; } sit_blk_cnt = DIV_ROUND_UP(main_segs, SIT_ENTRY_PER_BLOCK); if (sit_bitmap_size * 8 < sit_blk_cnt) { f2fs_err(sbi, "Wrong bitmap size: sit: %u, sit_blk_cnt:%u", sit_bitmap_size, sit_blk_cnt); return 1; } cp_pack_start_sum = __start_sum_addr(sbi); cp_payload = __cp_payload(sbi); if (cp_pack_start_sum < cp_payload + 1 || cp_pack_start_sum > blocks_per_seg - 1 - NR_CURSEG_PERSIST_TYPE) { f2fs_err(sbi, "Wrong cp_pack_start_sum: %u", cp_pack_start_sum); return 1; } if (__is_set_ckpt_flags(ckpt, CP_LARGE_NAT_BITMAP_FLAG) && le32_to_cpu(ckpt->checksum_offset) != CP_MIN_CHKSUM_OFFSET) { f2fs_warn(sbi, "using deprecated layout of large_nat_bitmap, " "please run fsck v1.13.0 or higher to repair, chksum_offset: %u, " "fixed with patch: \"f2fs-tools: relocate chksum_offset for large_nat_bitmap feature\"", le32_to_cpu(ckpt->checksum_offset)); return 1; } nat_blocks = nat_segs << log_blocks_per_seg; nat_bits_bytes = nat_blocks / BITS_PER_BYTE; nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8); if (__is_set_ckpt_flags(ckpt, CP_NAT_BITS_FLAG) && (cp_payload + F2FS_CP_PACKS + NR_CURSEG_PERSIST_TYPE + nat_bits_blocks >= blocks_per_seg)) { f2fs_warn(sbi, "Insane cp_payload: %u, nat_bits_blocks: %u)", cp_payload, nat_bits_blocks); return 1; } if (unlikely(f2fs_cp_error(sbi))) { f2fs_err(sbi, "A bug case: need to run fsck"); return 1; } return 0; } static void init_sb_info(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = sbi->raw_super; int i; sbi->log_sectors_per_block = le32_to_cpu(raw_super->log_sectors_per_block); sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize); sbi->blocksize = BIT(sbi->log_blocksize); sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); sbi->blocks_per_seg = BIT(sbi->log_blocks_per_seg); sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); sbi->total_sections = le32_to_cpu(raw_super->section_count); sbi->total_node_count = SEGS_TO_BLKS(sbi, ((le32_to_cpu(raw_super->segment_count_nat) / 2) * NAT_ENTRY_PER_BLOCK)); sbi->allocate_section_hint = le32_to_cpu(raw_super->section_count); sbi->allocate_section_policy = ALLOCATE_FORWARD_NOHINT; F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino); F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino); F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino); sbi->cur_victim_sec = NULL_SECNO; sbi->gc_mode = GC_NORMAL; sbi->next_victim_seg[BG_GC] = NULL_SEGNO; sbi->next_victim_seg[FG_GC] = NULL_SEGNO; sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; sbi->migration_granularity = SEGS_PER_SEC(sbi); sbi->migration_window_granularity = f2fs_sb_has_blkzoned(sbi) ? DEF_MIGRATION_WINDOW_GRANULARITY_ZONED : SEGS_PER_SEC(sbi); sbi->seq_file_ra_mul = MIN_RA_MUL; sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE; sbi->max_fragment_hole = DEF_FRAGMENT_SIZE; spin_lock_init(&sbi->gc_remaining_trials_lock); atomic64_set(&sbi->current_atomic_write, 0); sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; sbi->interval_time[ENABLE_TIME] = DEF_ENABLE_INTERVAL; sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] = DEF_UMOUNT_DISCARD_TIMEOUT; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) atomic_set(&sbi->nr_pages[i], 0); for (i = 0; i < META; i++) atomic_set(&sbi->wb_sync_req[i], 0); INIT_LIST_HEAD(&sbi->s_list); mutex_init(&sbi->umount_mutex); init_f2fs_rwsem(&sbi->io_order_lock); spin_lock_init(&sbi->cp_lock); sbi->dirty_device = 0; spin_lock_init(&sbi->dev_lock); init_f2fs_rwsem(&sbi->sb_lock); init_f2fs_rwsem(&sbi->pin_sem); } static int init_percpu_info(struct f2fs_sb_info *sbi) { int err; err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->rf_node_block_count, 0, GFP_KERNEL); if (err) goto err_valid_block; err = percpu_counter_init(&sbi->total_valid_inode_count, 0, GFP_KERNEL); if (err) goto err_node_block; return 0; err_node_block: percpu_counter_destroy(&sbi->rf_node_block_count); err_valid_block: percpu_counter_destroy(&sbi->alloc_valid_block_count); return err; } #ifdef CONFIG_BLK_DEV_ZONED struct f2fs_report_zones_args { struct f2fs_sb_info *sbi; struct f2fs_dev_info *dev; }; static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct f2fs_report_zones_args *rz_args = data; block_t unusable_blocks = (zone->len - zone->capacity) >> F2FS_LOG_SECTORS_PER_BLOCK; if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) return 0; set_bit(idx, rz_args->dev->blkz_seq); if (!rz_args->sbi->unusable_blocks_per_sec) { rz_args->sbi->unusable_blocks_per_sec = unusable_blocks; return 0; } if (rz_args->sbi->unusable_blocks_per_sec != unusable_blocks) { f2fs_err(rz_args->sbi, "F2FS supports single zone capacity\n"); return -EINVAL; } return 0; } static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; sector_t nr_sectors = bdev_nr_sectors(bdev); struct f2fs_report_zones_args rep_zone_arg; u64 zone_sectors; unsigned int max_open_zones; int ret; if (!f2fs_sb_has_blkzoned(sbi)) return 0; if (bdev_is_zoned(FDEV(devi).bdev)) { max_open_zones = bdev_max_open_zones(bdev); if (max_open_zones && (max_open_zones < sbi->max_open_zones)) sbi->max_open_zones = max_open_zones; if (sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) { f2fs_err(sbi, "zoned: max open zones %u is too small, need at least %u open zones", sbi->max_open_zones, F2FS_OPTION(sbi).active_logs); return -EINVAL; } } zone_sectors = bdev_zone_sectors(bdev); if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != SECTOR_TO_BLOCK(zone_sectors)) return -EINVAL; sbi->blocks_per_blkz = SECTOR_TO_BLOCK(zone_sectors); FDEV(devi).nr_blkz = div_u64(SECTOR_TO_BLOCK(nr_sectors), sbi->blocks_per_blkz); if (nr_sectors & (zone_sectors - 1)) FDEV(devi).nr_blkz++; FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi, BITS_TO_LONGS(FDEV(devi).nr_blkz) * sizeof(unsigned long), GFP_KERNEL); if (!FDEV(devi).blkz_seq) return -ENOMEM; rep_zone_arg.sbi = sbi; rep_zone_arg.dev = &FDEV(devi); ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, &rep_zone_arg); if (ret < 0) return ret; return 0; } #endif /* * Read f2fs raw super block. * Because we have two copies of super block, so read both of them * to get the first valid one. If any one of them is broken, we pass * them recovery flag back to the caller. */ static int read_raw_super_block(struct f2fs_sb_info *sbi, struct f2fs_super_block **raw_super, int *valid_super_block, int *recovery) { struct super_block *sb = sbi->sb; int block; struct folio *folio; struct f2fs_super_block *super; int err = 0; super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL); if (!super) return -ENOMEM; for (block = 0; block < 2; block++) { folio = read_mapping_folio(sb->s_bdev->bd_mapping, block, NULL); if (IS_ERR(folio)) { f2fs_err(sbi, "Unable to read %dth superblock", block + 1); err = PTR_ERR(folio); *recovery = 1; continue; } /* sanity checking of raw super */ err = sanity_check_raw_super(sbi, folio, block); if (err) { f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock", block + 1); folio_put(folio); *recovery = 1; continue; } if (!*raw_super) { memcpy(super, F2FS_SUPER_BLOCK(folio, block), sizeof(*super)); *valid_super_block = block; *raw_super = super; } folio_put(folio); } /* No valid superblock */ if (!*raw_super) kfree(super); else err = 0; return err; } int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { struct folio *folio; pgoff_t index; __u32 crc = 0; int err; if ((recover && f2fs_readonly(sbi->sb)) || f2fs_hw_is_readonly(sbi)) { set_sbi_flag(sbi, SBI_NEED_SB_WRITE); return -EROFS; } /* we should update superblock crc here */ if (!recover && f2fs_sb_has_sb_chksum(sbi)) { crc = f2fs_crc32(F2FS_RAW_SUPER(sbi), offsetof(struct f2fs_super_block, crc)); F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc); } /* write back-up superblock first */ index = sbi->valid_super_block ? 0 : 1; folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL); if (IS_ERR(folio)) return PTR_ERR(folio); err = __f2fs_commit_super(sbi, folio, index, true); folio_put(folio); /* if we are in recovery path, skip writing valid superblock */ if (recover || err) return err; /* write current valid superblock */ index = sbi->valid_super_block; folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL); if (IS_ERR(folio)) return PTR_ERR(folio); err = __f2fs_commit_super(sbi, folio, index, true); folio_put(folio); return err; } static void save_stop_reason(struct f2fs_sb_info *sbi, unsigned char reason) { unsigned long flags; spin_lock_irqsave(&sbi->error_lock, flags); if (sbi->stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0)) sbi->stop_reason[reason]++; spin_unlock_irqrestore(&sbi->error_lock, flags); } static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned long flags; int err; f2fs_down_write(&sbi->sb_lock); spin_lock_irqsave(&sbi->error_lock, flags); if (sbi->error_dirty) { memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors, MAX_F2FS_ERRORS); sbi->error_dirty = false; } memcpy(raw_super->s_stop_reason, sbi->stop_reason, MAX_STOP_REASON); spin_unlock_irqrestore(&sbi->error_lock, flags); err = f2fs_commit_super(sbi, false); f2fs_up_write(&sbi->sb_lock); if (err) f2fs_err_ratelimited(sbi, "f2fs_commit_super fails to record stop_reason, err:%d", err); } void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag) { unsigned long flags; spin_lock_irqsave(&sbi->error_lock, flags); if (!test_bit(flag, (unsigned long *)sbi->errors)) { set_bit(flag, (unsigned long *)sbi->errors); sbi->error_dirty = true; } spin_unlock_irqrestore(&sbi->error_lock, flags); } static bool f2fs_update_errors(struct f2fs_sb_info *sbi) { unsigned long flags; bool need_update = false; spin_lock_irqsave(&sbi->error_lock, flags); if (sbi->error_dirty) { memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors, MAX_F2FS_ERRORS); sbi->error_dirty = false; need_update = true; } spin_unlock_irqrestore(&sbi->error_lock, flags); return need_update; } static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error) { int err; f2fs_down_write(&sbi->sb_lock); if (!f2fs_update_errors(sbi)) goto out_unlock; err = f2fs_commit_super(sbi, false); if (err) f2fs_err_ratelimited(sbi, "f2fs_commit_super fails to record errors:%u, err:%d", error, err); out_unlock: f2fs_up_write(&sbi->sb_lock); } void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error) { f2fs_save_errors(sbi, error); f2fs_record_errors(sbi, error); } void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error) { f2fs_save_errors(sbi, error); if (!sbi->error_dirty) return; if (!test_bit(error, (unsigned long *)sbi->errors)) return; schedule_work(&sbi->s_error_work); } static bool system_going_down(void) { return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART; } void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason) { struct super_block *sb = sbi->sb; bool shutdown = reason == STOP_CP_REASON_SHUTDOWN; bool continue_fs = !shutdown && F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE; set_ckpt_flags(sbi, CP_ERROR_FLAG); if (!f2fs_hw_is_readonly(sbi)) { save_stop_reason(sbi, reason); /* * always create an asynchronous task to record stop_reason * in order to avoid potential deadlock when running into * f2fs_record_stop_reason() synchronously. */ schedule_work(&sbi->s_error_work); } /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC && !shutdown && !system_going_down() && !is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) panic("F2FS-fs (device %s): panic forced after error\n", sb->s_id); if (shutdown) set_sbi_flag(sbi, SBI_IS_SHUTDOWN); else dump_stack(); /* * Continue filesystem operators if errors=continue. Should not set * RO by shutdown, since RO bypasses thaw_super which can hang the * system. */ if (continue_fs || f2fs_readonly(sb) || shutdown) { f2fs_warn(sbi, "Stopped filesystem due to reason: %d", reason); return; } f2fs_warn(sbi, "Remounting filesystem read-only"); /* * We have already set CP_ERROR_FLAG flag to stop all updates * to filesystem, so it doesn't need to set SB_RDONLY flag here * because the flag should be set covered w/ sb->s_umount semaphore * via remount procedure, otherwise, it will confuse code like * freeze_super() which will lead to deadlocks and other problems. */ } static void f2fs_record_error_work(struct work_struct *work) { struct f2fs_sb_info *sbi = container_of(work, struct f2fs_sb_info, s_error_work); f2fs_record_stop_reason(sbi); } static inline unsigned int get_first_seq_zone_segno(struct f2fs_sb_info *sbi) { #ifdef CONFIG_BLK_DEV_ZONED unsigned int zoneno, total_zones; int devi; if (!f2fs_sb_has_blkzoned(sbi)) return NULL_SEGNO; for (devi = 0; devi < sbi->s_ndevs; devi++) { if (!bdev_is_zoned(FDEV(devi).bdev)) continue; total_zones = GET_ZONE_FROM_SEG(sbi, FDEV(devi).total_segments); for (zoneno = 0; zoneno < total_zones; zoneno++) { unsigned int segs, blks; if (!f2fs_zone_is_seq(sbi, devi, zoneno)) continue; segs = GET_SEG_FROM_SEC(sbi, zoneno * sbi->secs_per_zone); blks = SEGS_TO_BLKS(sbi, segs); return GET_SEGNO(sbi, FDEV(devi).start_blk + blks); } } #endif return NULL_SEGNO; } static int f2fs_scan_devices(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned int max_devices = MAX_DEVICES; unsigned int logical_blksize; blk_mode_t mode = sb_open_mode(sbi->sb->s_flags); int i; /* Initialize single device information */ if (!RDEV(0).path[0]) { if (!bdev_is_zoned(sbi->sb->s_bdev)) return 0; max_devices = 1; } /* * Initialize multiple devices information, or single * zoned block device information. */ sbi->devs = f2fs_kzalloc(sbi, array_size(max_devices, sizeof(struct f2fs_dev_info)), GFP_KERNEL); if (!sbi->devs) return -ENOMEM; logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev); sbi->aligned_blksize = true; sbi->bggc_io_aware = AWARE_ALL_IO; #ifdef CONFIG_BLK_DEV_ZONED sbi->max_open_zones = UINT_MAX; sbi->blkzone_alloc_policy = BLKZONE_ALLOC_PRIOR_SEQ; sbi->bggc_io_aware = AWARE_READ_IO; #endif for (i = 0; i < max_devices; i++) { if (max_devices == 1) { FDEV(i).total_segments = le32_to_cpu(raw_super->segment_count_main); FDEV(i).start_blk = 0; FDEV(i).end_blk = FDEV(i).total_segments * BLKS_PER_SEG(sbi); } if (i == 0) FDEV(0).bdev_file = sbi->sb->s_bdev_file; else if (!RDEV(i).path[0]) break; if (max_devices > 1) { /* Multi-device mount */ memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN); FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments); if (i == 0) { FDEV(i).start_blk = 0; FDEV(i).end_blk = FDEV(i).start_blk + SEGS_TO_BLKS(sbi, FDEV(i).total_segments) - 1 + le32_to_cpu(raw_super->segment0_blkaddr); sbi->allocate_section_hint = FDEV(i).total_segments / SEGS_PER_SEC(sbi); } else { FDEV(i).start_blk = FDEV(i - 1).end_blk + 1; FDEV(i).end_blk = FDEV(i).start_blk + SEGS_TO_BLKS(sbi, FDEV(i).total_segments) - 1; FDEV(i).bdev_file = bdev_file_open_by_path( FDEV(i).path, mode, sbi->sb, NULL); } } if (IS_ERR(FDEV(i).bdev_file)) return PTR_ERR(FDEV(i).bdev_file); FDEV(i).bdev = file_bdev(FDEV(i).bdev_file); /* to release errored devices */ sbi->s_ndevs = i + 1; if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev)) sbi->aligned_blksize = false; #ifdef CONFIG_BLK_DEV_ZONED if (bdev_is_zoned(FDEV(i).bdev)) { if (!f2fs_sb_has_blkzoned(sbi)) { f2fs_err(sbi, "Zoned block device feature not enabled"); return -EINVAL; } if (init_blkz_info(sbi, i)) { f2fs_err(sbi, "Failed to initialize F2FS blkzone information"); return -EINVAL; } if (max_devices == 1) break; f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: Host-managed)", i, FDEV(i).path, FDEV(i).total_segments, FDEV(i).start_blk, FDEV(i).end_blk); continue; } #endif f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x", i, FDEV(i).path, FDEV(i).total_segments, FDEV(i).start_blk, FDEV(i).end_blk); } return 0; } static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) { #if IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) { const struct f2fs_sb_encodings *encoding_info; struct unicode_map *encoding; __u16 encoding_flags; encoding_info = f2fs_sb_read_encoding(sbi->raw_super); if (!encoding_info) { f2fs_err(sbi, "Encoding requested by superblock is unknown"); return -EINVAL; } encoding_flags = le16_to_cpu(sbi->raw_super->s_encoding_flags); encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { f2fs_err(sbi, "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); return PTR_ERR(encoding); } f2fs_info(sbi, "Using encoding defined by superblock: " "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); sbi->sb->s_encoding = encoding; sbi->sb->s_encoding_flags = encoding_flags; } #else if (f2fs_sb_has_casefold(sbi)) { f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); return -EINVAL; } #endif return 0; } static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi) { /* adjust parameters according to the volume size */ if (MAIN_SEGS(sbi) <= SMALL_VOLUME_SEGMENTS) { if (f2fs_block_unit_discard(sbi)) SM_I(sbi)->dcc_info->discard_granularity = MIN_DISCARD_GRANULARITY; if (!f2fs_lfs_mode(sbi)) SM_I(sbi)->ipu_policy = BIT(F2FS_IPU_FORCE) | BIT(F2FS_IPU_HONOR_OPU_WRITE); } sbi->readdir_ra = true; } static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) { struct f2fs_fs_context *ctx = fc->fs_private; struct f2fs_sb_info *sbi; struct f2fs_super_block *raw_super; struct inode *root; int err; bool skip_recovery = false, need_fsck = false; int recovery, i, valid_super_block; struct curseg_info *seg_i; int retry_cnt = 1; #ifdef CONFIG_QUOTA bool quota_enabled = false; #endif try_onemore: err = -EINVAL; raw_super = NULL; valid_super_block = -1; recovery = 0; /* allocate memory for f2fs-specific super block info */ sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sbi->sb = sb; /* initialize locks within allocated memory */ init_f2fs_rwsem(&sbi->gc_lock); mutex_init(&sbi->writepages); init_f2fs_rwsem(&sbi->cp_global_sem); init_f2fs_rwsem(&sbi->node_write); init_f2fs_rwsem(&sbi->node_change); spin_lock_init(&sbi->stat_lock); init_f2fs_rwsem(&sbi->cp_rwsem); init_f2fs_rwsem(&sbi->quota_sem); init_waitqueue_head(&sbi->cp_wait); spin_lock_init(&sbi->error_lock); for (i = 0; i < NR_INODE_TYPE; i++) { INIT_LIST_HEAD(&sbi->inode_list[i]); spin_lock_init(&sbi->inode_lock[i]); } mutex_init(&sbi->flush_lock); /* set a block size */ if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { f2fs_err(sbi, "unable to set blocksize"); goto free_sbi; } err = read_raw_super_block(sbi, &raw_super, &valid_super_block, &recovery); if (err) goto free_sbi; sb->s_fs_info = sbi; sbi->raw_super = raw_super; INIT_WORK(&sbi->s_error_work, f2fs_record_error_work); memcpy(sbi->errors, raw_super->s_errors, MAX_F2FS_ERRORS); memcpy(sbi->stop_reason, raw_super->s_stop_reason, MAX_STOP_REASON); /* precompute checksum seed for metadata */ if (f2fs_sb_has_inode_chksum(sbi)) sbi->s_chksum_seed = f2fs_chksum(~0, raw_super->uuid, sizeof(raw_super->uuid)); default_options(sbi, false); err = f2fs_check_opt_consistency(fc, sb); if (err) goto free_sb_buf; f2fs_apply_options(fc, sb); err = f2fs_sanity_check_options(sbi, false); if (err) goto free_options; sb->s_maxbytes = max_file_blocks(NULL) << le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; err = f2fs_setup_casefold(sbi); if (err) goto free_options; #ifdef CONFIG_QUOTA sb->dq_op = &f2fs_quota_operations; sb->s_qcop = &f2fs_quotactl_ops; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; if (f2fs_sb_has_quota_ino(sbi)) { for (i = 0; i < MAXQUOTAS; i++) { if (f2fs_qf_ino(sbi->sb, i)) sbi->nquota_files++; } } #endif sb->s_op = &f2fs_sops; #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &f2fs_cryptops; #endif #ifdef CONFIG_FS_VERITY sb->s_vop = &f2fs_verityops; #endif sb->s_xattr = f2fs_xattr_handlers; sb->s_export_op = &f2fs_export_ops; sb->s_magic = F2FS_SUPER_MAGIC; sb->s_time_gran = 1; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); if (test_opt(sbi, INLINECRYPT)) sb->s_flags |= SB_INLINECRYPT; if (test_opt(sbi, LAZYTIME)) sb->s_flags |= SB_LAZYTIME; else sb->s_flags &= ~SB_LAZYTIME; super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid)); super_set_sysfs_name_bdev(sb); sb->s_iflags |= SB_I_CGROUPWB; /* init f2fs-specific super block info */ sbi->valid_super_block = valid_super_block; /* disallow all the data/node/meta page writes */ set_sbi_flag(sbi, SBI_POR_DOING); err = f2fs_init_write_merge_io(sbi); if (err) goto free_bio_info; init_sb_info(sbi); err = f2fs_init_iostat(sbi); if (err) goto free_bio_info; err = init_percpu_info(sbi); if (err) goto free_iostat; /* init per sbi slab cache */ err = f2fs_init_xattr_caches(sbi); if (err) goto free_percpu; err = f2fs_init_page_array_cache(sbi); if (err) goto free_xattr_cache; /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); if (IS_ERR(sbi->meta_inode)) { f2fs_err(sbi, "Failed to read F2FS meta data inode"); err = PTR_ERR(sbi->meta_inode); goto free_page_array_cache; } err = f2fs_get_valid_checkpoint(sbi); if (err) { f2fs_err(sbi, "Failed to get valid F2FS checkpoint"); goto free_meta_inode; } if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_DISABLED_QUICK_FLAG)) { set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL; } if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FSCK_FLAG)) set_sbi_flag(sbi, SBI_NEED_FSCK); /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { f2fs_err(sbi, "Failed to find devices"); goto free_devices; } err = f2fs_init_post_read_wq(sbi); if (err) { f2fs_err(sbi, "Failed to initialize post read workqueue"); goto free_devices; } sbi->total_valid_node_count = le32_to_cpu(sbi->ckpt->valid_node_count); percpu_counter_set(&sbi->total_valid_inode_count, le32_to_cpu(sbi->ckpt->valid_inode_count)); sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count); sbi->total_valid_block_count = le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; sbi->reserved_blocks = 0; sbi->current_reserved_blocks = 0; limit_reserve_root(sbi); adjust_unusable_cap_perc(sbi); f2fs_init_extent_cache_info(sbi); f2fs_init_ino_entry_info(sbi); f2fs_init_fsync_node_info(sbi); /* setup checkpoint request control and start checkpoint issue thread */ f2fs_init_ckpt_req_control(sbi); if (!f2fs_readonly(sb) && !test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, MERGE_CHECKPOINT)) { err = f2fs_start_ckpt_thread(sbi); if (err) { f2fs_err(sbi, "Failed to start F2FS issue_checkpoint_thread (%d)", err); goto stop_ckpt_thread; } } /* setup f2fs internal modules */ err = f2fs_build_segment_manager(sbi); if (err) { f2fs_err(sbi, "Failed to initialize F2FS segment manager (%d)", err); goto free_sm; } err = f2fs_build_node_manager(sbi); if (err) { f2fs_err(sbi, "Failed to initialize F2FS node manager (%d)", err); goto free_nm; } /* For write statistics */ sbi->sectors_written_start = f2fs_get_sectors_written(sbi); /* get segno of first zoned block device */ sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi); sbi->reserved_pin_section = f2fs_sb_has_blkzoned(sbi) ? ZONED_PIN_SEC_REQUIRED_COUNT : GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)); /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); if (__exist_node_summaries(sbi)) sbi->kbytes_written = le64_to_cpu(seg_i->journal->info.kbytes_written); f2fs_build_gc_manager(sbi); err = f2fs_build_stats(sbi); if (err) goto free_nm; /* get an inode for node space */ sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi)); if (IS_ERR(sbi->node_inode)) { f2fs_err(sbi, "Failed to read node inode"); err = PTR_ERR(sbi->node_inode); goto free_stats; } /* read root inode and dentry */ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); if (IS_ERR(root)) { f2fs_err(sbi, "Failed to read root inode"); err = PTR_ERR(root); goto free_node_inode; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size || !root->i_nlink) { iput(root); err = -EINVAL; goto free_node_inode; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); /* allocate root dentry */ if (!sb->s_root) { err = -ENOMEM; goto free_node_inode; } err = f2fs_init_compress_inode(sbi); if (err) goto free_root_inode; err = f2fs_register_sysfs(sbi); if (err) goto free_compress_inode; sbi->umount_lock_holder = current; #ifdef CONFIG_QUOTA /* Enable quota usage during mount */ if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) { err = f2fs_enable_quotas(sb); if (err) f2fs_err(sbi, "Cannot turn on quotas: error %d", err); } quota_enabled = f2fs_recover_quota_begin(sbi); #endif /* if there are any orphan inodes, free them */ err = f2fs_recover_orphan_inodes(sbi); if (err) goto free_meta; if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) { skip_recovery = true; goto reset_checkpoint; } /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD) && !test_opt(sbi, NORECOVERY)) { /* * mount should be failed, when device has readonly mode, and * previous checkpoint was not done by clean system shutdown. */ if (f2fs_hw_is_readonly(sbi)) { if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { err = f2fs_recover_fsync_data(sbi, true); if (err > 0) { err = -EROFS; f2fs_err(sbi, "Need to recover fsync data, but " "write access unavailable, please try " "mount w/ disable_roll_forward or norecovery"); } if (err < 0) goto free_meta; } f2fs_info(sbi, "write access unavailable, skipping recovery"); goto reset_checkpoint; } if (need_fsck) set_sbi_flag(sbi, SBI_NEED_FSCK); if (skip_recovery) goto reset_checkpoint; err = f2fs_recover_fsync_data(sbi, false); if (err < 0) { if (err != -ENOMEM) skip_recovery = true; need_fsck = true; f2fs_err(sbi, "Cannot recover all fsync data errno=%d", err); goto free_meta; } } else { err = f2fs_recover_fsync_data(sbi, true); if (!f2fs_readonly(sb) && err > 0) { err = -EINVAL; f2fs_err(sbi, "Need to recover fsync data"); goto free_meta; } } reset_checkpoint: #ifdef CONFIG_QUOTA f2fs_recover_quota_end(sbi, quota_enabled); #endif /* * If the f2fs is not readonly and fsync data recovery succeeds, * write pointer consistency of cursegs and other zones are already * checked and fixed during recovery. However, if recovery fails, * write pointers are left untouched, and retry-mount should check * them here. */ if (skip_recovery) err = f2fs_check_and_fix_write_pointer(sbi); if (err) goto free_meta; /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); err = f2fs_init_inmem_curseg(sbi); if (err) goto sync_free_meta; if (test_opt(sbi, DISABLE_CHECKPOINT)) { err = f2fs_disable_checkpoint(sbi); if (err) goto sync_free_meta; } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { f2fs_enable_checkpoint(sbi); } /* * If filesystem is not mounted as read-only then * do start the gc_thread. */ if ((F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF || test_opt(sbi, GC_MERGE)) && !f2fs_readonly(sb)) { /* After POR, we can run background GC thread.*/ err = f2fs_start_gc_thread(sbi); if (err) goto sync_free_meta; } /* recover broken superblock */ if (recovery) { err = f2fs_commit_super(sbi, true); f2fs_info(sbi, "Try to recover %dth superblock, ret: %d", sbi->valid_super_block ? 1 : 2, err); } f2fs_join_shrinker(sbi); f2fs_tuning_parameters(sbi); f2fs_notice(sbi, "Mounted with checkpoint version = %llx", cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); f2fs_update_time(sbi, REQ_TIME); clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); sbi->umount_lock_holder = NULL; return 0; sync_free_meta: /* safe to flush all the data */ sync_filesystem(sbi->sb); retry_cnt = 0; free_meta: #ifdef CONFIG_QUOTA f2fs_truncate_quota_inode_pages(sb); if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) f2fs_quota_off_umount(sbi->sb); #endif /* * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes() * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() * followed by f2fs_write_checkpoint() through f2fs_write_node_pages(), which * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); /* evict some inodes being cached by GC */ evict_inodes(sb); f2fs_unregister_sysfs(sbi); free_compress_inode: f2fs_destroy_compress_inode(sbi); free_root_inode: dput(sb->s_root); sb->s_root = NULL; free_node_inode: f2fs_release_ino_entry(sbi, true); truncate_inode_pages_final(NODE_MAPPING(sbi)); iput(sbi->node_inode); sbi->node_inode = NULL; free_stats: f2fs_destroy_stats(sbi); free_nm: /* stop discard thread before destroying node manager */ f2fs_stop_discard_thread(sbi); f2fs_destroy_node_manager(sbi); free_sm: f2fs_destroy_segment_manager(sbi); stop_ckpt_thread: f2fs_stop_ckpt_thread(sbi); /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); f2fs_destroy_post_read_wq(sbi); free_devices: destroy_device_list(sbi); kvfree(sbi->ckpt); free_meta_inode: make_bad_inode(sbi->meta_inode); iput(sbi->meta_inode); sbi->meta_inode = NULL; free_page_array_cache: f2fs_destroy_page_array_cache(sbi); free_xattr_cache: f2fs_destroy_xattr_caches(sbi); free_percpu: destroy_percpu_info(sbi); free_iostat: f2fs_destroy_iostat(sbi); free_bio_info: for (i = 0; i < NR_PAGE_TYPE; i++) kfree(sbi->write_io[i]); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); sb->s_encoding = NULL; #endif free_options: #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif /* no need to free dummy_enc_policy, we just keep it in ctx when failed */ swap(F2FS_CTX_INFO(ctx).dummy_enc_policy, F2FS_OPTION(sbi).dummy_enc_policy); free_sb_buf: kfree(raw_super); free_sbi: kfree(sbi); sb->s_fs_info = NULL; /* give only one another chance */ if (retry_cnt > 0 && skip_recovery) { retry_cnt--; shrink_dcache_sb(sb); goto try_onemore; } return err; } static int f2fs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, f2fs_fill_super); } static int f2fs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; return __f2fs_remount(fc, sb); } static void f2fs_fc_free(struct fs_context *fc) { struct f2fs_fs_context *ctx = fc->fs_private; if (!ctx) return; #ifdef CONFIG_QUOTA f2fs_unnote_qf_name_all(fc); #endif fscrypt_free_dummy_policy(&F2FS_CTX_INFO(ctx).dummy_enc_policy); kfree(ctx); } static const struct fs_context_operations f2fs_context_ops = { .parse_param = f2fs_parse_param, .get_tree = f2fs_get_tree, .reconfigure = f2fs_reconfigure, .free = f2fs_fc_free, }; static void kill_f2fs_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); if (sb->s_root) { sbi->umount_lock_holder = current; set_sbi_flag(sbi, SBI_IS_CLOSE); f2fs_stop_gc_thread(sbi); f2fs_stop_discard_thread(sbi); #ifdef CONFIG_F2FS_FS_COMPRESSION /* * latter evict_inode() can bypass checking and invalidating * compress inode cache. */ if (test_opt(sbi, COMPRESS_CACHE)) truncate_inode_pages_final(COMPRESS_MAPPING(sbi)); #endif if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { struct cp_control cpc = { .reason = CP_UMOUNT, }; stat_inc_cp_call_count(sbi, TOTAL_CALL); f2fs_write_checkpoint(sbi, &cpc); } if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb)) sb->s_flags &= ~SB_RDONLY; } kill_block_super(sb); /* Release block devices last, after fscrypt_destroy_keyring(). */ if (sbi) { destroy_device_list(sbi); kfree(sbi); sb->s_fs_info = NULL; } } static int f2fs_init_fs_context(struct fs_context *fc) { struct f2fs_fs_context *ctx; ctx = kzalloc(sizeof(struct f2fs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &f2fs_context_ops; return 0; } static struct file_system_type f2fs_fs_type = { .owner = THIS_MODULE, .name = "f2fs", .init_fs_context = f2fs_init_fs_context, .kill_sb = kill_f2fs_super, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("f2fs"); static int __init init_inodecache(void) { f2fs_inode_cachep = kmem_cache_create("f2fs_inode_cache", sizeof(struct f2fs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, NULL); return f2fs_inode_cachep ? 0 : -ENOMEM; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(f2fs_inode_cachep); } static int __init init_f2fs_fs(void) { int err; err = init_inodecache(); if (err) goto fail; err = f2fs_create_node_manager_caches(); if (err) goto free_inodecache; err = f2fs_create_segment_manager_caches(); if (err) goto free_node_manager_caches; err = f2fs_create_checkpoint_caches(); if (err) goto free_segment_manager_caches; err = f2fs_create_recovery_cache(); if (err) goto free_checkpoint_caches; err = f2fs_create_extent_cache(); if (err) goto free_recovery_cache; err = f2fs_create_garbage_collection_cache(); if (err) goto free_extent_cache; err = f2fs_init_sysfs(); if (err) goto free_garbage_collection_cache; err = f2fs_init_shrinker(); if (err) goto free_sysfs; f2fs_create_root_stats(); err = f2fs_init_post_read_processing(); if (err) goto free_root_stats; err = f2fs_init_iostat_processing(); if (err) goto free_post_read; err = f2fs_init_bio_entry_cache(); if (err) goto free_iostat; err = f2fs_init_bioset(); if (err) goto free_bio_entry_cache; err = f2fs_init_compress_mempool(); if (err) goto free_bioset; err = f2fs_init_compress_cache(); if (err) goto free_compress_mempool; err = f2fs_create_casefold_cache(); if (err) goto free_compress_cache; err = register_filesystem(&f2fs_fs_type); if (err) goto free_casefold_cache; return 0; free_casefold_cache: f2fs_destroy_casefold_cache(); free_compress_cache: f2fs_destroy_compress_cache(); free_compress_mempool: f2fs_destroy_compress_mempool(); free_bioset: f2fs_destroy_bioset(); free_bio_entry_cache: f2fs_destroy_bio_entry_cache(); free_iostat: f2fs_destroy_iostat_processing(); free_post_read: f2fs_destroy_post_read_processing(); free_root_stats: f2fs_destroy_root_stats(); f2fs_exit_shrinker(); free_sysfs: f2fs_exit_sysfs(); free_garbage_collection_cache: f2fs_destroy_garbage_collection_cache(); free_extent_cache: f2fs_destroy_extent_cache(); free_recovery_cache: f2fs_destroy_recovery_cache(); free_checkpoint_caches: f2fs_destroy_checkpoint_caches(); free_segment_manager_caches: f2fs_destroy_segment_manager_caches(); free_node_manager_caches: f2fs_destroy_node_manager_caches(); free_inodecache: destroy_inodecache(); fail: return err; } static void __exit exit_f2fs_fs(void) { unregister_filesystem(&f2fs_fs_type); f2fs_destroy_casefold_cache(); f2fs_destroy_compress_cache(); f2fs_destroy_compress_mempool(); f2fs_destroy_bioset(); f2fs_destroy_bio_entry_cache(); f2fs_destroy_iostat_processing(); f2fs_destroy_post_read_processing(); f2fs_destroy_root_stats(); f2fs_exit_shrinker(); f2fs_exit_sysfs(); f2fs_destroy_garbage_collection_cache(); f2fs_destroy_extent_cache(); f2fs_destroy_recovery_cache(); f2fs_destroy_checkpoint_caches(); f2fs_destroy_segment_manager_caches(); f2fs_destroy_node_manager_caches(); destroy_inodecache(); } module_init(init_f2fs_fs) module_exit(exit_f2fs_fs) MODULE_AUTHOR("Samsung Electronics's Praesto Team"); MODULE_DESCRIPTION("Flash Friendly File System"); MODULE_LICENSE("GPL"); |
| 2 2 2 2 1 1 1 2 2 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_bmap.h" #include "xfs_alloc.h" #include "xfs_fsops.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_dir2.h" #include "xfs_extfree_item.h" #include "xfs_mru_cache.h" #include "xfs_inode_item.h" #include "xfs_icache.h" #include "xfs_trace.h" #include "xfs_icreate_item.h" #include "xfs_filestream.h" #include "xfs_quota.h" #include "xfs_sysfs.h" #include "xfs_ondisk.h" #include "xfs_rmap_item.h" #include "xfs_refcount_item.h" #include "xfs_bmap_item.h" #include "xfs_reflink.h" #include "xfs_pwork.h" #include "xfs_ag.h" #include "xfs_defer.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" #include "xfs_iunlink_item.h" #include "xfs_dahash_test.h" #include "xfs_rtbitmap.h" #include "xfs_exchmaps_item.h" #include "xfs_parent.h" #include "xfs_rtalloc.h" #include "xfs_zone_alloc.h" #include "scrub/stats.h" #include "scrub/rcbag_btree.h" #include <linux/magic.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> static const struct super_operations xfs_super_operations; static struct dentry *xfs_debugfs; /* top-level xfs debugfs dir */ static struct kset *xfs_kset; /* top-level xfs sysfs dir */ #ifdef DEBUG static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #endif enum xfs_dax_mode { XFS_DAX_INODE = 0, XFS_DAX_ALWAYS = 1, XFS_DAX_NEVER = 2, }; /* Were quota mount options provided? Must use the upper 16 bits of qflags. */ #define XFS_QFLAGS_MNTOPTS (1U << 31) static void xfs_mount_set_dax_mode( struct xfs_mount *mp, enum xfs_dax_mode mode) { switch (mode) { case XFS_DAX_INODE: mp->m_features &= ~(XFS_FEAT_DAX_ALWAYS | XFS_FEAT_DAX_NEVER); break; case XFS_DAX_ALWAYS: mp->m_features |= XFS_FEAT_DAX_ALWAYS; mp->m_features &= ~XFS_FEAT_DAX_NEVER; break; case XFS_DAX_NEVER: mp->m_features |= XFS_FEAT_DAX_NEVER; mp->m_features &= ~XFS_FEAT_DAX_ALWAYS; break; } } static const struct constant_table dax_param_enums[] = { {"inode", XFS_DAX_INODE }, {"always", XFS_DAX_ALWAYS }, {"never", XFS_DAX_NEVER }, {} }; /* * Table driven mount option parser. */ enum { Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_largeio, Opt_nolargeio, Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota, Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce, Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, Opt_max_open_zones, Opt_lifetime, Opt_nolifetime, Opt_max_atomic_write, }; static const struct fs_parameter_spec xfs_fs_parameters[] = { fsparam_u32("logbufs", Opt_logbufs), fsparam_string("logbsize", Opt_logbsize), fsparam_string("logdev", Opt_logdev), fsparam_string("rtdev", Opt_rtdev), fsparam_flag("wsync", Opt_wsync), fsparam_flag("noalign", Opt_noalign), fsparam_flag("swalloc", Opt_swalloc), fsparam_u32("sunit", Opt_sunit), fsparam_u32("swidth", Opt_swidth), fsparam_flag("nouuid", Opt_nouuid), fsparam_flag("grpid", Opt_grpid), fsparam_flag("nogrpid", Opt_nogrpid), fsparam_flag("bsdgroups", Opt_bsdgroups), fsparam_flag("sysvgroups", Opt_sysvgroups), fsparam_string("allocsize", Opt_allocsize), fsparam_flag("norecovery", Opt_norecovery), fsparam_flag("inode64", Opt_inode64), fsparam_flag("inode32", Opt_inode32), fsparam_flag("largeio", Opt_largeio), fsparam_flag("nolargeio", Opt_nolargeio), fsparam_flag("filestreams", Opt_filestreams), fsparam_flag("quota", Opt_quota), fsparam_flag("noquota", Opt_noquota), fsparam_flag("usrquota", Opt_usrquota), fsparam_flag("grpquota", Opt_grpquota), fsparam_flag("prjquota", Opt_prjquota), fsparam_flag("uquota", Opt_uquota), fsparam_flag("gquota", Opt_gquota), fsparam_flag("pquota", Opt_pquota), fsparam_flag("uqnoenforce", Opt_uqnoenforce), fsparam_flag("gqnoenforce", Opt_gqnoenforce), fsparam_flag("pqnoenforce", Opt_pqnoenforce), fsparam_flag("qnoenforce", Opt_qnoenforce), fsparam_flag("discard", Opt_discard), fsparam_flag("nodiscard", Opt_nodiscard), fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, dax_param_enums), fsparam_u32("max_open_zones", Opt_max_open_zones), fsparam_flag("lifetime", Opt_lifetime), fsparam_flag("nolifetime", Opt_nolifetime), fsparam_string("max_atomic_write", Opt_max_atomic_write), {} }; struct proc_xfs_info { uint64_t flag; char *str; }; static int xfs_fs_show_options( struct seq_file *m, struct dentry *root) { static struct proc_xfs_info xfs_info_set[] = { /* the few simple ones we can get from the mount struct */ { XFS_FEAT_WSYNC, ",wsync" }, { XFS_FEAT_NOALIGN, ",noalign" }, { XFS_FEAT_SWALLOC, ",swalloc" }, { XFS_FEAT_NOUUID, ",nouuid" }, { XFS_FEAT_NORECOVERY, ",norecovery" }, { XFS_FEAT_FILESTREAMS, ",filestreams" }, { XFS_FEAT_GRPID, ",grpid" }, { XFS_FEAT_DISCARD, ",discard" }, { XFS_FEAT_LARGE_IOSIZE, ",largeio" }, { XFS_FEAT_DAX_ALWAYS, ",dax=always" }, { XFS_FEAT_DAX_NEVER, ",dax=never" }, { XFS_FEAT_NOLIFETIME, ",nolifetime" }, { 0, NULL } }; struct xfs_mount *mp = XFS_M(root->d_sb); struct proc_xfs_info *xfs_infop; for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) { if (mp->m_features & xfs_infop->flag) seq_puts(m, xfs_infop->str); } seq_printf(m, ",inode%d", xfs_has_small_inums(mp) ? 32 : 64); if (xfs_has_allocsize(mp)) seq_printf(m, ",allocsize=%dk", (1 << mp->m_allocsize_log) >> 10); if (mp->m_logbufs > 0) seq_printf(m, ",logbufs=%d", mp->m_logbufs); if (mp->m_logbsize > 0) seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10); if (mp->m_logname) seq_show_option(m, "logdev", mp->m_logname); if (mp->m_rtname) seq_show_option(m, "rtdev", mp->m_rtname); if (mp->m_dalign > 0) seq_printf(m, ",sunit=%d", (int)XFS_FSB_TO_BB(mp, mp->m_dalign)); if (mp->m_swidth > 0) seq_printf(m, ",swidth=%d", (int)XFS_FSB_TO_BB(mp, mp->m_swidth)); if (mp->m_qflags & XFS_UQUOTA_ENFD) seq_puts(m, ",usrquota"); else if (mp->m_qflags & XFS_UQUOTA_ACCT) seq_puts(m, ",uqnoenforce"); if (mp->m_qflags & XFS_PQUOTA_ENFD) seq_puts(m, ",prjquota"); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, ",pqnoenforce"); if (mp->m_qflags & XFS_GQUOTA_ENFD) seq_puts(m, ",grpquota"); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, ",gqnoenforce"); if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT)) seq_puts(m, ",noquota"); if (mp->m_max_open_zones) seq_printf(m, ",max_open_zones=%u", mp->m_max_open_zones); if (mp->m_awu_max_bytes) seq_printf(m, ",max_atomic_write=%lluk", mp->m_awu_max_bytes >> 10); return 0; } static bool xfs_set_inode_alloc_perag( struct xfs_perag *pag, xfs_ino_t ino, xfs_agnumber_t max_metadata) { if (!xfs_is_inode32(pag_mount(pag))) { set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return false; } if (ino > XFS_MAXINUMBER_32) { clear_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return false; } set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); if (pag_agno(pag) < max_metadata) set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); else clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return true; } /* * Set parameters for inode allocation heuristics, taking into account * filesystem size and inode32/inode64 mount options; i.e. specifically * whether or not XFS_FEAT_SMALL_INUMS is set. * * Inode allocation patterns are altered only if inode32 is requested * (XFS_FEAT_SMALL_INUMS), and the filesystem is sufficiently large. * If altered, XFS_OPSTATE_INODE32 is set as well. * * An agcount independent of that in the mount structure is provided * because in the growfs case, mp->m_sb.sb_agcount is not yet updated * to the potentially higher ag count. * * Returns the maximum AG index which may contain inodes. */ xfs_agnumber_t xfs_set_inode_alloc( struct xfs_mount *mp, xfs_agnumber_t agcount) { xfs_agnumber_t index; xfs_agnumber_t maxagi = 0; xfs_sb_t *sbp = &mp->m_sb; xfs_agnumber_t max_metadata; xfs_agino_t agino; xfs_ino_t ino; /* * Calculate how much should be reserved for inodes to meet * the max inode percentage. Used only for inode32. */ if (M_IGEO(mp)->maxicount) { uint64_t icount; icount = sbp->sb_dblocks * sbp->sb_imax_pct; do_div(icount, 100); icount += sbp->sb_agblocks - 1; do_div(icount, sbp->sb_agblocks); max_metadata = icount; } else { max_metadata = agcount; } /* Get the last possible inode in the filesystem */ agino = XFS_AGB_TO_AGINO(mp, sbp->sb_agblocks - 1); ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino); /* * If user asked for no more than 32-bit inodes, and the fs is * sufficiently large, set XFS_OPSTATE_INODE32 if we must alter * the allocator to accommodate the request. */ if (xfs_has_small_inums(mp) && ino > XFS_MAXINUMBER_32) xfs_set_inode32(mp); else xfs_clear_inode32(mp); for (index = 0; index < agcount; index++) { struct xfs_perag *pag; ino = XFS_AGINO_TO_INO(mp, index, agino); pag = xfs_perag_get(mp, index); if (xfs_set_inode_alloc_perag(pag, ino, max_metadata)) maxagi++; xfs_perag_put(pag); } return xfs_is_inode32(mp) ? maxagi : agcount; } static int xfs_setup_dax_always( struct xfs_mount *mp) { if (!mp->m_ddev_targp->bt_daxdev && (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) { xfs_alert(mp, "DAX unsupported by block device. Turning off DAX."); goto disable_dax; } if (mp->m_super->s_blocksize != PAGE_SIZE) { xfs_alert(mp, "DAX not supported for blocksize. Turning off DAX."); goto disable_dax; } if (xfs_has_reflink(mp) && bdev_is_partition(mp->m_ddev_targp->bt_bdev)) { xfs_alert(mp, "DAX and reflink cannot work with multi-partitions!"); return -EINVAL; } return 0; disable_dax: xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER); return 0; } STATIC int xfs_blkdev_get( xfs_mount_t *mp, const char *name, struct file **bdev_filep) { int error = 0; blk_mode_t mode; mode = sb_open_mode(mp->m_super->s_flags); *bdev_filep = bdev_file_open_by_path(name, mode, mp->m_super, &fs_holder_ops); if (IS_ERR(*bdev_filep)) { error = PTR_ERR(*bdev_filep); *bdev_filep = NULL; xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } return error; } STATIC void xfs_shutdown_devices( struct xfs_mount *mp) { /* * Udev is triggered whenever anyone closes a block device or unmounts * a file systemm on a block device. * The default udev rules invoke blkid to read the fs super and create * symlinks to the bdev under /dev/disk. For this, it uses buffered * reads through the page cache. * * xfs_db also uses buffered reads to examine metadata. There is no * coordination between xfs_db and udev, which means that they can run * concurrently. Note there is no coordination between the kernel and * blkid either. * * On a system with 64k pages, the page cache can cache the superblock * and the root inode (and hence the root directory) with the same 64k * page. If udev spawns blkid after the mkfs and the system is busy * enough that it is still running when xfs_db starts up, they'll both * read from the same page in the pagecache. * * The unmount writes updated inode metadata to disk directly. The XFS * buffer cache does not use the bdev pagecache, so it needs to * invalidate that pagecache on unmount. If the above scenario occurs, * the pagecache no longer reflects what's on disk, xfs_db reads the * stale metadata, and fails to find /a. Most of the time this succeeds * because closing a bdev invalidates the page cache, but when processes * race, everyone loses. */ if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } if (mp->m_rtdev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); invalidate_bdev(mp->m_ddev_targp->bt_bdev); } /* * The file system configurations are: * (1) device (partition) with data and internal log * (2) logical volume with data and log subvolumes. * (3) logical volume with data, log, and realtime subvolumes. * * We only have to handle opening the log and realtime volumes here if * they are present. The data subvolume has already been opened by * get_sb_bdev() and is stored in sb->s_bdev. */ STATIC int xfs_open_devices( struct xfs_mount *mp) { struct super_block *sb = mp->m_super; struct block_device *ddev = sb->s_bdev; struct file *logdev_file = NULL, *rtdev_file = NULL; int error; /* * Open real time and log devices - order is important. */ if (mp->m_logname) { error = xfs_blkdev_get(mp, mp->m_logname, &logdev_file); if (error) return error; } if (mp->m_rtname) { error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_file); if (error) goto out_close_logdev; if (file_bdev(rtdev_file) == ddev || (logdev_file && file_bdev(rtdev_file) == file_bdev(logdev_file))) { xfs_warn(mp, "Cannot mount filesystem with identical rtdev and ddev/logdev."); error = -EINVAL; goto out_close_rtdev; } } /* * Setup xfs_mount buffer target pointers */ mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_file); if (IS_ERR(mp->m_ddev_targp)) { error = PTR_ERR(mp->m_ddev_targp); mp->m_ddev_targp = NULL; goto out_close_rtdev; } if (rtdev_file) { mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_file); if (IS_ERR(mp->m_rtdev_targp)) { error = PTR_ERR(mp->m_rtdev_targp); mp->m_rtdev_targp = NULL; goto out_free_ddev_targ; } } if (logdev_file && file_bdev(logdev_file) != ddev) { mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_file); if (IS_ERR(mp->m_logdev_targp)) { error = PTR_ERR(mp->m_logdev_targp); mp->m_logdev_targp = NULL; goto out_free_rtdev_targ; } } else { mp->m_logdev_targp = mp->m_ddev_targp; /* Handle won't be used, drop it */ if (logdev_file) bdev_fput(logdev_file); } return 0; out_free_rtdev_targ: if (mp->m_rtdev_targp) xfs_free_buftarg(mp->m_rtdev_targp); out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: if (rtdev_file) bdev_fput(rtdev_file); out_close_logdev: if (logdev_file) bdev_fput(logdev_file); return error; } /* * Setup xfs_mount buffer target pointers based on superblock */ STATIC int xfs_setup_devices( struct xfs_mount *mp) { int error; error = xfs_configure_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize, mp->m_sb.sb_dblocks); if (error) return error; if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { unsigned int log_sector_size = BBSIZE; if (xfs_has_sector(mp)) log_sector_size = mp->m_sb.sb_logsectsize; error = xfs_configure_buftarg(mp->m_logdev_targp, log_sector_size, mp->m_sb.sb_logblocks); if (error) return error; } if (mp->m_sb.sb_rtstart) { if (mp->m_rtdev_targp) { xfs_warn(mp, "can't use internal and external rtdev at the same time"); return -EINVAL; } mp->m_rtdev_targp = mp->m_ddev_targp; } else if (mp->m_rtname) { error = xfs_configure_buftarg(mp->m_rtdev_targp, mp->m_sb.sb_sectsize, mp->m_sb.sb_rblocks); if (error) return error; } return 0; } STATIC int xfs_init_mount_workqueues( struct xfs_mount *mp) { mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU), 1, mp->m_super->s_id); if (!mp->m_buf_workqueue) goto out; mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU), 0, mp->m_super->s_id); if (!mp->m_unwritten_workqueue) goto out_destroy_buf; mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU), 0, mp->m_super->s_id); if (!mp->m_reclaim_workqueue) goto out_destroy_unwritten; mp->m_blockgc_wq = alloc_workqueue("xfs-blockgc/%s", XFS_WQFLAGS(WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM), 0, mp->m_super->s_id); if (!mp->m_blockgc_wq) goto out_destroy_reclaim; mp->m_inodegc_wq = alloc_workqueue("xfs-inodegc/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU), 1, mp->m_super->s_id); if (!mp->m_inodegc_wq) goto out_destroy_blockgc; mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_PERCPU), 0, mp->m_super->s_id); if (!mp->m_sync_workqueue) goto out_destroy_inodegc; return 0; out_destroy_inodegc: destroy_workqueue(mp->m_inodegc_wq); out_destroy_blockgc: destroy_workqueue(mp->m_blockgc_wq); out_destroy_reclaim: destroy_workqueue(mp->m_reclaim_workqueue); out_destroy_unwritten: destroy_workqueue(mp->m_unwritten_workqueue); out_destroy_buf: destroy_workqueue(mp->m_buf_workqueue); out: return -ENOMEM; } STATIC void xfs_destroy_mount_workqueues( struct xfs_mount *mp) { destroy_workqueue(mp->m_sync_workqueue); destroy_workqueue(mp->m_blockgc_wq); destroy_workqueue(mp->m_inodegc_wq); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); destroy_workqueue(mp->m_buf_workqueue); } static void xfs_flush_inodes_worker( struct work_struct *work) { struct xfs_mount *mp = container_of(work, struct xfs_mount, m_flush_inodes_work); struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { sync_inodes_sb(sb); up_read(&sb->s_umount); } } /* * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK * or a page lock. We use sync_inodes_sb() here to ensure we block while waiting * for IO to complete so that we effectively throttle multiple callers to the * rate at which IO is completing. */ void xfs_flush_inodes( struct xfs_mount *mp) { /* * If flush_work() returns true then that means we waited for a flush * which was already in progress. Don't bother running another scan. */ if (flush_work(&mp->m_flush_inodes_work)) return; queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work); flush_work(&mp->m_flush_inodes_work); } /* Catch misguided souls that try to use this interface on XFS */ STATIC struct inode * xfs_fs_alloc_inode( struct super_block *sb) { BUG(); return NULL; } /* * Now that the generic code is guaranteed not to be accessing * the linux inode, we can inactivate and reclaim the inode. */ STATIC void xfs_fs_destroy_inode( struct inode *inode) { struct xfs_inode *ip = XFS_I(inode); trace_xfs_destroy_inode(ip); ASSERT(!rwsem_is_locked(&inode->i_rwsem)); XFS_STATS_INC(ip->i_mount, vn_rele); XFS_STATS_INC(ip->i_mount, vn_remove); xfs_inode_mark_reclaimable(ip); } static void xfs_fs_dirty_inode( struct inode *inode, int flags) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; if (!(inode->i_sb->s_flags & SB_LAZYTIME)) return; /* * Only do the timestamp update if the inode is dirty (I_DIRTY_SYNC) * and has dirty timestamp (I_DIRTY_TIME). I_DIRTY_TIME can be passed * in flags possibly together with I_DIRTY_SYNC. */ if ((flags & ~I_DIRTY_TIME) != I_DIRTY_SYNC || !(flags & I_DIRTY_TIME)) return; if (xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp)) return; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP); xfs_trans_commit(tp); } /* * Slab object creation initialisation for the XFS inode. * This covers only the idempotent fields in the XFS inode; * all other fields need to be initialised on allocation * from the slab. This avoids the need to repeatedly initialise * fields in the xfs inode that left in the initialise state * when freeing the inode. */ STATIC void xfs_fs_inode_init_once( void *inode) { struct xfs_inode *ip = inode; memset(ip, 0, sizeof(struct xfs_inode)); /* vfs inode */ inode_init_once(VFS_I(ip)); /* xfs inode */ atomic_set(&ip->i_pincount, 0); spin_lock_init(&ip->i_flags_lock); init_rwsem(&ip->i_lock); } /* * We do an unlocked check for XFS_IDONTCACHE here because we are already * serialised against cache hits here via the inode->i_lock and igrab() in * xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be * racing with us, and it avoids needing to grab a spinlock here for every inode * we drop the final reference on. */ STATIC int xfs_fs_drop_inode( struct inode *inode) { struct xfs_inode *ip = XFS_I(inode); /* * If this unlinked inode is in the middle of recovery, don't * drop the inode just yet; log recovery will take care of * that. See the comment for this inode flag. */ if (ip->i_flags & XFS_IRECOVERY) { ASSERT(xlog_recovery_needed(ip->i_mount->m_log)); return 0; } return inode_generic_drop(inode); } STATIC void xfs_fs_evict_inode( struct inode *inode) { if (IS_DAX(inode)) dax_break_layout_final(inode); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } static void xfs_mount_free( struct xfs_mount *mp) { if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_logdev_targp); if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_rtdev_targp); if (mp->m_ddev_targp) xfs_free_buftarg(mp->m_ddev_targp); debugfs_remove(mp->m_debugfs); kfree(mp->m_rtname); kfree(mp->m_logname); kfree(mp); } STATIC int xfs_fs_sync_fs( struct super_block *sb, int wait) { struct xfs_mount *mp = XFS_M(sb); int error; trace_xfs_fs_sync_fs(mp, __return_address); /* * Doing anything during the async pass would be counterproductive. */ if (!wait) return 0; error = xfs_log_force(mp, XFS_LOG_SYNC); if (error) return error; if (laptop_mode) { /* * The disk must be active because we're syncing. * We schedule log work now (now that the disk is * active) instead of later (when it might not be). */ flush_delayed_work(&mp->m_log->l_work); } /* * If we are called with page faults frozen out, it means we are about * to freeze the transaction subsystem. Take the opportunity to shut * down inodegc because once SB_FREEZE_FS is set it's too late to * prevent inactivation races with freeze. The fs doesn't get called * again by the freezing process until after SB_FREEZE_FS has been set, * so it's now or never. Same logic applies to speculative allocation * garbage collection. * * We don't care if this is a normal syncfs call that does this or * freeze that does this - we can run this multiple times without issue * and we won't race with a restart because a restart can only occur * when the state is either SB_FREEZE_FS or SB_FREEZE_COMPLETE. */ if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) { xfs_inodegc_stop(mp); xfs_blockgc_stop(mp); xfs_zone_gc_stop(mp); } return 0; } static xfs_extlen_t xfs_internal_log_size( struct xfs_mount *mp) { if (!mp->m_sb.sb_logstart) return 0; return mp->m_sb.sb_logblocks; } static void xfs_statfs_data( struct xfs_mount *mp, struct kstatfs *st) { int64_t fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS); /* make sure st->f_bfree does not underflow */ st->f_bfree = max(0LL, fdblocks - xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS)); /* * sb_dblocks can change during growfs, but nothing cares about reporting * the old or new value during growfs. */ st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp); } /* * When stat(v)fs is called on a file with the realtime bit set or a directory * with the rtinherit bit, report freespace information for the RT device * instead of the main data device. */ static void xfs_statfs_rt( struct xfs_mount *mp, struct kstatfs *st) { st->f_bfree = xfs_rtbxlen_to_blen(mp, xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); st->f_blocks = mp->m_sb.sb_rblocks - xfs_rtbxlen_to_blen(mp, mp->m_free[XC_FREE_RTEXTENTS].res_total); } static void xfs_statfs_inodes( struct xfs_mount *mp, struct kstatfs *st) { uint64_t icount = percpu_counter_sum(&mp->m_icount); uint64_t ifree = percpu_counter_sum(&mp->m_ifree); uint64_t fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree); st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); if (M_IGEO(mp)->maxicount) st->f_files = min_t(typeof(st->f_files), st->f_files, M_IGEO(mp)->maxicount); /* If sb_icount overshot maxicount, report actual allocation */ st->f_files = max_t(typeof(st->f_files), st->f_files, mp->m_sb.sb_icount); /* Make sure st->f_ffree does not underflow */ st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree)); } STATIC int xfs_fs_statfs( struct dentry *dentry, struct kstatfs *st) { struct xfs_mount *mp = XFS_M(dentry->d_sb); struct xfs_inode *ip = XFS_I(d_inode(dentry)); /* * Expedite background inodegc but don't wait. We do not want to block * here waiting hours for a billion extent file to be truncated. */ xfs_inodegc_push(mp); st->f_type = XFS_SUPER_MAGIC; st->f_namelen = MAXNAMELEN - 1; st->f_bsize = mp->m_sb.sb_blocksize; st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev)); xfs_statfs_data(mp, st); xfs_statfs_inodes(mp, st); if (XFS_IS_REALTIME_MOUNT(mp) && (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) xfs_statfs_rt(mp, st); if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD)) xfs_qm_statvfs(ip, st); /* * XFS does not distinguish between blocks available to privileged and * unprivileged users. */ st->f_bavail = st->f_bfree; return 0; } STATIC void xfs_save_resvblks( struct xfs_mount *mp) { enum xfs_free_counter i; for (i = 0; i < XC_FREE_NR; i++) { mp->m_free[i].res_saved = mp->m_free[i].res_total; xfs_reserve_blocks(mp, i, 0); } } STATIC void xfs_restore_resvblks( struct xfs_mount *mp) { uint64_t resblks; enum xfs_free_counter i; for (i = 0; i < XC_FREE_NR; i++) { if (mp->m_free[i].res_saved) { resblks = mp->m_free[i].res_saved; mp->m_free[i].res_saved = 0; } else resblks = xfs_default_resblks(mp, i); xfs_reserve_blocks(mp, i, resblks); } } /* * Second stage of a freeze. The data is already frozen so we only * need to take care of the metadata. Once that's done sync the superblock * to the log to dirty it in case of a crash while frozen. This ensures that we * will recover the unlinked inode lists on the next mount. */ STATIC int xfs_fs_freeze( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); unsigned int flags; int ret; /* * The filesystem is now frozen far enough that memory reclaim * cannot safely operate on the filesystem. Hence we need to * set a GFP_NOFS context here to avoid recursion deadlocks. */ flags = memalloc_nofs_save(); xfs_save_resvblks(mp); ret = xfs_log_quiesce(mp); memalloc_nofs_restore(flags); /* * For read-write filesystems, we need to restart the inodegc on error * because we stopped it at SB_FREEZE_PAGEFAULT level and a thaw is not * going to be run to restart it now. We are at SB_FREEZE_FS level * here, so we can restart safely without racing with a stop in * xfs_fs_sync_fs(). */ if (ret && !xfs_is_readonly(mp)) { xfs_blockgc_start(mp); xfs_inodegc_start(mp); xfs_zone_gc_start(mp); } return ret; } STATIC int xfs_fs_unfreeze( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); xfs_restore_resvblks(mp); xfs_log_work_queue(mp); /* * Don't reactivate the inodegc worker on a readonly filesystem because * inodes are sent directly to reclaim. Don't reactivate the blockgc * worker because there are no speculative preallocations on a readonly * filesystem. */ if (!xfs_is_readonly(mp)) { xfs_zone_gc_start(mp); xfs_blockgc_start(mp); xfs_inodegc_start(mp); } return 0; } /* * This function fills in xfs_mount_t fields based on mount args. * Note: the superblock _has_ now been read in. */ STATIC int xfs_finish_flags( struct xfs_mount *mp) { /* Fail a mount where the logbuf is smaller than the log stripe */ if (xfs_has_logv2(mp)) { if (mp->m_logbsize <= 0 && mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) { mp->m_logbsize = mp->m_sb.sb_logsunit; } else if (mp->m_logbsize > 0 && mp->m_logbsize < mp->m_sb.sb_logsunit) { xfs_warn(mp, "logbuf size must be greater than or equal to log stripe size"); return -EINVAL; } } else { /* Fail a mount if the logbuf is larger than 32K */ if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) { xfs_warn(mp, "logbuf size for version 1 logs must be 16K or 32K"); return -EINVAL; } } /* * prohibit r/w mounts of read-only filesystems */ if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !xfs_is_readonly(mp)) { xfs_warn(mp, "cannot mount a read-only filesystem as read-write"); return -EROFS; } if ((mp->m_qflags & XFS_GQUOTA_ACCT) && (mp->m_qflags & XFS_PQUOTA_ACCT) && !xfs_has_pquotino(mp)) { xfs_warn(mp, "Super block does not support project and group quota together"); return -EINVAL; } if (!xfs_has_zoned(mp)) { if (mp->m_max_open_zones) { xfs_warn(mp, "max_open_zones mount option only supported on zoned file systems."); return -EINVAL; } if (mp->m_features & XFS_FEAT_NOLIFETIME) { xfs_warn(mp, "nolifetime mount option only supported on zoned file systems."); return -EINVAL; } } return 0; } static int xfs_init_percpu_counters( struct xfs_mount *mp) { int error; int i; error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL); if (error) return -ENOMEM; error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL); if (error) goto free_icount; error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL); if (error) goto free_ifree; error = percpu_counter_init(&mp->m_delalloc_rtextents, 0, GFP_KERNEL); if (error) goto free_delalloc; for (i = 0; i < XC_FREE_NR; i++) { error = percpu_counter_init(&mp->m_free[i].count, 0, GFP_KERNEL); if (error) goto free_freecounters; } return 0; free_freecounters: while (--i >= 0) percpu_counter_destroy(&mp->m_free[i].count); percpu_counter_destroy(&mp->m_delalloc_rtextents); free_delalloc: percpu_counter_destroy(&mp->m_delalloc_blks); free_ifree: percpu_counter_destroy(&mp->m_ifree); free_icount: percpu_counter_destroy(&mp->m_icount); return -ENOMEM; } void xfs_reinit_percpu_counters( struct xfs_mount *mp) { percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount); percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree); xfs_set_freecounter(mp, XC_FREE_BLOCKS, mp->m_sb.sb_fdblocks); if (!xfs_has_zoned(mp)) xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, mp->m_sb.sb_frextents); } static void xfs_destroy_percpu_counters( struct xfs_mount *mp) { enum xfs_free_counter i; for (i = 0; i < XC_FREE_NR; i++) percpu_counter_destroy(&mp->m_free[i].count); percpu_counter_destroy(&mp->m_icount); percpu_counter_destroy(&mp->m_ifree); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_rtextents) == 0); percpu_counter_destroy(&mp->m_delalloc_rtextents); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_blks) == 0); percpu_counter_destroy(&mp->m_delalloc_blks); } static int xfs_inodegc_init_percpu( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; mp->m_inodegc = alloc_percpu(struct xfs_inodegc); if (!mp->m_inodegc) return -ENOMEM; for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); gc->cpu = cpu; gc->mp = mp; init_llist_head(&gc->list); gc->items = 0; gc->error = 0; INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker); } return 0; } static void xfs_inodegc_free_percpu( struct xfs_mount *mp) { if (!mp->m_inodegc) return; free_percpu(mp->m_inodegc); } static void xfs_fs_put_super( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); xfs_notice(mp, "Unmounting Filesystem %pU", &mp->m_sb.sb_uuid); xfs_filestream_unmount(mp); xfs_unmountfs(mp); xfs_rtmount_freesb(mp); xfs_freesb(mp); xchk_mount_stats_free(mp); free_percpu(mp->m_stats.xs_stats); xfs_inodegc_free_percpu(mp); xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); xfs_shutdown_devices(mp); } static long xfs_fs_nr_cached_objects( struct super_block *sb, struct shrink_control *sc) { /* Paranoia: catch incorrect calls during mount setup or teardown */ if (WARN_ON_ONCE(!sb->s_fs_info)) return 0; return xfs_reclaim_inodes_count(XFS_M(sb)); } static long xfs_fs_free_cached_objects( struct super_block *sb, struct shrink_control *sc) { return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan); } static void xfs_fs_shutdown( struct super_block *sb) { xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED); } static int xfs_fs_show_stats( struct seq_file *m, struct dentry *root) { struct xfs_mount *mp = XFS_M(root->d_sb); if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT)) xfs_zoned_show_stats(m, mp); return 0; } static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, .dirty_inode = xfs_fs_dirty_inode, .drop_inode = xfs_fs_drop_inode, .evict_inode = xfs_fs_evict_inode, .put_super = xfs_fs_put_super, .sync_fs = xfs_fs_sync_fs, .freeze_fs = xfs_fs_freeze, .unfreeze_fs = xfs_fs_unfreeze, .statfs = xfs_fs_statfs, .show_options = xfs_fs_show_options, .nr_cached_objects = xfs_fs_nr_cached_objects, .free_cached_objects = xfs_fs_free_cached_objects, .shutdown = xfs_fs_shutdown, .show_stats = xfs_fs_show_stats, }; static int suffix_kstrtoint( const char *s, unsigned int base, int *res) { int last, shift_left_factor = 0, _res; char *value; int ret = 0; value = kstrdup(s, GFP_KERNEL); if (!value) return -ENOMEM; last = strlen(value) - 1; if (value[last] == 'K' || value[last] == 'k') { shift_left_factor = 10; value[last] = '\0'; } if (value[last] == 'M' || value[last] == 'm') { shift_left_factor = 20; value[last] = '\0'; } if (value[last] == 'G' || value[last] == 'g') { shift_left_factor = 30; value[last] = '\0'; } if (kstrtoint(value, base, &_res)) ret = -EINVAL; kfree(value); *res = _res << shift_left_factor; return ret; } static int suffix_kstrtoull( const char *s, unsigned int base, unsigned long long *res) { int last, shift_left_factor = 0; unsigned long long _res; char *value; int ret = 0; value = kstrdup(s, GFP_KERNEL); if (!value) return -ENOMEM; last = strlen(value) - 1; if (value[last] == 'K' || value[last] == 'k') { shift_left_factor = 10; value[last] = '\0'; } if (value[last] == 'M' || value[last] == 'm') { shift_left_factor = 20; value[last] = '\0'; } if (value[last] == 'G' || value[last] == 'g') { shift_left_factor = 30; value[last] = '\0'; } if (kstrtoull(value, base, &_res)) ret = -EINVAL; kfree(value); *res = _res << shift_left_factor; return ret; } static inline void xfs_fs_warn_deprecated( struct fs_context *fc, struct fs_parameter *param, uint64_t flag, bool value) { /* Don't print the warning if reconfiguring and current mount point * already had the flag set */ if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) && !!(XFS_M(fc->root->d_sb)->m_features & flag) == value) return; xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key); } /* * Set mount state from a mount option. * * NOTE: mp->m_super is NULL here! */ static int xfs_fs_parse_param( struct fs_context *fc, struct fs_parameter *param) { struct xfs_mount *parsing_mp = fc->s_fs_info; struct fs_parse_result result; int size = 0; int opt; BUILD_BUG_ON(XFS_QFLAGS_MNTOPTS & XFS_MOUNT_QUOTA_ALL); opt = fs_parse(fc, xfs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_logbufs: parsing_mp->m_logbufs = result.uint_32; return 0; case Opt_logbsize: if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize)) return -EINVAL; return 0; case Opt_logdev: kfree(parsing_mp->m_logname); parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL); if (!parsing_mp->m_logname) return -ENOMEM; return 0; case Opt_rtdev: kfree(parsing_mp->m_rtname); parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL); if (!parsing_mp->m_rtname) return -ENOMEM; return 0; case Opt_allocsize: if (suffix_kstrtoint(param->string, 10, &size)) return -EINVAL; parsing_mp->m_allocsize_log = ffs(size) - 1; parsing_mp->m_features |= XFS_FEAT_ALLOCSIZE; return 0; case Opt_grpid: case Opt_bsdgroups: parsing_mp->m_features |= XFS_FEAT_GRPID; return 0; case Opt_nogrpid: case Opt_sysvgroups: parsing_mp->m_features &= ~XFS_FEAT_GRPID; return 0; case Opt_wsync: parsing_mp->m_features |= XFS_FEAT_WSYNC; return 0; case Opt_norecovery: parsing_mp->m_features |= XFS_FEAT_NORECOVERY; return 0; case Opt_noalign: parsing_mp->m_features |= XFS_FEAT_NOALIGN; return 0; case Opt_swalloc: parsing_mp->m_features |= XFS_FEAT_SWALLOC; return 0; case Opt_sunit: parsing_mp->m_dalign = result.uint_32; return 0; case Opt_swidth: parsing_mp->m_swidth = result.uint_32; return 0; case Opt_inode32: parsing_mp->m_features |= XFS_FEAT_SMALL_INUMS; return 0; case Opt_inode64: parsing_mp->m_features &= ~XFS_FEAT_SMALL_INUMS; return 0; case Opt_nouuid: parsing_mp->m_features |= XFS_FEAT_NOUUID; return 0; case Opt_largeio: parsing_mp->m_features |= XFS_FEAT_LARGE_IOSIZE; return 0; case Opt_nolargeio: parsing_mp->m_features &= ~XFS_FEAT_LARGE_IOSIZE; return 0; case Opt_filestreams: parsing_mp->m_features |= XFS_FEAT_FILESTREAMS; return 0; case Opt_noquota: parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_quota: case Opt_uquota: case Opt_usrquota: parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_qnoenforce: case Opt_uqnoenforce: parsing_mp->m_qflags |= XFS_UQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_pquota: case Opt_prjquota: parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_pqnoenforce: parsing_mp->m_qflags |= XFS_PQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_gquota: case Opt_grpquota: parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_gqnoenforce: parsing_mp->m_qflags |= XFS_GQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_discard: parsing_mp->m_features |= XFS_FEAT_DISCARD; return 0; case Opt_nodiscard: parsing_mp->m_features &= ~XFS_FEAT_DISCARD; return 0; #ifdef CONFIG_FS_DAX case Opt_dax: xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS); return 0; case Opt_dax_enum: xfs_mount_set_dax_mode(parsing_mp, result.uint_32); return 0; #endif /* Following mount options will be removed in September 2025 */ case Opt_max_open_zones: parsing_mp->m_max_open_zones = result.uint_32; return 0; case Opt_lifetime: parsing_mp->m_features &= ~XFS_FEAT_NOLIFETIME; return 0; case Opt_nolifetime: parsing_mp->m_features |= XFS_FEAT_NOLIFETIME; return 0; case Opt_max_atomic_write: if (suffix_kstrtoull(param->string, 10, &parsing_mp->m_awu_max_bytes)) { xfs_warn(parsing_mp, "max atomic write size must be positive integer"); return -EINVAL; } return 0; default: xfs_warn(parsing_mp, "unknown mount option [%s].", param->key); return -EINVAL; } return 0; } static int xfs_fs_validate_params( struct xfs_mount *mp) { /* No recovery flag requires a read-only mount */ if (xfs_has_norecovery(mp) && !xfs_is_readonly(mp)) { xfs_warn(mp, "no-recovery mounts must be read-only."); return -EINVAL; } if (xfs_has_noalign(mp) && (mp->m_dalign || mp->m_swidth)) { xfs_warn(mp, "sunit and swidth options incompatible with the noalign option"); return -EINVAL; } if (!IS_ENABLED(CONFIG_XFS_QUOTA) && (mp->m_qflags & ~XFS_QFLAGS_MNTOPTS)) { xfs_warn(mp, "quota support not available in this kernel."); return -EINVAL; } if ((mp->m_dalign && !mp->m_swidth) || (!mp->m_dalign && mp->m_swidth)) { xfs_warn(mp, "sunit and swidth must be specified together"); return -EINVAL; } if (mp->m_dalign && (mp->m_swidth % mp->m_dalign != 0)) { xfs_warn(mp, "stripe width (%d) must be a multiple of the stripe unit (%d)", mp->m_swidth, mp->m_dalign); return -EINVAL; } if (mp->m_logbufs != -1 && mp->m_logbufs != 0 && (mp->m_logbufs < XLOG_MIN_ICLOGS || mp->m_logbufs > XLOG_MAX_ICLOGS)) { xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]", mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS); return -EINVAL; } if (mp->m_logbsize != -1 && mp->m_logbsize != 0 && (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE || mp->m_logbsize > XLOG_MAX_RECORD_BSIZE || !is_power_of_2(mp->m_logbsize))) { xfs_warn(mp, "invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]", mp->m_logbsize); return -EINVAL; } if (xfs_has_allocsize(mp) && (mp->m_allocsize_log > XFS_MAX_IO_LOG || mp->m_allocsize_log < XFS_MIN_IO_LOG)) { xfs_warn(mp, "invalid log iosize: %d [not %d-%d]", mp->m_allocsize_log, XFS_MIN_IO_LOG, XFS_MAX_IO_LOG); return -EINVAL; } return 0; } struct dentry * xfs_debugfs_mkdir( const char *name, struct dentry *parent) { struct dentry *child; /* Apparently we're expected to ignore error returns?? */ child = debugfs_create_dir(name, parent); if (IS_ERR(child)) return NULL; return child; } static int xfs_fs_fill_super( struct super_block *sb, struct fs_context *fc) { struct xfs_mount *mp = sb->s_fs_info; struct inode *root; int flags = 0, error; mp->m_super = sb; /* * Copy VFS mount flags from the context now that all parameter parsing * is guaranteed to have been completed by either the old mount API or * the newer fsopen/fsconfig API. */ if (fc->sb_flags & SB_RDONLY) xfs_set_readonly(mp); if (fc->sb_flags & SB_DIRSYNC) mp->m_features |= XFS_FEAT_DIRSYNC; if (fc->sb_flags & SB_SYNCHRONOUS) mp->m_features |= XFS_FEAT_WSYNC; error = xfs_fs_validate_params(mp); if (error) return error; sb_min_blocksize(sb, BBSIZE); sb->s_xattr = xfs_xattr_handlers; sb->s_export_op = &xfs_export_operations; #ifdef CONFIG_XFS_QUOTA sb->s_qcop = &xfs_quotactl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif sb->s_op = &xfs_super_operations; /* * Delay mount work if the debug hook is set. This is debug * instrumention to coordinate simulation of xfs mount failures with * VFS superblock operations */ if (xfs_globals.mount_delay) { xfs_notice(mp, "Delaying mount for %d seconds.", xfs_globals.mount_delay); msleep(xfs_globals.mount_delay * 1000); } if (fc->sb_flags & SB_SILENT) flags |= XFS_MFSI_QUIET; error = xfs_open_devices(mp); if (error) return error; if (xfs_debugfs) { mp->m_debugfs = xfs_debugfs_mkdir(mp->m_super->s_id, xfs_debugfs); } else { mp->m_debugfs = NULL; } error = xfs_init_mount_workqueues(mp); if (error) goto out_shutdown_devices; error = xfs_init_percpu_counters(mp); if (error) goto out_destroy_workqueues; error = xfs_inodegc_init_percpu(mp); if (error) goto out_destroy_counters; /* Allocate stats memory before we do operations that might use it */ mp->m_stats.xs_stats = alloc_percpu(struct xfsstats); if (!mp->m_stats.xs_stats) { error = -ENOMEM; goto out_destroy_inodegc; } error = xchk_mount_stats_alloc(mp); if (error) goto out_free_stats; error = xfs_readsb(mp, flags); if (error) goto out_free_scrub_stats; error = xfs_finish_flags(mp); if (error) goto out_free_sb; error = xfs_setup_devices(mp); if (error) goto out_free_sb; /* * V4 support is undergoing deprecation. * * Note: this has to use an open coded m_features check as xfs_has_crc * always returns false for !CONFIG_XFS_SUPPORT_V4. */ if (!(mp->m_features & XFS_FEAT_CRC)) { if (!IS_ENABLED(CONFIG_XFS_SUPPORT_V4)) { xfs_warn(mp, "Deprecated V4 format (crc=0) not supported by kernel."); error = -EINVAL; goto out_free_sb; } xfs_warn_once(mp, "Deprecated V4 format (crc=0) will not be supported after September 2030."); } /* ASCII case insensitivity is undergoing deprecation. */ if (xfs_has_asciici(mp)) { #ifdef CONFIG_XFS_SUPPORT_ASCII_CI xfs_warn_once(mp, "Deprecated ASCII case-insensitivity feature (ascii-ci=1) will not be supported after September 2030."); #else xfs_warn(mp, "Deprecated ASCII case-insensitivity feature (ascii-ci=1) not supported by kernel."); error = -EINVAL; goto out_free_sb; #endif } /* * Filesystem claims it needs repair, so refuse the mount unless * norecovery is also specified, in which case the filesystem can * be mounted with no risk of further damage. */ if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; } /* * Don't touch the filesystem if a user tool thinks it owns the primary * superblock. mkfs doesn't clear the flag from secondary supers, so * we don't check them at all. */ if (mp->m_sb.sb_inprogress) { xfs_warn(mp, "Offline file system operation in progress!"); error = -EFSCORRUPTED; goto out_free_sb; } if (mp->m_sb.sb_blocksize > PAGE_SIZE) { size_t max_folio_size = mapping_max_folio_size_supported(); if (!xfs_has_crc(mp)) { xfs_warn(mp, "V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.", mp->m_sb.sb_blocksize, PAGE_SIZE); error = -ENOSYS; goto out_free_sb; } if (mp->m_sb.sb_blocksize > max_folio_size) { xfs_warn(mp, "block size (%u bytes) not supported; Only block size (%zu) or less is supported", mp->m_sb.sb_blocksize, max_folio_size); error = -ENOSYS; goto out_free_sb; } xfs_warn_experimental(mp, XFS_EXPERIMENTAL_LBS); } /* Ensure this filesystem fits in the page cache limits */ if (xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_dblocks) || xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_rblocks)) { xfs_warn(mp, "file system too large to be mounted on this system."); error = -EFBIG; goto out_free_sb; } /* * XFS block mappings use 54 bits to store the logical block offset. * This should suffice to handle the maximum file size that the VFS * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON * to check this assertion. * * Avoid integer overflow by comparing the maximum bmbt offset to the * maximum pagecache offset in units of fs blocks. */ if (!xfs_verify_fileoff(mp, XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE))) { xfs_warn(mp, "MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!", XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE), XFS_MAX_FILEOFF); error = -EINVAL; goto out_free_sb; } error = xfs_rtmount_readsb(mp); if (error) goto out_free_sb; error = xfs_filestream_mount(mp); if (error) goto out_free_rtsb; /* * we must configure the block size in the superblock before we run the * full mount process as the mount process can lookup and cache inodes. */ sb->s_magic = XFS_SUPER_MAGIC; sb->s_blocksize = mp->m_sb.sb_blocksize; sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_max_links = XFS_MAXLINK; sb->s_time_gran = 1; if (xfs_has_bigtime(mp)) { sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN); sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX); } else { sb->s_time_min = XFS_LEGACY_TIME_MIN; sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); /* version 5 superblocks support inode version counters. */ if (xfs_has_crc(mp)) sb->s_flags |= SB_I_VERSION; if (xfs_has_dax_always(mp)) { error = xfs_setup_dax_always(mp); if (error) goto out_filestream_unmount; } if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) { xfs_warn(mp, "mounting with \"discard\" option, but the device does not support discard"); mp->m_features &= ~XFS_FEAT_DISCARD; } if (xfs_has_zoned(mp)) { if (!xfs_has_metadir(mp)) { xfs_alert(mp, "metadir feature required for zoned realtime devices."); error = -EINVAL; goto out_filestream_unmount; } xfs_warn_experimental(mp, XFS_EXPERIMENTAL_ZONED); } else if (xfs_has_metadir(mp)) { xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR); } if (xfs_has_reflink(mp)) { if (xfs_has_realtime(mp) && !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) { xfs_alert(mp, "reflink not compatible with realtime extent size %u!", mp->m_sb.sb_rextsize); error = -EINVAL; goto out_filestream_unmount; } if (xfs_has_zoned(mp)) { xfs_alert(mp, "reflink not compatible with zoned RT device!"); error = -EINVAL; goto out_filestream_unmount; } if (xfs_globals.always_cow) { xfs_info(mp, "using DEBUG-only always_cow mode."); mp->m_always_cow = true; } } /* * If no quota mount options were provided, maybe we'll try to pick * up the quota accounting and enforcement flags from the ondisk sb. */ if (!(mp->m_qflags & XFS_QFLAGS_MNTOPTS)) xfs_set_resuming_quotaon(mp); mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS; error = xfs_mountfs(mp); if (error) goto out_filestream_unmount; root = igrab(VFS_I(mp->m_rootip)); if (!root) { error = -ENOENT; goto out_unmount; } sb->s_root = d_make_root(root); if (!sb->s_root) { error = -ENOMEM; goto out_unmount; } return 0; out_filestream_unmount: xfs_filestream_unmount(mp); out_free_rtsb: xfs_rtmount_freesb(mp); out_free_sb: xfs_freesb(mp); out_free_scrub_stats: xchk_mount_stats_free(mp); out_free_stats: free_percpu(mp->m_stats.xs_stats); out_destroy_inodegc: xfs_inodegc_free_percpu(mp); out_destroy_counters: xfs_destroy_percpu_counters(mp); out_destroy_workqueues: xfs_destroy_mount_workqueues(mp); out_shutdown_devices: xfs_shutdown_devices(mp); return error; out_unmount: xfs_filestream_unmount(mp); xfs_unmountfs(mp); goto out_free_rtsb; } static int xfs_fs_get_tree( struct fs_context *fc) { return get_tree_bdev(fc, xfs_fs_fill_super); } static int xfs_remount_rw( struct xfs_mount *mp) { struct xfs_sb *sbp = &mp->m_sb; int error; if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp && xfs_readonly_buftarg(mp->m_logdev_targp)) { xfs_warn(mp, "ro->rw transition prohibited by read-only logdev"); return -EACCES; } if (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp)) { xfs_warn(mp, "ro->rw transition prohibited by read-only rtdev"); return -EACCES; } if (xfs_has_norecovery(mp)) { xfs_warn(mp, "ro->rw transition prohibited on norecovery mount"); return -EINVAL; } if (xfs_sb_is_v5(sbp) && xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_warn(mp, "ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); return -EINVAL; } xfs_clear_readonly(mp); /* * If this is the first remount to writeable state we might have some * superblock changes to update. */ if (mp->m_update_sb) { error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); return error; } mp->m_update_sb = false; } /* * Fill out the reserve pool if it is empty. Use the stashed value if * it is non-zero, otherwise go with the default. */ xfs_restore_resvblks(mp); xfs_log_work_queue(mp); xfs_blockgc_start(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); if (error && error != -ENOSPC) return error; /* Re-enable the background inode inactivation worker. */ xfs_inodegc_start(mp); /* Restart zone reclaim */ xfs_zone_gc_start(mp); return 0; } static int xfs_remount_ro( struct xfs_mount *mp) { struct xfs_icwalk icw = { .icw_flags = XFS_ICWALK_FLAG_SYNC, }; int error; /* Flush all the dirty data to disk. */ error = sync_filesystem(mp->m_super); if (error) return error; /* * Cancel background eofb scanning so it cannot race with the final * log force+buftarg wait and deadlock the remount. */ xfs_blockgc_stop(mp); /* * Clear out all remaining COW staging extents and speculative post-EOF * preallocations so that we don't leave inodes requiring inactivation * cleanups during reclaim on a read-only mount. We must process every * cached inode, so this requires a synchronous cache scan. */ error = xfs_blockgc_free_space(mp, &icw); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } /* * Stop the inodegc background worker. xfs_fs_reconfigure already * flushed all pending inodegc work when it sync'd the filesystem. * The VFS holds s_umount, so we know that inodes cannot enter * xfs_fs_destroy_inode during a remount operation. In readonly mode * we send inodes straight to reclaim, so no inodes will be queued. */ xfs_inodegc_stop(mp); /* Stop zone reclaim */ xfs_zone_gc_stop(mp); /* Free the per-AG metadata reservation pool. */ xfs_fs_unreserve_ag_blocks(mp); /* * Before we sync the metadata, we need to free up the reserve block * pool so that the used block count in the superblock on disk is * correct at the end of the remount. Stash the current* reserve pool * size so that if we get remounted rw, we can return it to the same * size. */ xfs_save_resvblks(mp); xfs_log_clean(mp); xfs_set_readonly(mp); return 0; } /* * Logically we would return an error here to prevent users from believing * they might have changed mount options using remount which can't be changed. * * But unfortunately mount(8) adds all options from mtab and fstab to the mount * arguments in some cases so we can't blindly reject options, but have to * check for each specified option if it actually differs from the currently * set option and only reject it if that's the case. * * Until that is implemented we return success for every remount request, and * silently ignore all options that we can't actually change. */ static int xfs_fs_reconfigure( struct fs_context *fc) { struct xfs_mount *mp = XFS_M(fc->root->d_sb); struct xfs_mount *new_mp = fc->s_fs_info; int flags = fc->sb_flags; int error; new_mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS; /* version 5 superblocks always support version counters. */ if (xfs_has_crc(mp)) fc->sb_flags |= SB_I_VERSION; error = xfs_fs_validate_params(new_mp); if (error) return error; /* Validate new max_atomic_write option before making other changes */ if (mp->m_awu_max_bytes != new_mp->m_awu_max_bytes) { error = xfs_set_max_atomic_write_opt(mp, new_mp->m_awu_max_bytes); if (error) return error; } /* inode32 -> inode64 */ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) { mp->m_features &= ~XFS_FEAT_SMALL_INUMS; mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } /* inode64 -> inode32 */ if (!xfs_has_small_inums(mp) && xfs_has_small_inums(new_mp)) { mp->m_features |= XFS_FEAT_SMALL_INUMS; mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } /* * Now that mp has been modified according to the remount options, we * do a final option validation with xfs_finish_flags() just like it is * just like it is done during mount. We cannot use * done during mount. We cannot use xfs_finish_flags() on new_mp as it * contains only the user given options. */ error = xfs_finish_flags(mp); if (error) return error; /* ro -> rw */ if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) { error = xfs_remount_rw(mp); if (error) return error; } /* rw -> ro */ if (!xfs_is_readonly(mp) && (flags & SB_RDONLY)) { error = xfs_remount_ro(mp); if (error) return error; } return 0; } static void xfs_fs_free( struct fs_context *fc) { struct xfs_mount *mp = fc->s_fs_info; /* * mp is stored in the fs_context when it is initialized. * mp is transferred to the superblock on a successful mount, * but if an error occurs before the transfer we have to free * it here. */ if (mp) xfs_mount_free(mp); } static const struct fs_context_operations xfs_context_ops = { .parse_param = xfs_fs_parse_param, .get_tree = xfs_fs_get_tree, .reconfigure = xfs_fs_reconfigure, .free = xfs_fs_free, }; /* * WARNING: do not initialise any parameters in this function that depend on * mount option parsing having already been performed as this can be called from * fsopen() before any parameters have been set. */ static int xfs_init_fs_context( struct fs_context *fc) { struct xfs_mount *mp; int i; mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL); if (!mp) return -ENOMEM; spin_lock_init(&mp->m_sb_lock); for (i = 0; i < XG_TYPE_MAX; i++) xa_init(&mp->m_groups[i].xa); mutex_init(&mp->m_growlock); mutex_init(&mp->m_metafile_resv_lock); INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); mp->m_kobj.kobject.kset = xfs_kset; /* * We don't create the finobt per-ag space reservation until after log * recovery, so we must set this to true so that an ifree transaction * started during log recovery will not depend on space reservations * for finobt expansion. */ mp->m_finobt_nores = true; /* * These can be overridden by the mount option parsing. */ mp->m_logbufs = -1; mp->m_logbsize = -1; mp->m_allocsize_log = 16; /* 64k */ xfs_hooks_init(&mp->m_dir_update_hooks); fc->s_fs_info = mp; fc->ops = &xfs_context_ops; return 0; } static void xfs_kill_sb( struct super_block *sb) { kill_block_super(sb); xfs_mount_free(XFS_M(sb)); } static struct file_system_type xfs_fs_type = { .owner = THIS_MODULE, .name = "xfs", .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = xfs_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME | FS_LBS, }; MODULE_ALIAS_FS("xfs"); STATIC int __init xfs_init_caches(void) { int error; xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT, NULL); if (!xfs_buf_cache) goto out; xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket", sizeof(struct xlog_ticket), 0, 0, NULL); if (!xfs_log_ticket_cache) goto out_destroy_buf_cache; error = xfs_btree_init_cur_caches(); if (error) goto out_destroy_log_ticket_cache; error = rcbagbt_init_cur_cache(); if (error) goto out_destroy_btree_cur_cache; error = xfs_defer_init_item_caches(); if (error) goto out_destroy_rcbagbt_cur_cache; xfs_da_state_cache = kmem_cache_create("xfs_da_state", sizeof(struct xfs_da_state), 0, 0, NULL); if (!xfs_da_state_cache) goto out_destroy_defer_item_cache; xfs_ifork_cache = kmem_cache_create("xfs_ifork", sizeof(struct xfs_ifork), 0, 0, NULL); if (!xfs_ifork_cache) goto out_destroy_da_state_cache; xfs_trans_cache = kmem_cache_create("xfs_trans", sizeof(struct xfs_trans), 0, 0, NULL); if (!xfs_trans_cache) goto out_destroy_ifork_cache; /* * The size of the cache-allocated buf log item is the maximum * size possible under XFS. This wastes a little bit of memory, * but it is much faster. */ xfs_buf_item_cache = kmem_cache_create("xfs_buf_item", sizeof(struct xfs_buf_log_item), 0, 0, NULL); if (!xfs_buf_item_cache) goto out_destroy_trans_cache; xfs_efd_cache = kmem_cache_create("xfs_efd_item", xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_efd_cache) goto out_destroy_buf_item_cache; xfs_efi_cache = kmem_cache_create("xfs_efi_item", xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_efi_cache) goto out_destroy_efd_cache; xfs_inode_cache = kmem_cache_create("xfs_inode", sizeof(struct xfs_inode), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), xfs_fs_inode_init_once); if (!xfs_inode_cache) goto out_destroy_efi_cache; xfs_ili_cache = kmem_cache_create("xfs_ili", sizeof(struct xfs_inode_log_item), 0, SLAB_RECLAIM_ACCOUNT, NULL); if (!xfs_ili_cache) goto out_destroy_inode_cache; xfs_icreate_cache = kmem_cache_create("xfs_icr", sizeof(struct xfs_icreate_item), 0, 0, NULL); if (!xfs_icreate_cache) goto out_destroy_ili_cache; xfs_rud_cache = kmem_cache_create("xfs_rud_item", sizeof(struct xfs_rud_log_item), 0, 0, NULL); if (!xfs_rud_cache) goto out_destroy_icreate_cache; xfs_rui_cache = kmem_cache_create("xfs_rui_item", xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_rui_cache) goto out_destroy_rud_cache; xfs_cud_cache = kmem_cache_create("xfs_cud_item", sizeof(struct xfs_cud_log_item), 0, 0, NULL); if (!xfs_cud_cache) goto out_destroy_rui_cache; xfs_cui_cache = kmem_cache_create("xfs_cui_item", xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_cui_cache) goto out_destroy_cud_cache; xfs_bud_cache = kmem_cache_create("xfs_bud_item", sizeof(struct xfs_bud_log_item), 0, 0, NULL); if (!xfs_bud_cache) goto out_destroy_cui_cache; xfs_bui_cache = kmem_cache_create("xfs_bui_item", xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_bui_cache) goto out_destroy_bud_cache; xfs_attrd_cache = kmem_cache_create("xfs_attrd_item", sizeof(struct xfs_attrd_log_item), 0, 0, NULL); if (!xfs_attrd_cache) goto out_destroy_bui_cache; xfs_attri_cache = kmem_cache_create("xfs_attri_item", sizeof(struct xfs_attri_log_item), 0, 0, NULL); if (!xfs_attri_cache) goto out_destroy_attrd_cache; xfs_iunlink_cache = kmem_cache_create("xfs_iul_item", sizeof(struct xfs_iunlink_item), 0, 0, NULL); if (!xfs_iunlink_cache) goto out_destroy_attri_cache; xfs_xmd_cache = kmem_cache_create("xfs_xmd_item", sizeof(struct xfs_xmd_log_item), 0, 0, NULL); if (!xfs_xmd_cache) goto out_destroy_iul_cache; xfs_xmi_cache = kmem_cache_create("xfs_xmi_item", sizeof(struct xfs_xmi_log_item), 0, 0, NULL); if (!xfs_xmi_cache) goto out_destroy_xmd_cache; xfs_parent_args_cache = kmem_cache_create("xfs_parent_args", sizeof(struct xfs_parent_args), 0, 0, NULL); if (!xfs_parent_args_cache) goto out_destroy_xmi_cache; return 0; out_destroy_xmi_cache: kmem_cache_destroy(xfs_xmi_cache); out_destroy_xmd_cache: kmem_cache_destroy(xfs_xmd_cache); out_destroy_iul_cache: kmem_cache_destroy(xfs_iunlink_cache); out_destroy_attri_cache: kmem_cache_destroy(xfs_attri_cache); out_destroy_attrd_cache: kmem_cache_destroy(xfs_attrd_cache); out_destroy_bui_cache: kmem_cache_destroy(xfs_bui_cache); out_destroy_bud_cache: kmem_cache_destroy(xfs_bud_cache); out_destroy_cui_cache: kmem_cache_destroy(xfs_cui_cache); out_destroy_cud_cache: kmem_cache_destroy(xfs_cud_cache); out_destroy_rui_cache: kmem_cache_destroy(xfs_rui_cache); out_destroy_rud_cache: kmem_cache_destroy(xfs_rud_cache); out_destroy_icreate_cache: kmem_cache_destroy(xfs_icreate_cache); out_destroy_ili_cache: kmem_cache_destroy(xfs_ili_cache); out_destroy_inode_cache: kmem_cache_destroy(xfs_inode_cache); out_destroy_efi_cache: kmem_cache_destroy(xfs_efi_cache); out_destroy_efd_cache: kmem_cache_destroy(xfs_efd_cache); out_destroy_buf_item_cache: kmem_cache_destroy(xfs_buf_item_cache); out_destroy_trans_cache: kmem_cache_destroy(xfs_trans_cache); out_destroy_ifork_cache: kmem_cache_destroy(xfs_ifork_cache); out_destroy_da_state_cache: kmem_cache_destroy(xfs_da_state_cache); out_destroy_defer_item_cache: xfs_defer_destroy_item_caches(); out_destroy_rcbagbt_cur_cache: rcbagbt_destroy_cur_cache(); out_destroy_btree_cur_cache: xfs_btree_destroy_cur_caches(); out_destroy_log_ticket_cache: kmem_cache_destroy(xfs_log_ticket_cache); out_destroy_buf_cache: kmem_cache_destroy(xfs_buf_cache); out: return -ENOMEM; } STATIC void xfs_destroy_caches(void) { /* * Make sure all delayed rcu free are flushed before we * destroy caches. */ rcu_barrier(); kmem_cache_destroy(xfs_parent_args_cache); kmem_cache_destroy(xfs_xmd_cache); kmem_cache_destroy(xfs_xmi_cache); kmem_cache_destroy(xfs_iunlink_cache); kmem_cache_destroy(xfs_attri_cache); kmem_cache_destroy(xfs_attrd_cache); kmem_cache_destroy(xfs_bui_cache); kmem_cache_destroy(xfs_bud_cache); kmem_cache_destroy(xfs_cui_cache); kmem_cache_destroy(xfs_cud_cache); kmem_cache_destroy(xfs_rui_cache); kmem_cache_destroy(xfs_rud_cache); kmem_cache_destroy(xfs_icreate_cache); kmem_cache_destroy(xfs_ili_cache); kmem_cache_destroy(xfs_inode_cache); kmem_cache_destroy(xfs_efi_cache); kmem_cache_destroy(xfs_efd_cache); kmem_cache_destroy(xfs_buf_item_cache); kmem_cache_destroy(xfs_trans_cache); kmem_cache_destroy(xfs_ifork_cache); kmem_cache_destroy(xfs_da_state_cache); xfs_defer_destroy_item_caches(); rcbagbt_destroy_cur_cache(); xfs_btree_destroy_cur_caches(); kmem_cache_destroy(xfs_log_ticket_cache); kmem_cache_destroy(xfs_buf_cache); } STATIC int __init xfs_init_workqueues(void) { /* * The allocation workqueue can be used in memory reclaim situations * (writepage path), and parallelism is only limited by the number of * AGs in all the filesystems mounted. Hence use the default large * max_active value for this workqueue. */ xfs_alloc_wq = alloc_workqueue("xfsalloc", XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU), 0); if (!xfs_alloc_wq) return -ENOMEM; xfs_discard_wq = alloc_workqueue("xfsdiscard", XFS_WQFLAGS(WQ_UNBOUND), 0); if (!xfs_discard_wq) goto out_free_alloc_wq; return 0; out_free_alloc_wq: destroy_workqueue(xfs_alloc_wq); return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { destroy_workqueue(xfs_discard_wq); destroy_workqueue(xfs_alloc_wq); } STATIC int __init init_xfs_fs(void) { int error; xfs_check_ondisk_structs(); error = xfs_dahash_test(); if (error) return error; printk(KERN_INFO XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled\n"); xfs_dir_startup(); error = xfs_init_caches(); if (error) goto out; error = xfs_init_workqueues(); if (error) goto out_destroy_caches; error = xfs_mru_cache_init(); if (error) goto out_destroy_wq; error = xfs_init_procfs(); if (error) goto out_mru_cache_uninit; error = xfs_sysctl_register(); if (error) goto out_cleanup_procfs; xfs_debugfs = xfs_debugfs_mkdir("xfs", NULL); xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj); if (!xfs_kset) { error = -ENOMEM; goto out_debugfs_unregister; } xfsstats.xs_kobj.kobject.kset = xfs_kset; xfsstats.xs_stats = alloc_percpu(struct xfsstats); if (!xfsstats.xs_stats) { error = -ENOMEM; goto out_kset_unregister; } error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL, "stats"); if (error) goto out_free_stats; error = xchk_global_stats_setup(xfs_debugfs); if (error) goto out_remove_stats_kobj; #ifdef DEBUG xfs_dbg_kobj.kobject.kset = xfs_kset; error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug"); if (error) goto out_remove_scrub_stats; #endif error = xfs_qm_init(); if (error) goto out_remove_dbg_kobj; error = register_filesystem(&xfs_fs_type); if (error) goto out_qm_exit; return 0; out_qm_exit: xfs_qm_exit(); out_remove_dbg_kobj: #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); out_remove_scrub_stats: #endif xchk_global_stats_teardown(); out_remove_stats_kobj: xfs_sysfs_del(&xfsstats.xs_kobj); out_free_stats: free_percpu(xfsstats.xs_stats); out_kset_unregister: kset_unregister(xfs_kset); out_debugfs_unregister: debugfs_remove(xfs_debugfs); xfs_sysctl_unregister(); out_cleanup_procfs: xfs_cleanup_procfs(); out_mru_cache_uninit: xfs_mru_cache_uninit(); out_destroy_wq: xfs_destroy_workqueues(); out_destroy_caches: xfs_destroy_caches(); out: return error; } STATIC void __exit exit_xfs_fs(void) { xfs_qm_exit(); unregister_filesystem(&xfs_fs_type); #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); #endif xchk_global_stats_teardown(); xfs_sysfs_del(&xfsstats.xs_kobj); free_percpu(xfsstats.xs_stats); kset_unregister(xfs_kset); debugfs_remove(xfs_debugfs); xfs_sysctl_unregister(); xfs_cleanup_procfs(); xfs_mru_cache_uninit(); xfs_destroy_workqueues(); xfs_destroy_caches(); xfs_uuid_table_free(); } module_init(init_xfs_fs); module_exit(exit_xfs_fs); MODULE_AUTHOR("Silicon Graphics, Inc."); MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled"); MODULE_LICENSE("GPL"); |
| 149 149 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * A wrapper for multiple PHYs which passes all phy_* function calls to * multiple (actual) PHY devices. This is comes handy when initializing * all PHYs on a HCD and to keep them all in the same state. * * Copyright (C) 2018 Martin Blumenstingl <martin.blumenstingl@googlemail.com> */ #include <linux/device.h> #include <linux/list.h> #include <linux/phy/phy.h> #include <linux/of.h> #include "phy.h" struct usb_phy_roothub { struct phy *phy; struct list_head list; }; /* Allocate the roothub_entry by specific name of phy */ static int usb_phy_roothub_add_phy_by_name(struct device *dev, const char *name, struct list_head *list) { struct usb_phy_roothub *roothub_entry; struct phy *phy; phy = devm_of_phy_get(dev, dev->of_node, name); if (IS_ERR(phy)) return PTR_ERR(phy); roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL); if (!roothub_entry) return -ENOMEM; INIT_LIST_HEAD(&roothub_entry->list); roothub_entry->phy = phy; list_add_tail(&roothub_entry->list, list); return 0; } static int usb_phy_roothub_add_phy(struct device *dev, int index, struct list_head *list) { struct usb_phy_roothub *roothub_entry; struct phy *phy; phy = devm_of_phy_get_by_index(dev, dev->of_node, index); if (IS_ERR(phy)) { if (PTR_ERR(phy) == -ENODEV) return 0; else return PTR_ERR(phy); } roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL); if (!roothub_entry) return -ENOMEM; INIT_LIST_HEAD(&roothub_entry->list); roothub_entry->phy = phy; list_add_tail(&roothub_entry->list, list); return 0; } struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev) { struct usb_phy_roothub *phy_roothub; int i, num_phys, err; if (!IS_ENABLED(CONFIG_GENERIC_PHY)) return NULL; num_phys = of_count_phandle_with_args(dev->of_node, "phys", "#phy-cells"); if (num_phys <= 0) return NULL; phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL); if (!phy_roothub) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&phy_roothub->list); if (!usb_phy_roothub_add_phy_by_name(dev, "usb2-phy", &phy_roothub->list)) return phy_roothub; for (i = 0; i < num_phys; i++) { err = usb_phy_roothub_add_phy(dev, i, &phy_roothub->list); if (err) return ERR_PTR(err); } return phy_roothub; } EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc); /** * usb_phy_roothub_alloc_usb3_phy - alloc the roothub * @dev: the device of the host controller * * Allocate the usb phy roothub if the host use a generic usb3-phy. * * Return: On success, a pointer to the usb_phy_roothub. Otherwise, * %NULL if no use usb3 phy or %-ENOMEM if out of memory. */ struct usb_phy_roothub *usb_phy_roothub_alloc_usb3_phy(struct device *dev) { struct usb_phy_roothub *phy_roothub; int num_phys; if (!IS_ENABLED(CONFIG_GENERIC_PHY)) return NULL; num_phys = of_count_phandle_with_args(dev->of_node, "phys", "#phy-cells"); if (num_phys <= 0) return NULL; phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL); if (!phy_roothub) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&phy_roothub->list); if (!usb_phy_roothub_add_phy_by_name(dev, "usb3-phy", &phy_roothub->list)) return phy_roothub; return NULL; } EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc_usb3_phy); int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_init(roothub_entry->phy); if (err) goto err_exit_phys; } return 0; err_exit_phys: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_exit(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_init); int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err, ret = 0; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_exit(roothub_entry->phy); if (err) ret = err; } return ret; } EXPORT_SYMBOL_GPL(usb_phy_roothub_exit); int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub, enum phy_mode mode) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_set_mode(roothub_entry->phy, mode); if (err) goto err_out; } return 0; err_out: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_power_off(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode); int usb_phy_roothub_calibrate(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_calibrate(roothub_entry->phy); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_calibrate); /** * usb_phy_roothub_notify_connect() - connect notification * @phy_roothub: the phy of roothub, if the host use a generic phy. * @port: the port index for connect * * If the phy needs to get connection status, the callback can be used. * Returns: %0 if successful, a negative error code otherwise */ int usb_phy_roothub_notify_connect(struct usb_phy_roothub *phy_roothub, int port) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_notify_connect(roothub_entry->phy, port); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_notify_connect); /** * usb_phy_roothub_notify_disconnect() - disconnect notification * @phy_roothub: the phy of roothub, if the host use a generic phy. * @port: the port index for disconnect * * If the phy needs to get connection status, the callback can be used. * Returns: %0 if successful, a negative error code otherwise */ int usb_phy_roothub_notify_disconnect(struct usb_phy_roothub *phy_roothub, int port) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_notify_disconnect(roothub_entry->phy, port); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_notify_disconnect); int usb_phy_roothub_power_on(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_power_on(roothub_entry->phy); if (err) goto err_out; } return 0; err_out: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_power_off(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_power_on); void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; if (!phy_roothub) return; list_for_each_entry_reverse(roothub_entry, &phy_roothub->list, list) phy_power_off(roothub_entry->phy); } EXPORT_SYMBOL_GPL(usb_phy_roothub_power_off); int usb_phy_roothub_suspend(struct device *controller_dev, struct usb_phy_roothub *phy_roothub) { usb_phy_roothub_power_off(phy_roothub); /* keep the PHYs initialized so the device can wake up the system */ if (device_may_wakeup(controller_dev)) return 0; return usb_phy_roothub_exit(phy_roothub); } EXPORT_SYMBOL_GPL(usb_phy_roothub_suspend); int usb_phy_roothub_resume(struct device *controller_dev, struct usb_phy_roothub *phy_roothub) { int err; /* if the device can't wake up the system _exit was called */ if (!device_may_wakeup(controller_dev)) { err = usb_phy_roothub_init(phy_roothub); if (err) return err; } err = usb_phy_roothub_power_on(phy_roothub); /* undo _init if _power_on failed */ if (err && !device_may_wakeup(controller_dev)) usb_phy_roothub_exit(phy_roothub); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_resume); |
| 7 8 8 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * dma-fence-array: aggregate fences to be waited together * * Copyright (C) 2016 Collabora Ltd * Copyright (C) 2016 Advanced Micro Devices, Inc. * Authors: * Gustavo Padovan <gustavo@padovan.org> * Christian König <christian.koenig@amd.com> */ #include <linux/export.h> #include <linux/slab.h> #include <linux/dma-fence-array.h> #define PENDING_ERROR 1 static const char *dma_fence_array_get_driver_name(struct dma_fence *fence) { return "dma_fence_array"; } static const char *dma_fence_array_get_timeline_name(struct dma_fence *fence) { return "unbound"; } static void dma_fence_array_set_pending_error(struct dma_fence_array *array, int error) { /* * Propagate the first error reported by any of our fences, but only * before we ourselves are signaled. */ if (error) cmpxchg(&array->base.error, PENDING_ERROR, error); } static void dma_fence_array_clear_pending_error(struct dma_fence_array *array) { /* Clear the error flag if not actually set. */ cmpxchg(&array->base.error, PENDING_ERROR, 0); } static void irq_dma_fence_array_work(struct irq_work *wrk) { struct dma_fence_array *array = container_of(wrk, typeof(*array), work); dma_fence_array_clear_pending_error(array); dma_fence_signal(&array->base); dma_fence_put(&array->base); } static void dma_fence_array_cb_func(struct dma_fence *f, struct dma_fence_cb *cb) { struct dma_fence_array_cb *array_cb = container_of(cb, struct dma_fence_array_cb, cb); struct dma_fence_array *array = array_cb->array; dma_fence_array_set_pending_error(array, f->error); if (atomic_dec_and_test(&array->num_pending)) irq_work_queue(&array->work); else dma_fence_put(&array->base); } static bool dma_fence_array_enable_signaling(struct dma_fence *fence) { struct dma_fence_array *array = to_dma_fence_array(fence); struct dma_fence_array_cb *cb = array->callbacks; unsigned i; for (i = 0; i < array->num_fences; ++i) { cb[i].array = array; /* * As we may report that the fence is signaled before all * callbacks are complete, we need to take an additional * reference count on the array so that we do not free it too * early. The core fence handling will only hold the reference * until we signal the array as complete (but that is now * insufficient). */ dma_fence_get(&array->base); if (dma_fence_add_callback(array->fences[i], &cb[i].cb, dma_fence_array_cb_func)) { int error = array->fences[i]->error; dma_fence_array_set_pending_error(array, error); dma_fence_put(&array->base); if (atomic_dec_and_test(&array->num_pending)) { dma_fence_array_clear_pending_error(array); return false; } } } return true; } static bool dma_fence_array_signaled(struct dma_fence *fence) { struct dma_fence_array *array = to_dma_fence_array(fence); int num_pending; unsigned int i; /* * We need to read num_pending before checking the enable_signal bit * to avoid racing with the enable_signaling() implementation, which * might decrement the counter, and cause a partial check. * atomic_read_acquire() pairs with atomic_dec_and_test() in * dma_fence_array_enable_signaling() * * The !--num_pending check is here to account for the any_signaled case * if we race with enable_signaling(), that means the !num_pending check * in the is_signalling_enabled branch might be outdated (num_pending * might have been decremented), but that's fine. The user will get the * right value when testing again later. */ num_pending = atomic_read_acquire(&array->num_pending); if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &array->base.flags)) { if (num_pending <= 0) goto signal; return false; } for (i = 0; i < array->num_fences; ++i) { if (dma_fence_is_signaled(array->fences[i]) && !--num_pending) goto signal; } return false; signal: dma_fence_array_clear_pending_error(array); return true; } static void dma_fence_array_release(struct dma_fence *fence) { struct dma_fence_array *array = to_dma_fence_array(fence); unsigned i; for (i = 0; i < array->num_fences; ++i) dma_fence_put(array->fences[i]); kfree(array->fences); dma_fence_free(fence); } static void dma_fence_array_set_deadline(struct dma_fence *fence, ktime_t deadline) { struct dma_fence_array *array = to_dma_fence_array(fence); unsigned i; for (i = 0; i < array->num_fences; ++i) dma_fence_set_deadline(array->fences[i], deadline); } const struct dma_fence_ops dma_fence_array_ops = { .get_driver_name = dma_fence_array_get_driver_name, .get_timeline_name = dma_fence_array_get_timeline_name, .enable_signaling = dma_fence_array_enable_signaling, .signaled = dma_fence_array_signaled, .release = dma_fence_array_release, .set_deadline = dma_fence_array_set_deadline, }; EXPORT_SYMBOL(dma_fence_array_ops); /** * dma_fence_array_alloc - Allocate a custom fence array * @num_fences: [in] number of fences to add in the array * * Return dma fence array on success, NULL on failure */ struct dma_fence_array *dma_fence_array_alloc(int num_fences) { struct dma_fence_array *array; return kzalloc(struct_size(array, callbacks, num_fences), GFP_KERNEL); } EXPORT_SYMBOL(dma_fence_array_alloc); /** * dma_fence_array_init - Init a custom fence array * @array: [in] dma fence array to arm * @num_fences: [in] number of fences to add in the array * @fences: [in] array containing the fences * @context: [in] fence context to use * @seqno: [in] sequence number to use * @signal_on_any: [in] signal on any fence in the array * * Implementation of @dma_fence_array_create without allocation. Useful to init * a preallocated dma fence array in the path of reclaim or dma fence signaling. */ void dma_fence_array_init(struct dma_fence_array *array, int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, bool signal_on_any) { WARN_ON(!num_fences || !fences); array->num_fences = num_fences; spin_lock_init(&array->lock); dma_fence_init(&array->base, &dma_fence_array_ops, &array->lock, context, seqno); init_irq_work(&array->work, irq_dma_fence_array_work); atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences); array->fences = fences; array->base.error = PENDING_ERROR; /* * dma_fence_array objects should never contain any other fence * containers or otherwise we run into recursion and potential kernel * stack overflow on operations on the dma_fence_array. * * The correct way of handling this is to flatten out the array by the * caller instead. * * Enforce this here by checking that we don't create a dma_fence_array * with any container inside. */ while (num_fences--) WARN_ON(dma_fence_is_container(fences[num_fences])); } EXPORT_SYMBOL(dma_fence_array_init); /** * dma_fence_array_create - Create a custom fence array * @num_fences: [in] number of fences to add in the array * @fences: [in] array containing the fences * @context: [in] fence context to use * @seqno: [in] sequence number to use * @signal_on_any: [in] signal on any fence in the array * * Allocate a dma_fence_array object and initialize the base fence with * dma_fence_init(). * In case of error it returns NULL. * * The caller should allocate the fences array with num_fences size * and fill it with the fences it wants to add to the object. Ownership of this * array is taken and dma_fence_put() is used on each fence on release. * * If @signal_on_any is true the fence array signals if any fence in the array * signals, otherwise it signals when all fences in the array signal. */ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, bool signal_on_any) { struct dma_fence_array *array; array = dma_fence_array_alloc(num_fences); if (!array) return NULL; dma_fence_array_init(array, num_fences, fences, context, seqno, signal_on_any); return array; } EXPORT_SYMBOL(dma_fence_array_create); /** * dma_fence_match_context - Check if all fences are from the given context * @fence: [in] fence or fence array * @context: [in] fence context to check all fences against * * Checks the provided fence or, for a fence array, all fences in the array * against the given context. Returns false if any fence is from a different * context. */ bool dma_fence_match_context(struct dma_fence *fence, u64 context) { struct dma_fence_array *array = to_dma_fence_array(fence); unsigned i; if (!dma_fence_is_array(fence)) return fence->context == context; for (i = 0; i < array->num_fences; i++) { if (array->fences[i]->context != context) return false; } return true; } EXPORT_SYMBOL(dma_fence_match_context); struct dma_fence *dma_fence_array_first(struct dma_fence *head) { struct dma_fence_array *array; if (!head) return NULL; array = to_dma_fence_array(head); if (!array) return head; if (!array->num_fences) return NULL; return array->fences[0]; } EXPORT_SYMBOL(dma_fence_array_first); struct dma_fence *dma_fence_array_next(struct dma_fence *head, unsigned int index) { struct dma_fence_array *array = to_dma_fence_array(head); if (!array || index >= array->num_fences) return NULL; return array->fences[index]; } EXPORT_SYMBOL(dma_fence_array_next); |
| 75 2 75 110 75 61 110 3 2 110 110 110 109 110 110 110 2 7 2 2 58 58 7 7 7 104 96 58 97 104 102 104 104 104 104 104 104 76 76 50 77 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * ucs.c - Universal Character Set processing */ #include <linux/array_size.h> #include <linux/bsearch.h> #include <linux/consolemap.h> #include <linux/minmax.h> struct ucs_interval16 { u16 first; u16 last; }; struct ucs_interval32 { u32 first; u32 last; }; #include "ucs_width_table.h" static int interval16_cmp(const void *key, const void *element) { u16 cp = *(u16 *)key; const struct ucs_interval16 *entry = element; if (cp < entry->first) return -1; if (cp > entry->last) return 1; return 0; } static int interval32_cmp(const void *key, const void *element) { u32 cp = *(u32 *)key; const struct ucs_interval32 *entry = element; if (cp < entry->first) return -1; if (cp > entry->last) return 1; return 0; } static bool cp_in_range16(u16 cp, const struct ucs_interval16 *ranges, size_t size) { if (cp < ranges[0].first || cp > ranges[size - 1].last) return false; return __inline_bsearch(&cp, ranges, size, sizeof(*ranges), interval16_cmp) != NULL; } static bool cp_in_range32(u32 cp, const struct ucs_interval32 *ranges, size_t size) { if (cp < ranges[0].first || cp > ranges[size - 1].last) return false; return __inline_bsearch(&cp, ranges, size, sizeof(*ranges), interval32_cmp) != NULL; } #define UCS_IS_BMP(cp) ((cp) <= 0xffff) /** * ucs_is_zero_width() - Determine if a Unicode code point is zero-width. * @cp: Unicode code point (UCS-4) * * Return: true if the character is zero-width, false otherwise */ bool ucs_is_zero_width(u32 cp) { if (UCS_IS_BMP(cp)) return cp_in_range16(cp, ucs_zero_width_bmp_ranges, ARRAY_SIZE(ucs_zero_width_bmp_ranges)); else return cp_in_range32(cp, ucs_zero_width_non_bmp_ranges, ARRAY_SIZE(ucs_zero_width_non_bmp_ranges)); } /** * ucs_is_double_width() - Determine if a Unicode code point is double-width. * @cp: Unicode code point (UCS-4) * * Return: true if the character is double-width, false otherwise */ bool ucs_is_double_width(u32 cp) { if (UCS_IS_BMP(cp)) return cp_in_range16(cp, ucs_double_width_bmp_ranges, ARRAY_SIZE(ucs_double_width_bmp_ranges)); else return cp_in_range32(cp, ucs_double_width_non_bmp_ranges, ARRAY_SIZE(ucs_double_width_non_bmp_ranges)); } /* * Structure for base with combining mark pairs and resulting recompositions. * Using u16 to save space since all values are within BMP range. */ struct ucs_recomposition { u16 base; /* base character */ u16 mark; /* combining mark */ u16 recomposed; /* corresponding recomposed character */ }; #include "ucs_recompose_table.h" struct compare_key { u16 base; u16 mark; }; static int recomposition_cmp(const void *key, const void *element) { const struct compare_key *search_key = key; const struct ucs_recomposition *entry = element; /* Compare base character first */ if (search_key->base < entry->base) return -1; if (search_key->base > entry->base) return 1; /* Base characters match, now compare combining character */ if (search_key->mark < entry->mark) return -1; if (search_key->mark > entry->mark) return 1; /* Both match */ return 0; } /** * ucs_recompose() - Attempt to recompose two Unicode characters into a single character. * @base: Base Unicode code point (UCS-4) * @mark: Combining mark Unicode code point (UCS-4) * * Return: Recomposed Unicode code point, or 0 if no recomposition is possible */ u32 ucs_recompose(u32 base, u32 mark) { /* Check if characters are within the range of our table */ if (base < UCS_RECOMPOSE_MIN_BASE || base > UCS_RECOMPOSE_MAX_BASE || mark < UCS_RECOMPOSE_MIN_MARK || mark > UCS_RECOMPOSE_MAX_MARK) return 0; struct compare_key key = { base, mark }; struct ucs_recomposition *result = __inline_bsearch(&key, ucs_recomposition_table, ARRAY_SIZE(ucs_recomposition_table), sizeof(*ucs_recomposition_table), recomposition_cmp); return result ? result->recomposed : 0; } /* * The fallback table structures implement a 2-level lookup. */ struct ucs_page_desc { u8 page; /* Page index (high byte of code points) */ u8 count; /* Number of entries in this page */ u16 start; /* Start index in entries array */ }; struct ucs_page_entry { u8 offset; /* Offset within page (0-255) */ u8 fallback; /* Fallback character or range start marker */ }; #include "ucs_fallback_table.h" static int ucs_page_desc_cmp(const void *key, const void *element) { u8 page = *(u8 *)key; const struct ucs_page_desc *entry = element; if (page < entry->page) return -1; if (page > entry->page) return 1; return 0; } static int ucs_page_entry_cmp(const void *key, const void *element) { u8 offset = *(u8 *)key; const struct ucs_page_entry *entry = element; if (offset < entry->offset) return -1; if (entry->fallback == UCS_PAGE_ENTRY_RANGE_MARKER) { if (offset > entry[1].offset) return 1; } else { if (offset > entry->offset) return 1; } return 0; } /** * ucs_get_fallback() - Get a substitution for the provided Unicode character * @cp: Unicode code point (UCS-4) * * Get a simpler fallback character for the provided Unicode character. * This is used for terminal display when corresponding glyph is unavailable. * The substitution may not be as good as the actual glyph for the original * character but still way more helpful than a squared question mark. * * Return: Fallback Unicode code point, or 0 if none is available */ u32 ucs_get_fallback(u32 cp) { const struct ucs_page_desc *page; const struct ucs_page_entry *entry; u8 page_idx = cp >> 8, offset = cp; if (!UCS_IS_BMP(cp)) return 0; /* * Full-width to ASCII mapping (covering all printable ASCII 33-126) * 0xFF01 (！) to 0xFF5E (～) -> ASCII 33 (!) to 126 (~) * We process them programmatically to reduce the table size. */ if (cp >= 0xFF01 && cp <= 0xFF5E) return cp - 0xFF01 + 33; page = __inline_bsearch(&page_idx, ucs_fallback_pages, ARRAY_SIZE(ucs_fallback_pages), sizeof(*ucs_fallback_pages), ucs_page_desc_cmp); if (!page) return 0; entry = __inline_bsearch(&offset, ucs_fallback_entries + page->start, page->count, sizeof(*ucs_fallback_entries), ucs_page_entry_cmp); if (!entry) return 0; if (entry->fallback == UCS_PAGE_ENTRY_RANGE_MARKER) entry++; return entry->fallback; } |
| 17391 17293 22 556 2964 13 17391 17401 17293 17275 2971 2976 2977 556 259 556 556 557 556 557 556 557 557 548 263 263 262 556 557 556 557 556 556 557 1 557 556 557 557 557 557 557 557 1 1 555 557 556 21 21 21 21 20 21 21 21 21 21 21 1 12436 12436 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(rstat_base_lock); static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); /* * Determines whether a given css can participate in rstat. * css's that are cgroup::self use rstat for base stats. * Other css's associated with a subsystem use rstat only when * they define the ss->css_rstat_flush callback. */ static inline bool css_uses_rstat(struct cgroup_subsys_state *css) { return css_is_self(css) || css->ss->css_rstat_flush != NULL; } static struct css_rstat_cpu *css_rstat_cpu( struct cgroup_subsys_state *css, int cpu) { return per_cpu_ptr(css->rstat_cpu, cpu); } static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu( struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_base_cpu, cpu); } static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss) { if (ss) return &ss->rstat_ss_lock; return &rstat_base_lock; } static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) { if (ss) return per_cpu_ptr(ss->lhead, cpu); return per_cpu_ptr(&rstat_backlog_list, cpu); } /** * css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * * Atomically inserts the css in the ss's llist for the given cpu. This is * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist * will be processed at the flush time to create the update tree. * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a * memory barrier is needed before the call to css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling * css_rstat_updated(). */ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct css_rstat_cpu __percpu *rstatc_pcpu; struct llist_node *self; /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; lockdep_assert_preemption_disabled(); /* * For archs withnot nmi safe cmpxchg or percpu ops support, ignore * the requests from nmi context. */ if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) return; rstatc = css_rstat_cpu(css, cpu); /* * If already on list return. This check is racy and smp_mb() is needed * to pair it with the smp_mb() in css_process_update_tree() if the * guarantee that the updated stats are visible to concurrent flusher is * needed. */ if (llist_on_list(&rstatc->lnode)) return; /* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note * that llist_add() does not protect against such scenarios. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use * this_cpu_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist. */ self = &rstatc->lnode; rstatc_pcpu = css->rstat_cpu; if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self) return; lhead = ss_lhead_cpu(css->ss, cpu); llist_add(&rstatc->lnode, lhead); } static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ while (true) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); struct cgroup_subsys_state *parent = css->parent; struct css_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = css; break; } prstatc = css_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = css; css = parent; } } static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) { struct llist_head *lhead = ss_lhead_cpu(ss, cpu); struct llist_node *lnode; while ((lnode = llist_del_first_init(lhead))) { struct css_rstat_cpu *rstatc; /* * smp_mb() is needed here (more specifically in between * init_llist_node() and per-cpu stats flushing) if the * guarantee is required by a rstat user where etiher the * updater should add itself on the lockless list or the * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before * css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add * smp_mb() here. */ rstatc = container_of(lnode, struct css_rstat_cpu, lnode); __css_process_update_tree(rstatc->owner, cpu); } } /** * css_rstat_push_children - push children css's into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of css's to be flushed * * Iteratively traverse down the css_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list via the rstat_flush_next pointer built from the * tail backward like "pushing" css's into a stack. The root is pushed by * the caller. */ static struct cgroup_subsys_state *css_rstat_push_children( struct cgroup_subsys_state *head, struct cgroup_subsys_state *child, int cpu) { struct cgroup_subsys_state *cnext = child; /* Next head of child css level */ struct cgroup_subsys_state *ghead = NULL; /* Head of grandchild css level */ struct cgroup_subsys_state *parent, *grandchild; struct css_rstat_cpu *crstatc; child->rstat_flush_next = NULL; /* * The subsystem rstat lock must be held for the whole duration from * here as the rstat_flush_next list is being constructed to when * it is consumed later in css_rstat_flush(). */ lockdep_assert_held(ss_rstat_lock(head->ss)); /* * Notation: -> updated_next pointer * => rstat_flush_next pointer * * Assuming the following sample updated_children lists: * P: C1 -> C2 -> P * C1: G11 -> G12 -> C1 * C2: G21 -> G22 -> C2 * * After 1st iteration: * head => C2 => C1 => NULL * ghead => G21 => G11 => NULL * * After 2nd iteration: * head => G12 => G11 => G22 => G21 => C2 => C1 => NULL */ next_level: while (cnext) { child = cnext; cnext = child->rstat_flush_next; parent = child->parent; /* updated_next is parent cgroup terminated if !NULL */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = css_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { cnext = ghead; ghead = NULL; goto next_level; } return head; } /** * css_rstat_updated_list - build a list of updated css's to be flushed * @root: root of the css subtree to traverse * @cpu: target cpu * Return: A singly linked list of css's to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned css is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child css's if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent css. An exception * here is the css root whose updated_next can be self terminated. */ static struct cgroup_subsys_state *css_rstat_updated_list( struct cgroup_subsys_state *root, int cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu); struct cgroup_subsys_state *head = NULL, *parent, *child; css_process_update_tree(root->ss, cpu); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) return NULL; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = root->parent; if (parent) { struct css_rstat_cpu *prstatc; struct cgroup_subsys_state **nextp; prstatc = css_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct css_rstat_cpu *nrstatc; nrstatc = css_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = css_rstat_push_children(head, child, cpu); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for css_rstat_updated() and * css_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __css_rstat_lock(struct cgroup_subsys_state *css, int cpu_in_loop) __acquires(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; bool contended; lock = ss_rstat_lock(css->ss); contended = !spin_trylock_irq(lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __css_rstat_unlock(struct cgroup_subsys_state *css, int cpu_in_loop) __releases(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; lock = ss_rstat_lock(css->ss); trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(lock); } /** * css_rstat_flush - flush stats in @css's rstat subtree * @css: target cgroup subsystem state * * Collect all per-cpu stats in @css's subtree into the global counters * and propagate them upwards. After this function returns, all rstat * nodes in the subtree have up-to-date ->stat. * * This also gets all rstat nodes in the subtree including @css off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css) { int cpu; bool is_self = css_is_self(css); /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; might_sleep(); for_each_possible_cpu(cpu) { struct cgroup_subsys_state *pos; /* Reacquire for each CPU to avoid disabling IRQs too long */ __css_rstat_lock(css, cpu); pos = css_rstat_updated_list(css, cpu); for (; pos; pos = pos->rstat_flush_next) { if (is_self) { cgroup_base_stat_flush(pos->cgroup, cpu); bpf_rstat_flush(pos->cgroup, cgroup_parent(pos->cgroup), cpu); } else pos->ss->css_rstat_flush(pos, cpu); } __css_rstat_unlock(css, cpu); if (!cond_resched()) cpu_relax(); } } int css_rstat_init(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; int cpu; bool is_self = css_is_self(css); if (is_self) { /* the root cgrp has rstat_base_cpu preallocated */ if (!cgrp->rstat_base_cpu) { cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu); if (!cgrp->rstat_base_cpu) return -ENOMEM; } } else if (css->ss->css_rstat_flush == NULL) return 0; /* the root cgrp's self css has rstat_cpu preallocated */ if (!css->rstat_cpu) { css->rstat_cpu = alloc_percpu(struct css_rstat_cpu); if (!css->rstat_cpu) { if (is_self) free_percpu(cgrp->rstat_base_cpu); return -ENOMEM; } } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); rstatc->owner = rstatc->updated_children = css; init_llist_node(&rstatc->lnode); if (is_self) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); u64_stats_init(&rstatbc->bsync); } } return 0; } void css_rstat_exit(struct cgroup_subsys_state *css) { int cpu; if (!css_uses_rstat(css)) return; if (!css->rstat_cpu) return; css_rstat_flush(css); /* sanity check */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); if (WARN_ON_ONCE(rstatc->updated_children != css) || WARN_ON_ONCE(rstatc->updated_next)) return; } if (css_is_self(css)) { struct cgroup *cgrp = css->cgroup; free_percpu(cgrp->rstat_base_cpu); cgrp->rstat_base_cpu = NULL; } free_percpu(css->rstat_cpu); css->rstat_cpu = NULL; } /** * ss_rstat_init - subsystem-specific rstat initialization * @ss: target subsystem * * If @ss is NULL, the static locks associated with the base stats * are initialized. If @ss is non-NULL, the subsystem-specific locks * are initialized. */ int __init ss_rstat_init(struct cgroup_subsys *ss) { int cpu; if (ss) { ss->lhead = alloc_percpu(struct llist_head); if (!ss->lhead) return -ENOMEM; } spin_lock_init(ss_rstat_lock(ss)); for_each_possible_cpu(cpu) init_llist_head(ss_lhead_cpu(ss, cpu)); return 0; } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_base_cpu *prstatbc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatbc->bsync); delta = rstatbc->bstat; } while (__u64_stats_fetch_retry(&rstatbc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatbc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatbc->last_bstat, &delta); cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatbc->subtree_bstat; prstatbc = cgroup_rstat_base_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat); cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_base_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu); *flags = u64_stats_update_begin_irqsave(&rstatbc->bsync); return rstatbc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_base_cpu *rstatbc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatbc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatbc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatbc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatbc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatbc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_base_stat bstat; if (cgroup_parent(cgrp)) { css_rstat_flush(&cgrp->self); __css_rstat_lock(&cgrp->self, -1); bstat = cgrp->bstat; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &bstat.cputime.utime, &bstat.cputime.stime); __css_rstat_unlock(&cgrp->self, -1); } else { root_cgroup_cputime(&bstat); } do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC); do_div(bstat.cputime.utime, NSEC_PER_USEC); do_div(bstat.cputime.stime, NSEC_PER_USEC); do_div(bstat.ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", bstat.cputime.sum_exec_runtime, bstat.cputime.utime, bstat.cputime.stime, bstat.ntime); cgroup_force_idle_show(seq, &bstat); } /* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, css_rstat_updated) BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 8 34 34 34 34 34 18 1 2 1 2 1 2 1 2 1 1 1 1 1 1 1 1 1 1 18 4 3 3 1 1 4 34 1 1 1 1 152 152 152 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/objtool.h> #include <linux/percpu.h> #include <asm/debugreg.h> #include <asm/mmu_context.h> #include <asm/msr.h> #include "x86.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" #include "pmu.h" #include "posted_intr.h" #include "sgx.h" #include "trace.h" #include "vmx.h" #include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); static bool __read_mostly nested_early_check = 0; module_param(nested_early_check, bool, S_IRUGO); #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK /* * Hyper-V requires all of these, so mark them as supported even though * they are just treated the same as all-context. */ #define VMX_VPID_EXTENT_SUPPORTED_MASK \ (VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT | \ VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | \ VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT | \ VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT) #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5 enum { VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR }; static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) struct shadow_vmcs_field { u16 encoding; u16 offset; }; static struct shadow_vmcs_field shadow_read_only_fields[] = { #define SHADOW_FIELD_RO(x, y) { x, offsetof(struct vmcs12, y) }, #include "vmcs_shadow_fields.h" }; static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); static struct shadow_vmcs_field shadow_read_write_fields[] = { #define SHADOW_FIELD_RW(x, y) { x, offsetof(struct vmcs12, y) }, #include "vmcs_shadow_fields.h" }; static int max_shadow_read_write_fields = ARRAY_SIZE(shadow_read_write_fields); static void init_vmcs_shadow_fields(void) { int i, j; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); for (i = j = 0; i < max_shadow_read_only_fields; i++) { struct shadow_vmcs_field entry = shadow_read_only_fields[i]; u16 field = entry.encoding; if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && (i + 1 == max_shadow_read_only_fields || shadow_read_only_fields[i + 1].encoding != field + 1)) pr_err("Missing field from shadow_read_only_field %x\n", field + 1); clear_bit(field, vmx_vmread_bitmap); if (field & 1) #ifdef CONFIG_X86_64 continue; #else entry.offset += sizeof(u32); #endif shadow_read_only_fields[j++] = entry; } max_shadow_read_only_fields = j; for (i = j = 0; i < max_shadow_read_write_fields; i++) { struct shadow_vmcs_field entry = shadow_read_write_fields[i]; u16 field = entry.encoding; if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && (i + 1 == max_shadow_read_write_fields || shadow_read_write_fields[i + 1].encoding != field + 1)) pr_err("Missing field from shadow_read_write_field %x\n", field + 1); WARN_ONCE(field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES, "Update vmcs12_write_any() to drop reserved bits from AR_BYTES"); /* * PML and the preemption timer can be emulated, but the * processor cannot vmwrite to fields that don't exist * on bare metal. */ switch (field) { case GUEST_PML_INDEX: if (!cpu_has_vmx_pml()) continue; break; case VMX_PREEMPTION_TIMER_VALUE: if (!cpu_has_vmx_preemption_timer()) continue; break; case GUEST_INTR_STATUS: if (!cpu_has_vmx_apicv()) continue; break; default: break; } clear_bit(field, vmx_vmwrite_bitmap); clear_bit(field, vmx_vmread_bitmap); if (field & 1) #ifdef CONFIG_X86_64 continue; #else entry.offset += sizeof(u32); #endif shadow_read_write_fields[j++] = entry; } max_shadow_read_write_fields = j; } /* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction (as specified * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated * instruction. */ static int nested_vmx_succeed(struct kvm_vcpu *vcpu) { vmx_set_rflags(vcpu, vmx_get_rflags(vcpu) & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF)); return kvm_skip_emulated_instruction(vcpu); } static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu) { vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF)) | X86_EFLAGS_CF); return kvm_skip_emulated_instruction(vcpu); } static int nested_vmx_failValid(struct kvm_vcpu *vcpu, u32 vm_instruction_error) { vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_SF | X86_EFLAGS_OF)) | X86_EFLAGS_ZF); get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; /* * We don't need to force sync to shadow VMCS because * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all * fields and thus must be synced. */ if (nested_vmx_is_evmptr12_set(to_vmx(vcpu))) to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; return kvm_skip_emulated_instruction(vcpu); } static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * failValid writes the error number to the current VMCS, which * can't be done if there isn't a current VMCS. */ if (vmx->nested.current_vmptr == INVALID_GPA && !nested_vmx_is_evmptr12_valid(vmx)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); } static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator); } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) { return fixed_bits_valid(control, low, high); } static inline u64 vmx_control_msr(u32 low, u32 high) { return low | ((u64)high << 32); } static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); vmx->nested.need_vmcs12_to_shadow_sync = false; } static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_HYPERV struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map); vmx->nested.hv_evmcs = NULL; vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; if (hv_vcpu) { hv_vcpu->nested.pa_page_gpa = INVALID_GPA; hv_vcpu->nested.vm_id = 0; hv_vcpu->nested.vp_id = 0; } #endif } static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) { #ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); /* * When Enlightened VMEntry is enabled on the calling CPU we treat * memory area pointer by vmptr as Enlightened VMCS (as there's no good * way to distinguish it from VMCS12) and we must not corrupt it by * writing to the non-existent 'launch_state' field. The area doesn't * have to be the currently active EVMCS on the calling CPU and there's * nothing KVM has to do to transition it from 'active' to 'non-active' * state. It is possible that the area will stay mapped as * vmx->nested.hv_evmcs but this shouldn't be a problem. */ if (!guest_cpu_cap_has_evmcs(vcpu) || !evmptr_is_valid(nested_get_evmptr(vcpu))) return false; if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr) nested_release_evmcs(vcpu); return true; #else return false; #endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, struct loaded_vmcs *prev) { struct vmcs_host_state *dest, *src; if (unlikely(!vmx->vt.guest_state_loaded)) return; src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; dest->es_sel = src->es_sel; #endif } static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct loaded_vmcs *prev; int cpu; if (WARN_ON_ONCE(vmx->loaded_vmcs == vmcs)) return; cpu = get_cpu(); prev = vmx->loaded_vmcs; vmx->loaded_vmcs = vmcs; vmx_vcpu_load_vmcs(vcpu, cpu); vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; /* * All lazily updated registers will be reloaded from VMCS12 on both * vmentry and vmexit. */ vcpu->arch.regs_dirty = 0; } static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map); kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map); kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map); vmx->nested.pi_desc = NULL; } /* * Free whatever needs to be freed from vmx->nested when L1 goes down, or * just stops using VMX. */ static void free_nested(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01)) vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; vmx->nested.vmxon_ptr = INVALID_GPA; free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = INVALID_GPA; if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); vmx->nested.cached_shadow_vmcs12 = NULL; nested_put_vmcs12_pages(vcpu); kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); nested_release_evmcs(vcpu); free_loaded_vmcs(&vmx->nested.vmcs02); } /* * Ensure that the current vmcs of the logical processor is the * vmcs01 of the vcpu before calling free_nested(). */ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); vmx_leave_nested(vcpu); vcpu_put(vcpu); } #define EPTP_PA_MASK GENMASK_ULL(51, 12) static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) { return VALID_PAGE(root_hpa) && ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); } static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, gpa_t addr) { unsigned long roots = 0; uint i; struct kvm_mmu_root_info *cached_root; WARN_ON_ONCE(!mmu_is_nested(vcpu)); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { cached_root = &vcpu->arch.mmu->prev_roots[i]; if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, eptp)) roots |= KVM_MMU_ROOT_PREVIOUS(i); } if (roots) kvm_mmu_invalidate_addr(vcpu, vcpu->arch.mmu, addr, roots); } static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; u32 vm_exit_reason; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; /* * It should be impossible to trigger a nested PML Full VM-Exit * for anything other than an EPT Violation from L2. KVM *can* * trigger nEPT page fault injection in response to an EPT * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT * tables also changed, but KVM should not treat EPT Misconfig * VM-Exits as writes. */ WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION); /* * PML Full and EPT Violation VM-Exits both use bit 12 to report * "NMI unblocking due to IRET", i.e. the bit can be propagated * as-is from the original EXIT_QUALIFICATION. */ exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; } else { if (fault->error_code & PFERR_RSVD_MASK) { vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; exit_qualification = 0; } else { exit_qualification = fault->exit_qualification; exit_qualification |= vmx_get_exit_qual(vcpu) & (EPT_VIOLATION_GVA_IS_VALID | EPT_VIOLATION_GVA_TRANSLATED); vm_exit_reason = EXIT_REASON_EPT_VIOLATION; } /* * Although the caller (kvm_inject_emulated_page_fault) would * have already synced the faulting address in the shadow EPT * tables for the current EPTP12, we also need to sync it for * any other cached EPTP02s based on the same EP4TA, since the * TLB associates mappings to the EP4TA rather than the full EPTP. */ nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, fault->address); } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; } static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; nested_ept_new_eptp(vcpu); vcpu->arch.mmu->get_guest_pgd = nested_ept_get_eptp; vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.mmu->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) { vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; } static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code) { bool inequality, bit; bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0; inequality = (error_code & vmcs12->page_fault_error_code_mask) != vmcs12->page_fault_error_code_match; return inequality ^ bit; } static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, u32 error_code) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); /* * Drop bits 31:16 of the error code when performing the #PF mask+match * check. All VMCS fields involved are 32 bits, but Intel CPUs never * set bits 31:16 and VMX disallows setting bits 31:16 in the injected * error code. Including the to-be-dropped bits in the check might * result in an "impossible" or missed exit from L1's perspective. */ if (vector == PF_VECTOR) return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code); return (vmcs12->exception_bitmap & (1u << vector)); } static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return 0; if (CC(!page_address_valid(vcpu, vmcs12->io_bitmap_a)) || CC(!page_address_valid(vcpu, vmcs12->io_bitmap_b))) return -EINVAL; return 0; } static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 0; if (CC(!page_address_valid(vcpu, vmcs12->msr_bitmap))) return -EINVAL; return 0; } static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return 0; if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))) return -EINVAL; return 0; } /* * For x2APIC MSRs, ignore the vmcs01 bitmap. L1 can enable x2APIC without L1 * itself utilizing x2APIC. All MSRs were previously set to be intercepted, * only the "disable intercept" case needs to be handled. */ static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1, unsigned long *msr_bitmap_l0, u32 msr, int type) { if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr)) vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr); if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr)) vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr); } static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { unsigned word = msr / BITS_PER_LONG; msr_bitmap[word] = ~0; msr_bitmap[word + (0x800 / sizeof(long))] = ~0; } } #define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ static inline \ void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ unsigned long *msr_bitmap_l1, \ unsigned long *msr_bitmap_l0, u32 msr) \ { \ if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ else \ vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ } BUILD_NVMX_MSR_INTERCEPT_HELPER(read) BUILD_NVMX_MSR_INTERCEPT_HELPER(write) static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, unsigned long *msr_bitmap_l1, unsigned long *msr_bitmap_l0, u32 msr, int types) { if (types & MSR_TYPE_R) nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, msr_bitmap_l0, msr); if (types & MSR_TYPE_W) nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, msr_bitmap_l0, msr); } /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. */ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; struct kvm_host_map map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; /* * MSR bitmap update can be skipped when: * - MSR bitmap for L1 hasn't changed. * - Nested hypervisor (L1) is attempting to launch the same L2 as * before. * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature * and tells KVM (L0) there were no changes in MSR bitmap for L2. */ if (!vmx->nested.force_msr_bitmap_recalc) { struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap && evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) return true; } if (kvm_vcpu_map_readonly(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), &map)) return false; msr_bitmap_l1 = (unsigned long *)map.hva; /* * To keep the control flow simple, pay eight 8-byte writes (sixteen * 4-byte writes on 32-bit systems) up front to enable intercepts for * the x2APIC MSR range and selectively toggle those relevant to L2. */ enable_x2apic_msr_intercepts(msr_bitmap_l0); if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) { /* * L0 need not intercept reads for MSRs between 0x800 * and 0x8ff, it just lets the processor take the value * from the virtual-APIC page; take those 256 bits * directly from the L1 bitmap. */ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { unsigned word = msr / BITS_PER_LONG; msr_bitmap_l0[word] = msr_bitmap_l1[word]; } } nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); } } /* * Always check vmcs01's bitmap to honor userspace MSR filters and any * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. */ #ifdef CONFIG_X86_64 nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_FS_BASE, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_GS_BASE, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PRED_CMD, MSR_TYPE_W); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_FLUSH_CMD, MSR_TYPE_W); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_APERF, MSR_TYPE_R); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_MPERF, MSR_TYPE_R); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_U_CET, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_S_CET, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PL0_SSP, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PL1_SSP, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PL2_SSP, MSR_TYPE_RW); nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PL3_SSP, MSR_TYPE_RW); kvm_vcpu_unmap(vcpu, &map); vmx->nested.force_msr_bitmap_recalc = false; return true; } static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; if (ghc->gpa != vmcs12->vmcs_link_pointer && kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), VMCS12_SIZE); } static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; if (ghc->gpa != vmcs12->vmcs_link_pointer && kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), VMCS12_SIZE); } /* * In nested virtualization, check if L1 has set * VM_EXIT_ACK_INTR_ON_EXIT */ static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu) { return get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_ACK_INTR_ON_EXIT; } static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && CC(!page_address_valid(vcpu, vmcs12->apic_access_addr))) return -EINVAL; else return 0; } static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && !nested_cpu_has_apic_reg_virt(vmcs12) && !nested_cpu_has_vid(vmcs12) && !nested_cpu_has_posted_intr(vmcs12)) return 0; /* * If virtualize x2apic mode is enabled, * virtualize apic access must be disabled. */ if (CC(nested_cpu_has_virt_x2apic_mode(vmcs12) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))) return -EINVAL; /* * If virtual interrupt delivery is enabled, * we must exit on external interrupts. */ if (CC(nested_cpu_has_vid(vmcs12) && !nested_exit_on_intr(vcpu))) return -EINVAL; /* * bits 15:8 should be zero in posted_intr_nv, * the descriptor address has been already checked * in nested_get_vmcs12_pages. * * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && (CC(!nested_cpu_has_vid(vmcs12)) || CC(!nested_exit_intr_ack_set(vcpu)) || CC((vmcs12->posted_intr_nv & 0xff00)) || CC(!kvm_vcpu_is_legal_aligned_gpa(vcpu, vmcs12->posted_intr_desc_addr, 64)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ if (CC(!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))) return -EINVAL; return 0; } static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, vmx->nested.msrs.misc_high); return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; } static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, u32 count, u64 addr) { if (count == 0) return 0; /* * Exceeding the limit results in architecturally _undefined_ behavior, * i.e. KVM is allowed to do literally anything in response to a bad * limit. Immediately generate a consistency check so that code that * consumes the count doesn't need to worry about extreme edge cases. */ if (count > nested_vmx_max_atomic_switch_msrs(vcpu)) return -EINVAL; if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) || !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1))) return -EINVAL; return 0; } static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (CC(nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_load_count, vmcs12->vm_exit_msr_load_addr)) || CC(nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_store_count, vmcs12->vm_exit_msr_store_addr))) return -EINVAL; return 0; } static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (CC(nested_vmx_check_msr_switch(vcpu, vmcs12->vm_entry_msr_load_count, vmcs12->vm_entry_msr_load_addr))) return -EINVAL; return 0; } static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has_pml(vmcs12)) return 0; if (CC(!nested_cpu_has_ept(vmcs12)) || CC(!page_address_valid(vcpu, vmcs12->pml_address))) return -EINVAL; return 0; } static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) && !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) && !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (!nested_cpu_has_shadow_vmcs(vmcs12)) return 0; if (CC(!page_address_valid(vcpu, vmcs12->vmread_bitmap)) || CC(!page_address_valid(vcpu, vmcs12->vmwrite_bitmap))) return -EINVAL; return 0; } static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ if (CC(vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)) return -EINVAL; if (CC(e->index == MSR_IA32_UCODE_WRITE) || /* SDM Table 35-2 */ CC(e->index == MSR_IA32_UCODE_REV)) return -EINVAL; if (CC(e->reserved != 0)) return -EINVAL; return 0; } static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { if (CC(e->index == MSR_FS_BASE) || CC(e->index == MSR_GS_BASE) || CC(e->index == MSR_IA32_SMM_MONITOR_CTL) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; } static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { if (CC(e->index == MSR_IA32_SMBASE) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; } /* * Load guest's/host's msr at nested entry/exit. * return 0 for success, entry index for failure. * * One of the failure modes for MSR load/store is when a list exceeds the * virtual hardware's capacity. To maintain compatibility with hardware inasmuch * as possible, process all valid entries before failing rather than precheck * for a capacity violation. */ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { u32 i; struct vmx_msr_entry e; u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { if (WARN_ON_ONCE(i >= max_msr_list_size)) goto fail; if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), &e, sizeof(e))) { pr_debug_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); goto fail; } if (nested_vmx_load_msr_check(vcpu, &e)) { pr_debug_ratelimited( "%s check failed (%u, 0x%x, 0x%x)\n", __func__, i, e.index, e.reserved); goto fail; } if (kvm_emulate_msr_write(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); goto fail; } } return 0; fail: /* Note, max_msr_list_size is at most 4096, i.e. this can't wrap. */ return i + 1; } static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * If the L0 hypervisor stored a more accurate value for the TSC that * does not include the time taken for emulation of the L2->L1 * VM-exit in L0, use the more accurate value. */ if (msr_index == MSR_IA32_TSC) { int i = vmx_find_loadstore_msr_slot(&vmx->msr_autostore.guest, MSR_IA32_TSC); if (i >= 0) { u64 val = vmx->msr_autostore.guest.val[i].value; *data = kvm_read_l1_tsc(vcpu, val); return true; } } if (kvm_emulate_msr_read(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; } return true; } static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i, struct vmx_msr_entry *e) { if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(*e), e, 2 * sizeof(u32))) { pr_debug_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(*e)); return false; } if (nested_vmx_store_msr_check(vcpu, e)) { pr_debug_ratelimited( "%s check failed (%u, 0x%x, 0x%x)\n", __func__, i, e->index, e->reserved); return false; } return true; } static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { u64 data; u32 i; struct vmx_msr_entry e; u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { if (WARN_ON_ONCE(i >= max_msr_list_size)) return -EINVAL; if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) return -EINVAL; if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data)) return -EINVAL; if (kvm_vcpu_write_guest(vcpu, gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), &data, sizeof(data))) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, data); return -EINVAL; } } return 0; } static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 count = vmcs12->vm_exit_msr_store_count; u64 gpa = vmcs12->vm_exit_msr_store_addr; struct vmx_msr_entry e; u32 i; for (i = 0; i < count; i++) { if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) return false; if (e.index == msr_index) return true; } return false; } static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, u32 msr_index) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_msrs *autostore = &vmx->msr_autostore.guest; bool in_vmcs12_store_list; int msr_autostore_slot; bool in_autostore_list; int last; msr_autostore_slot = vmx_find_loadstore_msr_slot(autostore, msr_index); in_autostore_list = msr_autostore_slot >= 0; in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index); if (in_vmcs12_store_list && !in_autostore_list) { if (autostore->nr == MAX_NR_LOADSTORE_MSRS) { /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by * nested_vmx_get_vmexit_msr_value() by reading KVM's * internal MSR state instead of reading the value from * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", msr_index); return; } last = autostore->nr++; autostore->val[last].index = msr_index; } else if (!in_vmcs12_store_list && in_autostore_list) { last = --autostore->nr; autostore->val[msr_autostore_slot] = autostore->val[last]; } } /* * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are * emulating VM-Entry into a guest with EPT enabled. On failure, the expected * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to * @entry_failure_code. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } /* * If PAE paging and EPT are both on, CR3 is not used by the CPU and * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } vcpu->arch.cr3 = cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); if (!nested_ept) kvm_mmu_new_pgd(vcpu, cr3); return 0; } /* * Returns if KVM is able to config CPU to tag TLB entries * populated by L2 differently than TLB entries populated * by L1. * * If L0 uses EPT, L1 and L2 run with different EPTP because * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries * are tagged with different EPTP. * * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged * with different VPID (L1 entries are tagged with vmx->vpid * while L2 entries are tagged with vmx->nested.vpid02). */ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); return enable_ept || (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02); } static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, bool is_vmenter) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* Handle pending Hyper-V TLB flush requests */ kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); /* * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the * same VPID as the host, and so architecturally, linear and combined * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit. KVM * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2, * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01. This * is required if VPID is disabled in KVM, as a TLB flush (there are no * VPIDs) still occurs from L1's perspective, and KVM may need to * synchronize the MMU in response to the guest TLB flush. * * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. * EPT is a special snowflake, as guest-physical mappings aren't * flushed on VPID invalidations, including VM-Enter or VM-Exit with * VPID disabled. As a result, KVM _never_ needs to sync nEPT * entries on VM-Enter because L1 can't rely on VM-Enter to flush * those mappings. */ if (!nested_cpu_has_vpid(vmcs12)) { kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; } /* L2 should never have a VPID if VPID is disabled. */ WARN_ON(!enable_vpid); /* * VPID is enabled and in use by vmcs12. If vpid12 is changing, then * emulate a guest TLB flush as KVM does not track vpid12 history nor * is the VPID incorporated into the MMU context. I.e. KVM must assume * that the new vpid12 has never been used and thus represents a new * guest ASID that cannot have entries in the TLB. */ if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; } /* * If VPID is enabled, used by vmc12, and vpid12 is not changing but * does not have a unique TLB tag (ASID), i.e. EPT is disabled and * KVM was unable to allocate a VPID for L2, flush the current context * as the effective ASID is common to both L1 and L2. */ if (!nested_has_guest_tlb_tag(vcpu)) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) { superset &= mask; subset &= mask; return (superset | subset) == superset; } static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | VMX_BASIC_INOUT | VMX_BASIC_TRUE_CTLS | VMX_BASIC_NO_HW_ERROR_CODE_CC; const u64 reserved_bits = GENMASK_ULL(63, 57) | GENMASK_ULL(47, 45) | BIT_ULL(31); u64 vmx_basic = vmcs_config.nested.basic; BUILD_BUG_ON(feature_bits & reserved_bits); /* * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has * inverted polarity), the incoming value must not set feature bits or * reserved bits that aren't allowed/supported by KVM. Fields, i.e. * multi-bit values, are explicitly checked below. */ if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != vmx_basic_vmcs_revision_id(data)) return -EINVAL; if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data)) return -EINVAL; vmx->nested.msrs.basic = data; return 0; } static void vmx_get_control_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u32 **low, u32 **high) { switch (msr_index) { case MSR_IA32_VMX_TRUE_PINBASED_CTLS: *low = &msrs->pinbased_ctls_low; *high = &msrs->pinbased_ctls_high; break; case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: *low = &msrs->procbased_ctls_low; *high = &msrs->procbased_ctls_high; break; case MSR_IA32_VMX_TRUE_EXIT_CTLS: *low = &msrs->exit_ctls_low; *high = &msrs->exit_ctls_high; break; case MSR_IA32_VMX_TRUE_ENTRY_CTLS: *low = &msrs->entry_ctls_low; *high = &msrs->entry_ctls_high; break; case MSR_IA32_VMX_PROCBASED_CTLS2: *low = &msrs->secondary_ctls_low; *high = &msrs->secondary_ctls_high; break; default: BUG(); } } static int vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) { u32 *lowp, *highp; u64 supported; vmx_get_control_msr(&vmcs_config.nested, msr_index, &lowp, &highp); supported = vmx_control_msr(*lowp, *highp); /* Check must-be-1 bits are still 1. */ if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0))) return -EINVAL; /* Check must-be-0 bits are still 0. */ if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32))) return -EINVAL; vmx_get_control_msr(&vmx->nested.msrs, msr_index, &lowp, &highp); *lowp = data; *highp = data >> 32; return 0; } static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_SHUTDOWN | VMX_MISC_ACTIVITY_WAIT_SIPI | VMX_MISC_INTEL_PT | VMX_MISC_RDMSR_IN_SMM | VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_VMXOFF_BLOCK_SMI | VMX_MISC_ZERO_LEN_INS; const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, vmcs_config.nested.misc_high); BUILD_BUG_ON(feature_bits & reserved_bits); /* * The incoming value must not set feature bits or reserved bits that * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are * explicitly checked below. */ if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) && vmx_misc_preemption_timer_rate(data) != vmx_misc_preemption_timer_rate(vmx_misc)) return -EINVAL; if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc)) return -EINVAL; if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc)) return -EINVAL; if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc)) return -EINVAL; vmx->nested.msrs.misc_low = data; vmx->nested.msrs.misc_high = data >> 32; return 0; } static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data) { u64 vmx_ept_vpid_cap = vmx_control_msr(vmcs_config.nested.ept_caps, vmcs_config.nested.vpid_caps); /* Every bit is either reserved or a feature bit. */ if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL)) return -EINVAL; vmx->nested.msrs.ept_caps = data; vmx->nested.msrs.vpid_caps = data >> 32; return 0; } static u64 *vmx_get_fixed0_msr(struct nested_vmx_msrs *msrs, u32 msr_index) { switch (msr_index) { case MSR_IA32_VMX_CR0_FIXED0: return &msrs->cr0_fixed0; case MSR_IA32_VMX_CR4_FIXED0: return &msrs->cr4_fixed0; default: BUG(); } } static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) { const u64 *msr = vmx_get_fixed0_msr(&vmcs_config.nested, msr_index); /* * 1 bits (which indicates bits which "must-be-1" during VMX operation) * must be 1 in the restored value. */ if (!is_bitwise_subset(data, *msr, -1ULL)) return -EINVAL; *vmx_get_fixed0_msr(&vmx->nested.msrs, msr_index) = data; return 0; } /* * Called when userspace is restoring VMX MSRs. * * Returns 0 on success, non-0 otherwise. */ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Don't allow changes to the VMX capability MSRs while the vCPU * is in VMX operation. */ if (vmx->nested.vmxon) return -EBUSY; switch (msr_index) { case MSR_IA32_VMX_BASIC: return vmx_restore_vmx_basic(vmx, data); case MSR_IA32_VMX_PINBASED_CTLS: case MSR_IA32_VMX_PROCBASED_CTLS: case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_ENTRY_CTLS: /* * The "non-true" VMX capability MSRs are generated from the * "true" MSRs, so we do not support restoring them directly. * * If userspace wants to emulate VMX_BASIC[55]=0, userspace * should restore the "true" MSRs with the must-be-1 bits * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND * DEFAULT SETTINGS". */ return -EINVAL; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: case MSR_IA32_VMX_PROCBASED_CTLS2: return vmx_restore_control_msr(vmx, msr_index, data); case MSR_IA32_VMX_MISC: return vmx_restore_vmx_misc(vmx, data); case MSR_IA32_VMX_CR0_FIXED0: case MSR_IA32_VMX_CR4_FIXED0: return vmx_restore_fixed0_msr(vmx, msr_index, data); case MSR_IA32_VMX_CR0_FIXED1: case MSR_IA32_VMX_CR4_FIXED1: /* * These MSRs are generated based on the vCPU's CPUID, so we * do not support restoring them directly. */ return -EINVAL; case MSR_IA32_VMX_EPT_VPID_CAP: return vmx_restore_vmx_ept_vpid_cap(vmx, data); case MSR_IA32_VMX_VMCS_ENUM: vmx->nested.msrs.vmcs_enum = data; return 0; case MSR_IA32_VMX_VMFUNC: if (data & ~vmcs_config.nested.vmfunc_controls) return -EINVAL; vmx->nested.msrs.vmfunc_controls = data; return 0; default: /* * The rest of the VMX capability MSRs do not support restore. */ return -EINVAL; } } /* Returns 0 on success, non-0 otherwise. */ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata) { switch (msr_index) { case MSR_IA32_VMX_BASIC: *pdata = msrs->basic; break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: *pdata = vmx_control_msr( msrs->pinbased_ctls_low, msrs->pinbased_ctls_high); if (msr_index == MSR_IA32_VMX_PINBASED_CTLS) *pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; break; case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: case MSR_IA32_VMX_PROCBASED_CTLS: *pdata = vmx_control_msr( msrs->procbased_ctls_low, msrs->procbased_ctls_high); if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS) *pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; break; case MSR_IA32_VMX_TRUE_EXIT_CTLS: case MSR_IA32_VMX_EXIT_CTLS: *pdata = vmx_control_msr( msrs->exit_ctls_low, msrs->exit_ctls_high); if (msr_index == MSR_IA32_VMX_EXIT_CTLS) *pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; break; case MSR_IA32_VMX_TRUE_ENTRY_CTLS: case MSR_IA32_VMX_ENTRY_CTLS: *pdata = vmx_control_msr( msrs->entry_ctls_low, msrs->entry_ctls_high); if (msr_index == MSR_IA32_VMX_ENTRY_CTLS) *pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; break; case MSR_IA32_VMX_MISC: *pdata = vmx_control_msr( msrs->misc_low, msrs->misc_high); break; case MSR_IA32_VMX_CR0_FIXED0: *pdata = msrs->cr0_fixed0; break; case MSR_IA32_VMX_CR0_FIXED1: *pdata = msrs->cr0_fixed1; break; case MSR_IA32_VMX_CR4_FIXED0: *pdata = msrs->cr4_fixed0; break; case MSR_IA32_VMX_CR4_FIXED1: *pdata = msrs->cr4_fixed1; break; case MSR_IA32_VMX_VMCS_ENUM: *pdata = msrs->vmcs_enum; break; case MSR_IA32_VMX_PROCBASED_CTLS2: *pdata = vmx_control_msr( msrs->secondary_ctls_low, msrs->secondary_ctls_high); break; case MSR_IA32_VMX_EPT_VPID_CAP: *pdata = msrs->ept_caps | ((u64)msrs->vpid_caps << 32); break; case MSR_IA32_VMX_VMFUNC: *pdata = msrs->vmfunc_controls; break; default: return 1; } return 0; } /* * Copy the writable VMCS shadow fields back to the VMCS12, in case they have * been modified by the L1 guest. Note, "writable" in this context means * "writable by the guest", i.e. tagged SHADOW_FIELD_RW; the set of * fields tagged SHADOW_FIELD_RO may or may not align with the "read-only" * VM-exit information fields (which are actually writable if the vCPU is * configured to support "VMWRITE to any supported field in the VMCS"). */ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) { struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu); struct shadow_vmcs_field field; unsigned long val; int i; if (WARN_ON(!shadow_vmcs)) return; preempt_disable(); vmcs_load(shadow_vmcs); for (i = 0; i < max_shadow_read_write_fields; i++) { field = shadow_read_write_fields[i]; val = __vmcs_readl(field.encoding); vmcs12_write_any(vmcs12, field.encoding, field.offset, val); } vmcs_clear(shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); preempt_enable(); } static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) { const struct shadow_vmcs_field *fields[] = { shadow_read_write_fields, shadow_read_only_fields }; const int max_fields[] = { max_shadow_read_write_fields, max_shadow_read_only_fields }; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu); struct shadow_vmcs_field field; unsigned long val; int i, q; if (WARN_ON(!shadow_vmcs)) return; vmcs_load(shadow_vmcs); for (q = 0; q < ARRAY_SIZE(fields); q++) { for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; val = vmcs12_read_any(vmcs12, field.encoding, field.offset); __vmcs_writel(field.encoding, val); } } vmcs_clear(shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); } static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { #ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) { hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page; hv_vcpu->nested.vm_id = evmcs->hv_vm_id; hv_vcpu->nested.vp_id = evmcs->hv_vp_id; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; vmcs12->guest_interruptibility_info = evmcs->guest_interruptibility_info; /* * Not present in struct vmcs12: * vmcs12->guest_ssp = evmcs->guest_ssp; */ } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) { vmcs12->cpu_based_vm_exec_control = evmcs->cpu_based_vm_exec_control; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) { vmcs12->exception_bitmap = evmcs->exception_bitmap; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) { vmcs12->vm_entry_controls = evmcs->vm_entry_controls; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) { vmcs12->vm_entry_intr_info_field = evmcs->vm_entry_intr_info_field; vmcs12->vm_entry_exception_error_code = evmcs->vm_entry_exception_error_code; vmcs12->vm_entry_instruction_len = evmcs->vm_entry_instruction_len; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) { vmcs12->host_ia32_pat = evmcs->host_ia32_pat; vmcs12->host_ia32_efer = evmcs->host_ia32_efer; vmcs12->host_cr0 = evmcs->host_cr0; vmcs12->host_cr3 = evmcs->host_cr3; vmcs12->host_cr4 = evmcs->host_cr4; vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp; vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip; vmcs12->host_rip = evmcs->host_rip; vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs; vmcs12->host_es_selector = evmcs->host_es_selector; vmcs12->host_cs_selector = evmcs->host_cs_selector; vmcs12->host_ss_selector = evmcs->host_ss_selector; vmcs12->host_ds_selector = evmcs->host_ds_selector; vmcs12->host_fs_selector = evmcs->host_fs_selector; vmcs12->host_gs_selector = evmcs->host_gs_selector; vmcs12->host_tr_selector = evmcs->host_tr_selector; vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl; /* * Not present in struct vmcs12: * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet; * vmcs12->host_ssp = evmcs->host_ssp; * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr; */ } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) { vmcs12->pin_based_vm_exec_control = evmcs->pin_based_vm_exec_control; vmcs12->vm_exit_controls = evmcs->vm_exit_controls; vmcs12->secondary_vm_exec_control = evmcs->secondary_vm_exec_control; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) { vmcs12->io_bitmap_a = evmcs->io_bitmap_a; vmcs12->io_bitmap_b = evmcs->io_bitmap_b; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) { vmcs12->msr_bitmap = evmcs->msr_bitmap; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) { vmcs12->guest_es_base = evmcs->guest_es_base; vmcs12->guest_cs_base = evmcs->guest_cs_base; vmcs12->guest_ss_base = evmcs->guest_ss_base; vmcs12->guest_ds_base = evmcs->guest_ds_base; vmcs12->guest_fs_base = evmcs->guest_fs_base; vmcs12->guest_gs_base = evmcs->guest_gs_base; vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base; vmcs12->guest_tr_base = evmcs->guest_tr_base; vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base; vmcs12->guest_idtr_base = evmcs->guest_idtr_base; vmcs12->guest_es_limit = evmcs->guest_es_limit; vmcs12->guest_cs_limit = evmcs->guest_cs_limit; vmcs12->guest_ss_limit = evmcs->guest_ss_limit; vmcs12->guest_ds_limit = evmcs->guest_ds_limit; vmcs12->guest_fs_limit = evmcs->guest_fs_limit; vmcs12->guest_gs_limit = evmcs->guest_gs_limit; vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit; vmcs12->guest_tr_limit = evmcs->guest_tr_limit; vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit; vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit; vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes; vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes; vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes; vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes; vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes; vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes; vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes; vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes; vmcs12->guest_es_selector = evmcs->guest_es_selector; vmcs12->guest_cs_selector = evmcs->guest_cs_selector; vmcs12->guest_ss_selector = evmcs->guest_ss_selector; vmcs12->guest_ds_selector = evmcs->guest_ds_selector; vmcs12->guest_fs_selector = evmcs->guest_fs_selector; vmcs12->guest_gs_selector = evmcs->guest_gs_selector; vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector; vmcs12->guest_tr_selector = evmcs->guest_tr_selector; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) { vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap; vmcs12->tsc_multiplier = evmcs->tsc_multiplier; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) { vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask; vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask; vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow; vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow; vmcs12->guest_cr0 = evmcs->guest_cr0; vmcs12->guest_cr3 = evmcs->guest_cr3; vmcs12->guest_cr4 = evmcs->guest_cr4; vmcs12->guest_dr7 = evmcs->guest_dr7; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) { vmcs12->host_fs_base = evmcs->host_fs_base; vmcs12->host_gs_base = evmcs->host_gs_base; vmcs12->host_tr_base = evmcs->host_tr_base; vmcs12->host_gdtr_base = evmcs->host_gdtr_base; vmcs12->host_idtr_base = evmcs->host_idtr_base; vmcs12->host_rsp = evmcs->host_rsp; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) { vmcs12->ept_pointer = evmcs->ept_pointer; vmcs12->virtual_processor_id = evmcs->virtual_processor_id; } if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) { vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer; vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl; vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat; vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer; vmcs12->guest_pdptr0 = evmcs->guest_pdptr0; vmcs12->guest_pdptr1 = evmcs->guest_pdptr1; vmcs12->guest_pdptr2 = evmcs->guest_pdptr2; vmcs12->guest_pdptr3 = evmcs->guest_pdptr3; vmcs12->guest_pending_dbg_exceptions = evmcs->guest_pending_dbg_exceptions; vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp; vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip; vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs; vmcs12->guest_activity_state = evmcs->guest_activity_state; vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs; vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl; /* * Not present in struct vmcs12: * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet; * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl; * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr; */ } /* * Not used? * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr; * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr; * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr; * vmcs12->page_fault_error_code_mask = * evmcs->page_fault_error_code_mask; * vmcs12->page_fault_error_code_match = * evmcs->page_fault_error_code_match; * vmcs12->cr3_target_count = evmcs->cr3_target_count; * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count; * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count; * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count; */ /* * Read only fields: * vmcs12->guest_physical_address = evmcs->guest_physical_address; * vmcs12->vm_instruction_error = evmcs->vm_instruction_error; * vmcs12->vm_exit_reason = evmcs->vm_exit_reason; * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info; * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code; * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field; * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code; * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len; * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info; * vmcs12->exit_qualification = evmcs->exit_qualification; * vmcs12->guest_linear_address = evmcs->guest_linear_address; * * Not present in struct vmcs12: * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx; * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi; * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi; * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip; */ return; #else /* CONFIG_KVM_HYPERV */ KVM_BUG_ON(1, vmx->vcpu.kvm); #endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { #ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); /* * Should not be changed by KVM: * * evmcs->host_es_selector = vmcs12->host_es_selector; * evmcs->host_cs_selector = vmcs12->host_cs_selector; * evmcs->host_ss_selector = vmcs12->host_ss_selector; * evmcs->host_ds_selector = vmcs12->host_ds_selector; * evmcs->host_fs_selector = vmcs12->host_fs_selector; * evmcs->host_gs_selector = vmcs12->host_gs_selector; * evmcs->host_tr_selector = vmcs12->host_tr_selector; * evmcs->host_ia32_pat = vmcs12->host_ia32_pat; * evmcs->host_ia32_efer = vmcs12->host_ia32_efer; * evmcs->host_cr0 = vmcs12->host_cr0; * evmcs->host_cr3 = vmcs12->host_cr3; * evmcs->host_cr4 = vmcs12->host_cr4; * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp; * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip; * evmcs->host_rip = vmcs12->host_rip; * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs; * evmcs->host_fs_base = vmcs12->host_fs_base; * evmcs->host_gs_base = vmcs12->host_gs_base; * evmcs->host_tr_base = vmcs12->host_tr_base; * evmcs->host_gdtr_base = vmcs12->host_gdtr_base; * evmcs->host_idtr_base = vmcs12->host_idtr_base; * evmcs->host_rsp = vmcs12->host_rsp; * sync_vmcs02_to_vmcs12() doesn't read these: * evmcs->io_bitmap_a = vmcs12->io_bitmap_a; * evmcs->io_bitmap_b = vmcs12->io_bitmap_b; * evmcs->msr_bitmap = vmcs12->msr_bitmap; * evmcs->ept_pointer = vmcs12->ept_pointer; * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap; * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr; * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr; * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr; * evmcs->tpr_threshold = vmcs12->tpr_threshold; * evmcs->virtual_processor_id = vmcs12->virtual_processor_id; * evmcs->exception_bitmap = vmcs12->exception_bitmap; * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer; * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control; * evmcs->vm_exit_controls = vmcs12->vm_exit_controls; * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control; * evmcs->page_fault_error_code_mask = * vmcs12->page_fault_error_code_mask; * evmcs->page_fault_error_code_match = * vmcs12->page_fault_error_code_match; * evmcs->cr3_target_count = vmcs12->cr3_target_count; * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr; * evmcs->tsc_offset = vmcs12->tsc_offset; * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl; * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask; * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask; * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow; * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow; * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count; * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count; * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count; * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl; * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl; * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap; * evmcs->tsc_multiplier = vmcs12->tsc_multiplier; * * Not present in struct vmcs12: * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx; * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi; * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi; * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip; * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet; * evmcs->host_ssp = vmcs12->host_ssp; * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr; * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet; * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl; * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr; * evmcs->guest_ssp = vmcs12->guest_ssp; */ evmcs->guest_es_selector = vmcs12->guest_es_selector; evmcs->guest_cs_selector = vmcs12->guest_cs_selector; evmcs->guest_ss_selector = vmcs12->guest_ss_selector; evmcs->guest_ds_selector = vmcs12->guest_ds_selector; evmcs->guest_fs_selector = vmcs12->guest_fs_selector; evmcs->guest_gs_selector = vmcs12->guest_gs_selector; evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector; evmcs->guest_tr_selector = vmcs12->guest_tr_selector; evmcs->guest_es_limit = vmcs12->guest_es_limit; evmcs->guest_cs_limit = vmcs12->guest_cs_limit; evmcs->guest_ss_limit = vmcs12->guest_ss_limit; evmcs->guest_ds_limit = vmcs12->guest_ds_limit; evmcs->guest_fs_limit = vmcs12->guest_fs_limit; evmcs->guest_gs_limit = vmcs12->guest_gs_limit; evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit; evmcs->guest_tr_limit = vmcs12->guest_tr_limit; evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit; evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit; evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes; evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes; evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes; evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes; evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes; evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes; evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes; evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes; evmcs->guest_es_base = vmcs12->guest_es_base; evmcs->guest_cs_base = vmcs12->guest_cs_base; evmcs->guest_ss_base = vmcs12->guest_ss_base; evmcs->guest_ds_base = vmcs12->guest_ds_base; evmcs->guest_fs_base = vmcs12->guest_fs_base; evmcs->guest_gs_base = vmcs12->guest_gs_base; evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base; evmcs->guest_tr_base = vmcs12->guest_tr_base; evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base; evmcs->guest_idtr_base = vmcs12->guest_idtr_base; evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat; evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer; evmcs->guest_pdptr0 = vmcs12->guest_pdptr0; evmcs->guest_pdptr1 = vmcs12->guest_pdptr1; evmcs->guest_pdptr2 = vmcs12->guest_pdptr2; evmcs->guest_pdptr3 = vmcs12->guest_pdptr3; evmcs->guest_pending_dbg_exceptions = vmcs12->guest_pending_dbg_exceptions; evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp; evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip; evmcs->guest_activity_state = vmcs12->guest_activity_state; evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs; evmcs->guest_cr0 = vmcs12->guest_cr0; evmcs->guest_cr3 = vmcs12->guest_cr3; evmcs->guest_cr4 = vmcs12->guest_cr4; evmcs->guest_dr7 = vmcs12->guest_dr7; evmcs->guest_physical_address = vmcs12->guest_physical_address; evmcs->vm_instruction_error = vmcs12->vm_instruction_error; evmcs->vm_exit_reason = vmcs12->vm_exit_reason; evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info; evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code; evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field; evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code; evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len; evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info; evmcs->exit_qualification = vmcs12->exit_qualification; evmcs->guest_linear_address = vmcs12->guest_linear_address; evmcs->guest_rsp = vmcs12->guest_rsp; evmcs->guest_rflags = vmcs12->guest_rflags; evmcs->guest_interruptibility_info = vmcs12->guest_interruptibility_info; evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control; evmcs->vm_entry_controls = vmcs12->vm_entry_controls; evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field; evmcs->vm_entry_exception_error_code = vmcs12->vm_entry_exception_error_code; evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len; evmcs->guest_rip = vmcs12->guest_rip; evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; #else /* CONFIG_KVM_HYPERV */ KVM_BUG_ON(1, vmx->vcpu.kvm); #endif /* CONFIG_KVM_HYPERV */ } /* * This is an equivalent of the nested hypervisor executing the vmptrld * instruction. */ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { #ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; if (likely(!guest_cpu_cap_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; evmcs_gpa = nested_get_evmptr(vcpu); if (!evmptr_is_valid(evmcs_gpa)) { nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; } if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { vmx->nested.current_vmptr = INVALID_GPA; nested_release_evmcs(vcpu); if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa), &vmx->nested.hv_evmcs_map)) return EVMPTRLD_ERROR; vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva; /* * Currently, KVM only supports eVMCS version 1 * (== KVM_EVMCS_VERSION) and thus we expect guest to set this * value to first u32 field of eVMCS which should specify eVMCS * VersionNumber. * * Guest should be aware of supported eVMCS versions by host by * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is * expected to set this CPUID leaf according to the value * returned in vmcs_version from nested_enable_evmcs(). * * However, it turns out that Microsoft Hyper-V fails to comply * to their own invented interface: When Hyper-V use eVMCS, it * just sets first u32 field of eVMCS to revision_id specified * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number * which is one of the supported versions specified in * CPUID.0x4000000A.EAX[0:15]. * * To overcome Hyper-V bug, we accept here either a supported * eVMCS version or VMCS12 revision_id as valid values for first * u32 field of eVMCS. */ if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) && (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) { nested_release_evmcs(vcpu); return EVMPTRLD_VMFAIL; } vmx->nested.hv_evmcs_vmptr = evmcs_gpa; evmcs_gpa_changed = true; /* * Unlike normal vmcs12, enlightened vmcs12 is not fully * reloaded from guest's memory (read only fields, fields not * present in struct hv_enlightened_vmcs, ...). Make sure there * are no leftovers. */ if (from_launch) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); memset(vmcs12, 0, sizeof(*vmcs12)); vmcs12->hdr.revision_id = VMCS12_REVISION; } } /* * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; vmx->nested.force_msr_bitmap_recalc = true; } return EVMPTRLD_SUCCEEDED; #else return EVMPTRLD_DISABLED; #endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (nested_vmx_is_evmptr12_valid(vmx)) copy_vmcs12_to_enlightened(vmx); else copy_vmcs12_to_shadow(vmx); vmx->nested.need_vmcs12_to_shadow_sync = false; } static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) { struct vcpu_vmx *vmx = container_of(timer, struct vcpu_vmx, nested.preemption_timer); vmx->nested.preemption_timer_expired = true; kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu); kvm_vcpu_kick(&vmx->vcpu); return HRTIMER_NORESTART; } static u64 vmx_calc_preemption_timer_value(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u64 l1_scaled_tsc = kvm_read_l1_tsc(vcpu, rdtsc()) >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; if (!vmx->nested.has_preemption_timer_deadline) { vmx->nested.preemption_timer_deadline = vmcs12->vmx_preemption_timer_value + l1_scaled_tsc; vmx->nested.has_preemption_timer_deadline = true; } return vmx->nested.preemption_timer_deadline - l1_scaled_tsc; } static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu, u64 preemption_timeout) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * A timer value of zero is architecturally guaranteed to cause * a VMExit prior to executing any instructions in the guest. */ if (preemption_timeout == 0) { vmx_preemption_timer_fn(&vmx->nested.preemption_timer); return; } if (vcpu->arch.virtual_tsc_khz == 0) return; preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); hrtimer_start(&vmx->nested.preemption_timer, ktime_add_ns(ktime_get(), preemption_timeout), HRTIMER_MODE_ABS_PINNED); } static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) return vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME); else return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME); } static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) { struct kvm *kvm = vmx->vcpu.kvm; /* * If vmcs02 hasn't been initialized, set the constant vmcs02 state * according to L0's settings (vmcs12 is irrelevant here). Host * fields that come from L0 and are not constant, e.g. HOST_CR3, * will be set as needed prior to VMLAUNCH/VMRESUME. */ if (vmx->nested.vmcs02_initialized) return; vmx->nested.vmcs02_initialized = true; /* * We don't care what the EPTP value is we just need to guarantee * it's valid so we don't get a false positive when doing early * consistency checks. */ if (enable_ept && nested_early_check) vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL)); if (vmx->ve_info) vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); /* All VMFUNCs are currently emulated through L0 vmexits. */ if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); if (cpu_has_vmx_posted_intr()) vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); /* * PML is emulated for L2, but never enabled in hardware as the MMU * handles A/D emulation. Disabling PML for L2 also avoids having to * deal with filtering out L2 GPAs from the buffer. */ if (enable_pml) { vmcs_write64(PML_ADDRESS, 0); vmcs_write16(GUEST_PML_INDEX, -1); } if (cpu_has_vmx_encls_vmexit()) vmcs_write64(ENCLS_EXITING_BITMAP, INVALID_GPA); if (kvm_notify_vmexit_enabled(kvm)) vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); /* * Set the MSR load/store lists to match L0's settings. Only the * addresses are constant (for vmcs02), the counts can change based * on L2's behavior, e.g. switching to/from long mode. */ vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val)); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); vmx_set_constant_host_state(vmx); } static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { prepare_vmcs02_constant_state(vmx); vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); /* * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the * same VPID as the host. Emulate this behavior by using vpid01 for L2 * if VPID is disabled in vmcs12. Note, if VPID is disabled, VM-Enter * and VM-Exit are architecturally required to flush VPID=0, but *only* * VPID=0. I.e. using vpid02 would be ok (so long as KVM emulates the * required flushes), but doing so would cause KVM to over-flush. E.g. * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled, * and then runs L2 X again, then KVM can and should retain TLB entries * for VPID12=1. */ if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); else vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); } } static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01, struct vmcs12 *vmcs12) { u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) prepare_vmcs02_early_rare(vmx, vmcs12); /* * PIN CONTROLS */ exec_control = __pin_controls_get(vmcs01); exec_control |= (vmcs12->pin_based_vm_exec_control & ~PIN_BASED_VMX_PREEMPTION_TIMER); /* Posted interrupts setting is only taken from vmcs12. */ vmx->nested.pi_pending = false; if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; } else { vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; } pin_controls_set(vmx, exec_control); /* * EXEC CONTROLS */ exec_control = __exec_controls_get(vmcs01); /* L0's desires */ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; vmx->nested.l1_tpr_threshold = -1; if (exec_control & CPU_BASED_TPR_SHADOW) vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); #ifdef CONFIG_X86_64 else exec_control |= CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING; #endif /* * A vmexit (to either L1 hypervisor or L0 userspace) is always needed * for I/O port accesses. */ exec_control |= CPU_BASED_UNCOND_IO_EXITING; exec_control &= ~CPU_BASED_USE_IO_BITMAPS; /* * This bit will be computed in nested_get_vmcs12_pages, because * we do not have access to L1's MSR bitmap yet. For now, keep * the same bit as before, hoping to avoid multiple VMWRITEs that * only set/clear this bit. */ exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; exec_control |= exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS; exec_controls_set(vmx, exec_control); /* * SECONDARY EXEC CONTROLS */ if (cpu_has_secondary_exec_ctrls()) { exec_control = __secondary_exec_controls_get(vmcs01); /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | SECONDARY_EXEC_ENABLE_XSAVES | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_DESC); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; /* PML is emulated and never enabled in hardware for L2. */ exec_control &= ~SECONDARY_EXEC_ENABLE_PML; /* VMCS shadowing for L2 is emulated for now */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; /* * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4() * will not have to rewrite the controls just for this bit. */ if (vmx_umip_emulated() && (vmcs12->guest_cr4 & X86_CR4_UMIP)) exec_control |= SECONDARY_EXEC_DESC; if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) vmcs_write16(GUEST_INTR_STATUS, vmcs12->guest_intr_status); if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST)) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (exec_control & SECONDARY_EXEC_ENCLS_EXITING) vmx_write_encls_bitmap(&vmx->vcpu, vmcs12); secondary_exec_controls_set(vmx, exec_control); } /* * ENTRY CONTROLS * * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). * * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to * do the same for L2. */ exec_control = __vm_entry_controls_get(vmcs01); exec_control |= (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; if (guest_efer != kvm_host.efer) exec_control |= VM_ENTRY_LOAD_IA32_EFER; } vm_entry_controls_set(vmx, exec_control); /* * EXIT CONTROLS * * L2->L1 exit controls are emulated - the hardware exit is to L0 so * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ exec_control = __vm_exit_controls_get(vmcs01); if (cpu_has_load_ia32_efer() && guest_efer != kvm_host.efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; else exec_control &= ~VM_EXIT_LOAD_IA32_EFER; vm_exit_controls_set(vmx, exec_control); /* * Interrupt/Exception Fields */ if (vmx->nested.nested_run_pending) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, vmcs12->vm_entry_intr_info_field); vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, vmcs12->vm_entry_exception_error_code); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmcs12->vm_entry_instruction_len); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); vmx->loaded_vmcs->nmi_known_unmasked = !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI); } else { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } } static void vmcs_read_cet_state(struct kvm_vcpu *vcpu, u64 *s_cet, u64 *ssp, u64 *ssp_tbl) { if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) *s_cet = vmcs_readl(GUEST_S_CET); if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { *ssp = vmcs_readl(GUEST_SSP); *ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); } } static void vmcs_write_cet_state(struct kvm_vcpu *vcpu, u64 s_cet, u64 ssp, u64 ssp_tbl) { if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) vmcs_writel(GUEST_S_CET, s_cet); if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { vmcs_writel(GUEST_SSP, ssp); vmcs_writel(GUEST_INTR_SSP_TABLE, ssp_tbl); } } static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector); vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector); vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector); vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector); vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector); vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit); vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit); vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit); vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit); vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit); vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit); vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit); vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit); vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit); vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit); vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes); vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes); vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes); vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes); vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes); vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes); vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes); vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base); vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base); vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base); vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base); vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base); vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) { vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs12->guest_pending_dbg_exceptions); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip); /* * L1 may access the L2's PDPTR, so save them to construct * vmcs12 */ if (enable_ept) { vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); } if (kvm_mpx_supported() && vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); } if (nested_cpu_has_xsaves(vmcs12)) vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap); /* * Whether page-faults are trapped is determined by a combination of * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. If L0 * doesn't care about page faults then we should set all of these to * L1's desires. However, if L0 does care about (some) page faults, it * is not easy (if at all possible?) to merge L0 and L1's desires, we * simply ask to exit on each and every L2 page fault. This is done by * setting MASK=MATCH=0 and (see below) EB.PF=1. * Note that below we don't need special code to set EB.PF beyond the * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when * !enable_ept, EB.PF is 1, so the "or" will always be 1. */ if (vmx_need_pf_intercept(&vmx->vcpu)) { /* * TODO: if both L0 and L1 need the same MASK and MATCH, * go ahead and use it? */ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); } else { vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, vmcs12->page_fault_error_code_mask); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, vmcs12->page_fault_error_code_match); } if (cpu_has_vmx_apicv()) { vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1); vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2); vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); } /* * Make sure the msr_autostore list is up to date before we set the * count in the vmcs02. */ prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC); vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) vmcs_write_cet_state(&vmx->vcpu, vmcs12->guest_s_cet, vmcs12->guest_ssp, vmcs12->guest_ssp_tbl); set_cr4_guest_host_mask(vmx); } /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 * guest in a way that will both be appropriate to L1's requests, and our * needs. In addition to modifying the active vmcs (which is vmcs02), this * function also has additional necessary side-effects, like setting various * vcpu->arch fields. * Returns 0 on success, 1 on failure. Invalid state exit qualification code * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, bool from_vmentry, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); bool load_guest_pdptrs_vmcs12 = false; if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) || !(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) vmcs_write_cet_state(vcpu, vmx->nested.pre_vmenter_s_cet, vmx->nested.pre_vmenter_ssp, vmx->nested.pre_vmenter_ssp_tbl); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmcs_write64(GUEST_BNDCFGS, vmx->nested.pre_vmenter_bndcfgs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the * bitwise-or of what L1 wants to trap for L2, and what we want to * trap. Note that CR0.TS also needs updating - we do this later. */ vmx_update_exception_bitmap(vcpu); vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask; vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( vcpu->arch.l1_tsc_offset, vmx_get_l2_tsc_offset(vcpu), vmx_get_l2_tsc_multiplier(vcpu)); vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( vcpu->arch.l1_tsc_scaling_ratio, vmx_get_l2_tsc_multiplier(vcpu)); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); if (nested_cpu_has_ept(vmcs12)) nested_ept_init_mmu_context(vcpu); /* * Override the CR0/CR4 read shadows after setting the effective guest * CR0/CR4. The common helpers also set the shadows, but they don't * account for vmcs12's cr0/4_guest_host_mask. */ vmx_set_cr0(vcpu, vmcs12->guest_cr0); vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); vmx_set_cr4(vcpu, vmcs12->guest_cr4); vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12)); vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12); /* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */ vmx_set_efer(vcpu, vcpu->arch.efer); /* * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. * * However when force loading the guest state (SMM exit or * loading nested state after migration, it is possible to * have invalid guest state now, which will be later fixed by * restoring L2 register state */ if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), from_vmentry, entry_failure_code)) return -EINVAL; /* * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 * on nested VM-Exit, which can occur without actually running L2 and * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the * transition to HLT instead of running L2. */ if (enable_ept) vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) && WARN_ON_ONCE(__kvm_emulate_msr_write(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, vmcs12->guest_ia32_perf_global_ctrl))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); /* * It was observed that genuine Hyper-V running in L1 doesn't reset * 'hv_clean_fields' by itself, it only sets the corresponding dirty * bits when it changes a field in eVMCS. Mark all fields as clean * here. */ if (nested_vmx_is_evmptr12_valid(vmx)) evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; return 0; } static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) { if (CC(!nested_cpu_has_nmi_exiting(vmcs12) && nested_cpu_has_virtual_nmis(vmcs12))) return -EINVAL; if (CC(!nested_cpu_has_virtual_nmis(vmcs12) && nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING))) return -EINVAL; return 0; } static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* Check for memory type validity */ switch (new_eptp & VMX_EPTP_MT_MASK) { case VMX_EPTP_MT_UC: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))) return false; break; case VMX_EPTP_MT_WB: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT))) return false; break; default: return false; } /* Page-walk levels validity. */ switch (new_eptp & VMX_EPTP_PWL_MASK) { case VMX_EPTP_PWL_5: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT))) return false; break; case VMX_EPTP_PWL_4: if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT))) return false; break; default: return false; } /* Reserved bits should not be set */ if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) { if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))) return false; } return true; } /* * Checks related to VM-Execution Control Fields */ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (CC(!vmx_control_verify(vmcs12->pin_based_vm_exec_control, vmx->nested.msrs.pinbased_ctls_low, vmx->nested.msrs.pinbased_ctls_high)) || CC(!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, vmx->nested.msrs.procbased_ctls_low, vmx->nested.msrs.procbased_ctls_high))) return -EINVAL; if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) && CC(!vmx_control_verify(vmcs12->secondary_vm_exec_control, vmx->nested.msrs.secondary_ctls_low, vmx->nested.msrs.secondary_ctls_high))) return -EINVAL; if (CC(vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu)) || nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) || nested_vmx_check_apic_access_controls(vcpu, vmcs12) || nested_vmx_check_apicv_controls(vcpu, vmcs12) || nested_vmx_check_nmi_controls(vmcs12) || nested_vmx_check_pml_controls(vcpu, vmcs12) || nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) || nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) || nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) || CC(nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) return -EINVAL; if (!nested_cpu_has_preemption_timer(vmcs12) && nested_cpu_has_save_preemption_timer(vmcs12)) return -EINVAL; if (nested_cpu_has_ept(vmcs12) && CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer))) return -EINVAL; if (nested_cpu_has_vmfunc(vmcs12)) { if (CC(vmcs12->vm_function_control & ~vmx->nested.msrs.vmfunc_controls)) return -EINVAL; if (nested_cpu_has_eptp_switching(vmcs12)) { if (CC(!nested_cpu_has_ept(vmcs12)) || CC(!page_address_valid(vcpu, vmcs12->eptp_list_address))) return -EINVAL; } } return 0; } /* * Checks related to VM-Exit Control Fields */ static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (CC(!vmx_control_verify(vmcs12->vm_exit_controls, vmx->nested.msrs.exit_ctls_low, vmx->nested.msrs.exit_ctls_high)) || CC(nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12))) return -EINVAL; return 0; } /* * Checks related to VM-Entry Control Fields */ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (CC(!vmx_control_verify(vmcs12->vm_entry_controls, vmx->nested.msrs.entry_ctls_low, vmx->nested.msrs.entry_ctls_high))) return -EINVAL; /* * From the Intel SDM, volume 3: * Fields relevant to VM-entry event injection must be set properly. * These fields are the VM-entry interruption-information field, the * VM-entry exception error code, and the VM-entry instruction length. */ if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) { u32 intr_info = vmcs12->vm_entry_intr_info_field; u8 vector = intr_info & INTR_INFO_VECTOR_MASK; u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; bool urg = nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST); bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; /* VM-entry interruption-info field: interruption type */ if (CC(intr_type == INTR_TYPE_RESERVED) || CC(intr_type == INTR_TYPE_OTHER_EVENT && !nested_cpu_supports_monitor_trap_flag(vcpu))) return -EINVAL; /* VM-entry interruption-info field: vector */ if (CC(intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || CC(intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) return -EINVAL; /* * Cannot deliver error code in real mode or if the interrupt * type is not hardware exception. For other cases, do the * consistency check only if the vCPU doesn't enumerate * VMX_BASIC_NO_HW_ERROR_CODE_CC. */ if (!prot_mode || intr_type != INTR_TYPE_HARD_EXCEPTION) { if (CC(has_error_code)) return -EINVAL; } else if (!nested_cpu_has_no_hw_errcode_cc(vcpu)) { if (CC(has_error_code != x86_exception_has_error_code(vector))) return -EINVAL; } /* VM-entry exception error code */ if (CC(has_error_code && vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ if (CC(intr_info & INTR_INFO_RESVD_BITS_MASK)) return -EINVAL; /* VM-entry instruction length */ switch (intr_type) { case INTR_TYPE_SOFT_EXCEPTION: case INTR_TYPE_SOFT_INTR: case INTR_TYPE_PRIV_SW_EXCEPTION: if (CC(vmcs12->vm_entry_instruction_len > X86_MAX_INSTRUCTION_LENGTH) || CC(vmcs12->vm_entry_instruction_len == 0 && CC(!nested_cpu_has_zero_length_injection(vcpu)))) return -EINVAL; } } if (nested_vmx_check_entry_msr_switch_controls(vcpu, vmcs12)) return -EINVAL; return 0; } static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (nested_check_vm_execution_controls(vcpu, vmcs12) || nested_check_vm_exit_controls(vcpu, vmcs12) || nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; #ifdef CONFIG_KVM_HYPERV if (guest_cpu_cap_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); #endif return 0; } static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { #ifdef CONFIG_X86_64 if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) != !!(vcpu->arch.efer & EFER_LMA))) return -EINVAL; #endif return 0; } static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12) { /* * Check that the given linear address is canonical after a VM exit * from L2, based on HOST_CR4.LA57 value that will be loaded for L1. */ u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48; return !__is_canonical_address(la, l1_address_bits_on_exit); } static int nested_vmx_check_cet_state_common(struct kvm_vcpu *vcpu, u64 s_cet, u64 ssp, u64 ssp_tbl) { if (CC(!kvm_is_valid_u_s_cet(vcpu, s_cet)) || CC(!IS_ALIGNED(ssp, 4)) || CC(is_noncanonical_msr_address(ssp_tbl, vcpu))) return -EINVAL; return 0; } static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(vmcs12->host_cr4 & X86_CR4_CET && !(vmcs12->host_cr0 & X86_CR0_WP))) return -EINVAL; if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->host_ia32_pat))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), vmcs12->host_ia32_perf_global_ctrl))) return -EINVAL; if (ia32e) { if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; } else { if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || CC((vmcs12->host_rip) >> 32)) return -EINVAL; } if (CC(vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || CC(vmcs12->host_cs_selector == 0) || CC(vmcs12->host_tr_selector == 0) || CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) || CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) || CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) || CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) || CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) || CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12))) return -EINVAL; /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, * the values of the LMA and LME bits in the field must each be that of * the host address-space size VM-exit control. */ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { if (CC(!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer)) || CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA)) || CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))) return -EINVAL; } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) { if (nested_vmx_check_cet_state_common(vcpu, vmcs12->host_s_cet, vmcs12->host_ssp, vmcs12->host_ssp_tbl)) return -EINVAL; /* * IA32_S_CET and SSP must be canonical if the host will * enter 64-bit mode after VM-exit; otherwise, higher * 32-bits must be all 0s. */ if (ia32e) { if (CC(is_noncanonical_msr_address(vmcs12->host_s_cet, vcpu)) || CC(is_noncanonical_msr_address(vmcs12->host_ssp, vcpu))) return -EINVAL; } else { if (CC(vmcs12->host_s_cet >> 32) || CC(vmcs12->host_ssp >> 32)) return -EINVAL; } } return 0; } static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; struct vmcs_hdr hdr; if (vmcs12->vmcs_link_pointer == INVALID_GPA) return 0; if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; if (ghc->gpa != vmcs12->vmcs_link_pointer && CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmcs12->vmcs_link_pointer, VMCS12_SIZE))) return -EINVAL; if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, offsetof(struct vmcs12, hdr), sizeof(hdr)))) return -EINVAL; if (CC(hdr.revision_id != VMCS12_REVISION) || CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) return -EINVAL; return 0; } /* * Checks related to Guest Non-register State */ static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12) { if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT && vmcs12->guest_activity_state != GUEST_ACTIVITY_WAIT_SIPI)) return -EINVAL; return 0; } static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *entry_failure_code = ENTRY_FAIL_DEFAULT; if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) || CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) return -EINVAL; if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) return -EINVAL; if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { *entry_failure_code = ENTRY_FAIL_VMCS_LINK_PTR; return -EINVAL; } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), vmcs12->guest_ia32_perf_global_ctrl))) return -EINVAL; if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG)) return -EINVAL; if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) || CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG))) return -EINVAL; /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: * - Bits reserved in the IA32_EFER MSR must be 0. * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of * the IA-32e mode guest VM-exit control. It must also be identical * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to * CR0.PG) is 1. */ if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || CC(((vmcs12->guest_cr0 & X86_CR0_PG) && ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))) return -EINVAL; } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) { if (nested_vmx_check_cet_state_common(vcpu, vmcs12->guest_s_cet, vmcs12->guest_ssp, vmcs12->guest_ssp_tbl)) return -EINVAL; /* * Guest SSP must have 63:N bits identical, rather than * be canonical (i.e., 63:N-1 bits identical), where N is * the CPU's maximum linear-address width. Similar to * is_noncanonical_msr_address(), use the host's * linear-address width. */ if (CC(!__is_canonical_address(vmcs12->guest_ssp, max_host_virt_addr_bits() + 1))) return -EINVAL; } if (nested_check_guest_non_reg_state(vmcs12)) return -EINVAL; return 0; } static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; bool vm_fail; if (!nested_early_check) return 0; if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); if (vmx->msr_autoload.guest.nr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); preempt_disable(); vmx_prepare_switch_to_guest(vcpu); /* * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS, * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e. * there is no need to preserve other bits or save/restore the field. */ vmcs_writel(GUEST_RFLAGS, 0); cr3 = __get_current_cr3_fast(); if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { vmcs_writel(HOST_CR3, cr3); vmx->loaded_vmcs->host_state.cr3 = cr3; } cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); vmx->loaded_vmcs->host_state.cr4 = cr4; } vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, __vmx_vcpu_run_flags(vmx)); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); if (vmx->msr_autoload.guest.nr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); if (vm_fail) { u32 error = vmcs_read32(VM_INSTRUCTION_ERROR); preempt_enable(); trace_kvm_nested_vmenter_failed( "early hardware check VM-instruction error: ", error); WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } /* * VMExit clears RFLAGS.IF and DR7, even on a consistency check. */ if (hw_breakpoint_active()) set_debugreg(__this_cpu_read(cpu_dr7), 7); local_irq_enable(); preempt_enable(); /* * A non-failing VMEntry means we somehow entered guest mode with * an illegal RIP, and that's just the tip of the iceberg. There * is no telling what memory has been modified or what state has * been exposed to unknown code. Hitting this all but guarantees * a (very critical) hardware issue. */ WARN_ON(!(vmcs_read32(VM_EXIT_REASON) & VMX_EXIT_REASONS_FAILED_VMENTRY)); return 0; } #ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * hv_evmcs may end up being not mapped after migration (when * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ if (guest_cpu_cap_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || evmptrld_status == EVMPTRLD_ERROR) return false; /* * Post migration VMCS12 always provides the most actual * information, copy it to eVMCS upon entry. */ vmx->nested.need_vmcs12_to_shadow_sync = true; } return true; } #endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_host_map *map; if (!vcpu->arch.pdptrs_from_userspace && !nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { /* * Reload the guest's PDPTRs since after a migration * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { map = &vmx->nested.apic_access_page_map; if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->apic_access_addr), map)) { vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(map->pfn)); } else { pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n", __func__); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; return false; } } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { map = &vmx->nested.virtual_apic_map; if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->virtual_apic_page_addr), map)) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, pfn_to_hpa(map->pfn)); } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) && nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) && !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * The processor will never use the TPR shadow, simply * clear the bit from the execution control. Such a * configuration is useless, but it happens in tests. * For any other configuration, failing the vm entry is * _not_ what the processor does but it's basically the * only possibility we have. */ exec_controls_clearbit(vmx, CPU_BASED_TPR_SHADOW); } else { /* * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to * force VM-Entry to fail. */ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, INVALID_GPA); } } if (nested_cpu_has_posted_intr(vmcs12)) { map = &vmx->nested.pi_desc_map; if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->posted_intr_desc_addr), map)) { vmx->nested.pi_desc = (struct pi_desc *)(((void *)map->hva) + offset_in_page(vmcs12->posted_intr_desc_addr)); vmcs_write64(POSTED_INTR_DESC_ADDR, pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr)); } else { /* * Defer the KVM_INTERNAL_EXIT until KVM tries to * access the contents of the VMCS12 posted interrupt * descriptor. (Note that KVM may do this when it * should not, per the architectural specification.) */ vmx->nested.pi_desc = NULL; pin_controls_clearbit(vmx, PIN_BASED_POSTED_INTR); } } if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); return true; } static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_HYPERV /* * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post * migration. */ if (!nested_get_evmcs_page(vcpu)) { pr_debug_ratelimited("%s: enlightened vmptrld failed\n", __func__); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; return false; } #endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; return true; } static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); gpa_t dst; if (WARN_ON_ONCE(!is_guest_mode(vcpu))) return 0; if (WARN_ON_ONCE(vmx->nested.pml_full)) return 1; /* * Check if PML is enabled for the nested guest. Whether eptp bit 6 is * set is already checked as part of A/D emulation. */ vmcs12 = get_vmcs12(vcpu); if (!nested_cpu_has_pml(vmcs12)) return 0; if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) { vmx->nested.pml_full = true; return 1; } gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, offset_in_page(dst), sizeof(gpa))) return 0; vmcs12->guest_pml_index--; return 0; } /* * Intel's VMX Instruction Reference specifies a common set of prerequisites * for running VMX instructions (except VMXON, whose prerequisites are * slightly different). It also specifies what exception to inject otherwise. * Note that many of these exceptions have priority over VM exits, so they * don't have to be checked again here. */ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) { if (!to_vmx(vcpu)->nested.vmxon) { kvm_queue_exception(vcpu, UD_VECTOR); return 0; } if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); return 0; } return 1; } static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); /* * If from_vmentry is false, this is being called from state restore (either RSM * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. * * Returns: * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode * NVMX_VMENTRY_VMFAIL: Consistency check VMFail * NVMX_VMENTRY_VMEXIT: Consistency check VMExit * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error */ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; union vmx_exit_reason exit_reason = { .basic = EXIT_REASON_INVALID_STATE, .failed_vmentry = 1, }; u32 failed_index; trace_kvm_nested_vmenter(kvm_rip_read(vcpu), vmx->nested.current_vmptr, vmcs12->guest_rip, vmcs12->guest_intr_status, vmcs12->vm_entry_intr_info_field, vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT, vmcs12->ept_pointer, vmcs12->guest_cr3, KVM_ISA_VMX); kvm_service_local_tlb_flush_requests(vcpu); if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmx->nested.pre_vmenter_bndcfgs = vmcs_read64(GUEST_BNDCFGS); if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) vmcs_read_cet_state(vcpu, &vmx->nested.pre_vmenter_s_cet, &vmx->nested.pre_vmenter_ssp, &vmx->nested.pre_vmenter_ssp_tbl); /* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* * nested early checks are disabled. In the event of a "late" VM-Fail, * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its * software model to the pre-VMEntry host state. When EPT is disabled, * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3. Stuffing * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to * the correct value. Smashing vmcs01.GUEST_CR3 is safe because nested * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is * guaranteed to be overwritten with a shadow CR3 prior to re-entering * L1. Don't stuff vmcs01.GUEST_CR3 when using nested early checks as * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail * path would need to manually save/restore vmcs01.GUEST_CR3. */ if (!enable_ept && !nested_early_check) vmcs_writel(GUEST_CR3, vcpu->arch.cr3); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12); if (from_vmentry) { if (unlikely(!nested_get_vmcs12_pages(vcpu))) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_KVM_INTERNAL_ERROR; } if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_VMFAIL; } if (nested_vmx_check_guest_state(vcpu, vmcs12, &entry_failure_code)) { exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit; } } enter_guest_mode(vcpu); if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &entry_failure_code)) { exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; } if (from_vmentry) { failed_index = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); if (failed_index) { exit_reason.basic = EXIT_REASON_MSR_LOAD_FAIL; vmcs12->exit_qualification = failed_index; goto vmentry_fail_vmexit_guest_mode; } } else { /* * The MMU is not initialized to point at the right entities yet and * "get pages" would need to read data from the guest (i.e. we will * need to perform gpa to hpa translation). Request a call * to nested_get_vmcs12_pages before the next VM-entry. The MSRs * have already been set at vmentry time and should not be reset. */ kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); } /* * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit * unconditionally. Take care to pull data from vmcs01 as appropriate, * e.g. when checking for interrupt windows, as vmcs02 is now loaded. */ if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING)) || kvm_apic_has_pending_init_or_sipi(vcpu) || kvm_apic_has_interrupt(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); /* * Do not start the preemption timer hrtimer until after we know * we are successful, so that only nested_vmx_vmexit needs to cancel * the timer. */ vmx->nested.preemption_timer_expired = false; if (nested_cpu_has_preemption_timer(vmcs12)) { u64 timer_value = vmx_calc_preemption_timer_value(vcpu); vmx_start_preemption_timer(vcpu, timer_value); } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ return NVMX_VMENTRY_SUCCESS; /* * A failed consistency check that leads to a VMExit during L1's * VMEnter to L2 is a variation of a normal VMexit, as explained in * 26.7 "VM-entry failures during or after loading guest state". */ vmentry_fail_vmexit_guest_mode: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); vmentry_fail_vmexit: vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!from_vmentry) return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } /* * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 * for running an L2 nested guest. */ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); enum nested_evmptrld_status evmptrld_status; if (!nested_vmx_check_permission(vcpu)) return 1; evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch); if (evmptrld_status == EVMPTRLD_ERROR) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } kvm_pmu_branch_retired(vcpu); if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); if (CC(!nested_vmx_is_evmptr12_valid(vmx) && vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); vmcs12 = get_vmcs12(vcpu); /* * Can't VMLAUNCH or VMRESUME a shadow VMCS. Despite the fact * that there *is* a valid VMCS pointer, RFLAGS.CF is set * rather than RFLAGS.ZF, and no error number is stored to the * VM-instruction error field. */ if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); if (nested_vmx_is_evmptr12_valid(vmx)) { struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { copy_shadow_to_vmcs12(vmx); } /* * The nested entry process starts with enforcing various prerequisites * on vmcs12 as required by the Intel SDM, and act appropriately when * they fail: As the SDM explains, some conditions should cause the * instruction to fail, while others will cause the instruction to seem * to succeed, but return an EXIT_REASON_INVALID_STATE. * To speed up the normal (success) code path, we should avoid checking * for misconfigurations which will anyway be caught by the processor * when using the merged vmcs02. */ if (CC(interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS); if (CC(vmcs12->launch_state == launch)) return nested_vmx_fail(vcpu, launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS : VMXERR_VMRESUME_NONLAUNCHED_VMCS); if (nested_vmx_check_controls(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); if (nested_vmx_check_address_space_size(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); if (nested_vmx_check_host_state(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); /* * We're finally done with prerequisite checking, and can start with * the nested entry. */ vmx->nested.nested_run_pending = 1; vmx->nested.has_preemption_timer_deadline = false; status = nested_vmx_enter_non_root_mode(vcpu, true); if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; /* * Must happen outside of nested_vmx_enter_non_root_mode() as it will * also be used as part of restoring nVMX state for * snapshot restore (migration). * * In this flow, it is assumed that vmcs12 cache was * transferred as part of captured nVMX state and should * therefore not be read from guest memory (which may not * exist on destination host yet). */ nested_cache_shadow_vmcs12(vcpu, vmcs12); switch (vmcs12->guest_activity_state) { case GUEST_ACTIVITY_HLT: /* * If we're entering a halted L2 vcpu and the L2 vcpu won't be * awakened by event injection or by an NMI-window VM-exit or * by an interrupt-window VM-exit, halt the vcpu. */ if (!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && !nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING) && !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: vmx->nested.nested_run_pending = 0; kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED); break; default: break; } return 1; vmentry_failed: vmx->nested.nested_run_pending = 0; if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) return 0; if (status == NVMX_VMENTRY_VMEXIT) return 1; WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL); return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); } /* * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK). * This function returns the new value we should put in vmcs12.guest_cr0. * It's not enough to just return the vmcs02 GUEST_CR0. Rather, * 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now * available in vmcs02 GUEST_CR0. (Note: It's enough to check that L0 * didn't trap the bit, because if L1 did, so would L0). * 2. Bits that L1 asked to trap (and therefore L0 also did) could not have * been modified by L2, and L1 knows it. So just leave the old value of * the bit from vmcs12.guest_cr0. Note that the bit from vmcs02 GUEST_CR0 * isn't relevant, because if L0 traps this bit it can set it to anything. * 3. Bits that L1 didn't trap, but L0 did. L1 believes the guest could have * changed these bits, and therefore they need to be updated, but L0 * didn't necessarily allow them to be changed in GUEST_CR0 - and rather * put them in vmcs02 CR0_READ_SHADOW. So take these bits from there. */ static inline unsigned long vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { return /*1*/ (vmcs_readl(GUEST_CR0) & vcpu->arch.cr0_guest_owned_bits) | /*2*/ (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask) | /*3*/ (vmcs_readl(CR0_READ_SHADOW) & ~(vmcs12->cr0_guest_host_mask | vcpu->arch.cr0_guest_owned_bits)); } static inline unsigned long vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { return /*1*/ (vmcs_readl(GUEST_CR4) & vcpu->arch.cr4_guest_owned_bits) | /*2*/ (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask) | /*3*/ (vmcs_readl(CR4_READ_SHADOW) & ~(vmcs12->cr4_guest_host_mask | vcpu->arch.cr4_guest_owned_bits)); } static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 vm_exit_reason, u32 exit_intr_info) { u32 idt_vectoring; unsigned int nr; /* * Per the SDM, VM-Exits due to double and triple faults are never * considered to occur during event delivery, even if the double/triple * fault is the result of an escalating vectoring issue. * * Note, the SDM qualifies the double fault behavior with "The original * event results in a double-fault exception". It's unclear why the * qualification exists since exits due to double fault can occur only * while vectoring a different exception (injected events are never * subject to interception), i.e. there's _always_ an original event. * * The SDM also uses NMI as a confusing example for the "original event * causes the VM exit directly" clause. NMI isn't special in any way, * the same rule applies to all events that cause an exit directly. * NMI is an odd choice for the example because NMIs can only occur on * instruction boundaries, i.e. they _can't_ occur during vectoring. */ if ((u16)vm_exit_reason == EXIT_REASON_TRIPLE_FAULT || ((u16)vm_exit_reason == EXIT_REASON_EXCEPTION_NMI && is_double_fault(exit_intr_info))) { vmcs12->idt_vectoring_info_field = 0; } else if (vcpu->arch.exception.injected) { nr = vcpu->arch.exception.vector; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; if (kvm_exception_is_soft(nr)) { vmcs12->vm_exit_instruction_len = vcpu->arch.event_exit_inst_len; idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION; } else idt_vectoring |= INTR_TYPE_HARD_EXCEPTION; if (vcpu->arch.exception.has_error_code) { idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK; vmcs12->idt_vectoring_error_code = vcpu->arch.exception.error_code; } vmcs12->idt_vectoring_info_field = idt_vectoring; } else if (vcpu->arch.nmi_injected) { vmcs12->idt_vectoring_info_field = INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; } else if (vcpu->arch.interrupt.injected) { nr = vcpu->arch.interrupt.nr; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; if (vcpu->arch.interrupt.soft) { idt_vectoring |= INTR_TYPE_SOFT_INTR; vmcs12->vm_entry_instruction_len = vcpu->arch.event_exit_inst_len; } else idt_vectoring |= INTR_TYPE_EXT_INTR; vmcs12->idt_vectoring_info_field = idt_vectoring; } else { vmcs12->idt_vectoring_info_field = 0; } } void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gfn_t gfn; /* * Don't need to mark the APIC access page dirty; it is never * written to by the CPU during APIC virtualization. */ if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; kvm_vcpu_mark_page_dirty(vcpu, gfn); } if (nested_cpu_has_posted_intr(vmcs12)) { gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; kvm_vcpu_mark_page_dirty(vcpu, gfn); } } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; if (!vmx->nested.pi_pending) return 0; if (!vmx->nested.pi_desc) goto mmio_needed; vmx->nested.pi_pending = false; if (!pi_test_and_clear_on(vmx->nested.pi_desc)) return 0; max_irr = pi_find_highest_vector(vmx->nested.pi_desc); if (max_irr > 0) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) goto mmio_needed; __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page, &max_irr); status = vmcs_read16(GUEST_INTR_STATUS); if ((u8)max_irr > ((u8)status & 0xff)) { status &= ~0xff; status |= (u8)max_irr; vmcs_write16(GUEST_INTR_STATUS, status); } } nested_mark_vmcs12_pages_dirty(vcpu); return 0; mmio_needed: kvm_handle_memory_failure(vcpu, X86EMUL_IO_NEEDED, NULL); return -ENXIO; } static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long exit_qual; if (ex->has_payload) { exit_qual = ex->payload; } else if (ex->vector == PF_VECTOR) { exit_qual = vcpu->arch.cr2; } else if (ex->vector == DB_VECTOR) { exit_qual = vcpu->arch.dr6; exit_qual &= ~DR6_BT; exit_qual ^= DR6_ACTIVE_LOW; } else { exit_qual = 0; } /* * Unlike AMD's Paged Real Mode, which reports an error code on #PF * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the * "has error code" flags on VM-Exit if the CPU is in Real Mode. */ if (ex->has_error_code && is_protmode(vcpu)) { /* * Intel CPUs do not generate error codes with bits 31:16 set, * and more importantly VMX disallows setting bits 31:16 in the * injected error code for VM-Entry. Drop the bits to mimic * hardware and avoid inducing failure on nested VM-Entry if L1 * chooses to inject the exception back to L2. AMD CPUs _do_ * generate "full" 32-bit error codes, so KVM allows userspace * to inject exception error codes with bits 31:16 set. */ vmcs12->vm_exit_intr_error_code = (u16)ex->error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (kvm_exception_is_soft(ex->vector)) intr_info |= INTR_TYPE_SOFT_EXCEPTION; else intr_info |= INTR_TYPE_HARD_EXCEPTION; if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) && vmx_get_nmi_mask(vcpu)) intr_info |= INTR_INFO_UNBLOCK_NMI; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } /* * Returns true if a debug trap is (likely) pending delivery. Infer the class * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6). * Using the payload is flawed because code breakpoints (fault-like) and data * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e. * this will return false positives if a to-be-injected code breakpoint #DB is * pending (from KVM's perspective, but not "pending" across an instruction * boundary). ICEBP, a.k.a. INT1, is also not reflected here even though it * too is trap-like. * * KVM "works" despite these flaws as ICEBP isn't currently supported by the * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the * #DB has already happened), and MTF isn't marked pending on code breakpoints * from the emulator (because such #DBs are fault-like and thus don't trigger * actions that fire on instruction retire). */ static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex) { if (!ex->pending || ex->vector != DB_VECTOR) return 0; /* General Detect #DBs are always fault-like. */ return ex->payload & ~DR6_BD; } /* * Returns true if there's a pending #DB exception that is lower priority than * a pending Monitor Trap Flag VM-Exit. TSS T-flag #DBs are not emulated by * KVM, but could theoretically be injected by userspace. Note, this code is * imperfect, see above. */ static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex) { return vmx_get_pending_dbg_trap(ex) & ~DR6_BT; } /* * Certain VM-exits set the 'pending debug exceptions' field to indicate a * recognized #DB (data or single-step) that has yet to be delivered. Since KVM * represents these debug traps with a payload that is said to be compatible * with the 'pending debug exceptions' field, write the payload to the VMCS * field if a VM-exit is delivered before the debug trap. */ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) { unsigned long pending_dbg; pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception); if (pending_dbg) vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg); } static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) { return nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) && to_vmx(vcpu)->nested.preemption_timer_expired; } static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_vmx *vmx = to_vmx(vcpu); void *vapic = vmx->nested.virtual_apic_map.hva; int max_irr, vppr; if (nested_vmx_preemption_timer_pending(vcpu) || vmx->nested.mtf_pending) return true; /* * Virtual Interrupt Delivery doesn't require manual injection. Either * the interrupt is already in GUEST_RVI and will be recognized by CPU * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move * the interrupt from the PIR to RVI prior to entering the guest. */ if (for_injection) return false; if (!nested_cpu_has_vid(get_vmcs12(vcpu)) || __vmx_interrupt_blocked(vcpu)) return false; if (!vapic) return false; vppr = *((u32 *)(vapic + APIC_PROCPRI)); max_irr = vmx_get_rvi(); if ((max_irr & 0xf0) > (vppr & 0xf0)) return true; if (vmx->nested.pi_pending && vmx->nested.pi_desc && pi_test_on(vmx->nested.pi_desc)) { max_irr = pi_find_highest_vector(vmx->nested.pi_desc); if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0)) return true; } return false; } /* * Per the Intel SDM's table "Priority Among Concurrent Events", with minor * edits to fill in missing examples, e.g. #DB due to split-lock accesses, * and less minor edits to splice in the priority of VMX Non-Root specific * events, e.g. MTF and NMI/INTR-window exiting. * * 1 Hardware Reset and Machine Checks * - RESET * - Machine Check * * 2 Trap on Task Switch * - T flag in TSS is set (on task switch) * * 3 External Hardware Interventions * - FLUSH * - STOPCLK * - SMI * - INIT * * 3.5 Monitor Trap Flag (MTF) VM-exit[1] * * 4 Traps on Previous Instruction * - Breakpoints * - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O * breakpoint, or #DB due to a split-lock access) * * 4.3 VMX-preemption timer expired VM-exit * * 4.6 NMI-window exiting VM-exit[2] * * 5 Nonmaskable Interrupts (NMI) * * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery * * 6 Maskable Hardware Interrupts * * 7 Code Breakpoint Fault * * 8 Faults from Fetching Next Instruction * - Code-Segment Limit Violation * - Code Page Fault * - Control protection exception (missing ENDBRANCH at target of indirect * call or jump) * * 9 Faults from Decoding Next Instruction * - Instruction length > 15 bytes * - Invalid Opcode * - Coprocessor Not Available * *10 Faults on Executing Instruction * - Overflow * - Bound error * - Invalid TSS * - Segment Not Present * - Stack fault * - General Protection * - Data Page Fault * - Alignment Check * - x86 FPU Floating-point exception * - SIMD floating-point exception * - Virtualization exception * - Control protection exception * * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs), * INIT signals, and higher priority events take priority over MTF VM exits. * MTF VM exits take priority over debug-trap exceptions and lower priority * events. * * [2] Debug-trap exceptions and higher priority events take priority over VM exits * caused by the VMX-preemption timer. VM exits caused by the VMX-preemption * timer take priority over VM exits caused by the "NMI-window exiting" * VM-execution control and lower priority events. * * [3] Debug-trap exceptions and higher priority events take priority over VM exits * caused by "NMI-window exiting". VM exits caused by this control take * priority over non-maskable interrupts (NMIs) and lower priority events. * * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to * the 1-setting of the "interrupt-window exiting" VM-execution control. Thus, * non-maskable interrupts (NMIs) and higher priority events take priority over * delivery of a virtual interrupt; delivery of a virtual interrupt takes * priority over external interrupts and lower priority events. */ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Only a pending nested run blocks a pending exception. If there is a * previously injected event, the pending exception occurred while said * event was being delivered and thus needs to be handled. */ bool block_nested_exceptions = vmx->nested.nested_run_pending; /* * Events that don't require injection, i.e. that are virtualized by * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need * to regain control in order to deliver the event, and hardware will * handle event ordering, e.g. with respect to injected exceptions. * * But, new events (not exceptions) are only recognized at instruction * boundaries. If an event needs reinjection, then KVM is handling a * VM-Exit that occurred _during_ instruction execution; new events, * irrespective of whether or not they're injected, are blocked until * the instruction completes. */ bool block_non_injected_events = kvm_event_needs_reinjection(vcpu); /* * Inject events are blocked by nested VM-Enter, as KVM is responsible * for managing priority between concurrent events, i.e. KVM needs to * wait until after VM-Enter completes to deliver injected events. */ bool block_nested_events = block_nested_exceptions || block_non_injected_events; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); clear_bit(KVM_APIC_INIT, &apic->pending_events); if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED) nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); /* MTF is discarded if the vCPU is in WFS. */ vmx->nested.mtf_pending = false; return 0; } if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_SIPI, &apic->pending_events)) { if (block_nested_events) return -EBUSY; clear_bit(KVM_APIC_SIPI, &apic->pending_events); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0, apic->sipi_vector & 0xFFUL); return 0; } /* Fallthrough, the SIPI is completely ignored. */ } /* * Process exceptions that are higher priority than Monitor Trap Flag: * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but * could theoretically come in from userspace), and ICEBP (INT1). * * TODO: SMIs have higher priority than MTF and trap-like #DBs (except * for TSS T flag #DBs). KVM also doesn't save/restore pending MTF * across SMI/RSM as it should; that needs to be addressed in order to * prioritize SMI over MTF and trap-like #DBs. */ if (vcpu->arch.exception_vmexit.pending && !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) { if (block_nested_exceptions) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu); return 0; } if (vcpu->arch.exception.pending && !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) { if (block_nested_exceptions) return -EBUSY; goto no_vmexit; } if (vmx->nested.mtf_pending) { if (block_nested_events) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); return 0; } if (vcpu->arch.exception_vmexit.pending) { if (block_nested_exceptions) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu); return 0; } if (vcpu->arch.exception.pending) { if (block_nested_exceptions) return -EBUSY; goto no_vmexit; } if (nested_vmx_preemption_timer_pending(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0); return 0; } if (vcpu->arch.smi_pending && !is_smm(vcpu)) { if (block_nested_events) return -EBUSY; goto no_vmexit; } if (vcpu->arch.nmi_pending && !vmx_nmi_blocked(vcpu)) { if (block_nested_events) return -EBUSY; if (!nested_exit_on_nmi(vcpu)) goto no_vmexit; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, NMI_VECTOR | INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK, 0); /* * The NMI-triggered VM exit counts as injection: * clear this one and block further NMIs. */ vcpu->arch.nmi_pending = 0; vmx_set_nmi_mask(vcpu, true); return 0; } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { int irq; if (!nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; goto no_vmexit; } if (!nested_exit_intr_ack_set(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); return 0; } irq = kvm_cpu_get_extint(vcpu); if (irq != -1) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); return 0; } irq = kvm_apic_has_interrupt(vcpu); if (WARN_ON_ONCE(irq < 0)) goto no_vmexit; /* * If the IRQ is L2's PI notification vector, process posted * interrupts for L2 instead of injecting VM-Exit, as the * detection/morphing architecturally occurs when the IRQ is * delivered to the CPU. Note, only interrupts that are routed * through the local APIC trigger posted interrupt processing, * and enabling posted interrupts requires ACK-on-exit. */ if (irq == vmx->nested.posted_intr_nv) { /* * Nested posted interrupts are delivered via RVI, i.e. * aren't injected by KVM, and so can be queued even if * manual event injection is disallowed. */ if (block_non_injected_events) return -EBUSY; vmx->nested.pi_pending = true; kvm_apic_clear_irr(vcpu, irq); goto no_vmexit; } if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); /* * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI * if APICv is active. */ kvm_apic_ack_interrupt(vcpu, irq); return 0; } no_vmexit: return vmx_complete_nested_posted_interrupt(vcpu); } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) { ktime_t remaining = hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer); u64 value; if (ktime_to_ns(remaining) <= 0) return 0; value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz; do_div(value, 1000000); return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; } static bool is_vmcs12_ext_field(unsigned long field) { switch (field) { case GUEST_ES_SELECTOR: case GUEST_CS_SELECTOR: case GUEST_SS_SELECTOR: case GUEST_DS_SELECTOR: case GUEST_FS_SELECTOR: case GUEST_GS_SELECTOR: case GUEST_LDTR_SELECTOR: case GUEST_TR_SELECTOR: case GUEST_ES_LIMIT: case GUEST_CS_LIMIT: case GUEST_SS_LIMIT: case GUEST_DS_LIMIT: case GUEST_FS_LIMIT: case GUEST_GS_LIMIT: case GUEST_LDTR_LIMIT: case GUEST_TR_LIMIT: case GUEST_GDTR_LIMIT: case GUEST_IDTR_LIMIT: case GUEST_ES_AR_BYTES: case GUEST_DS_AR_BYTES: case GUEST_FS_AR_BYTES: case GUEST_GS_AR_BYTES: case GUEST_LDTR_AR_BYTES: case GUEST_TR_AR_BYTES: case GUEST_ES_BASE: case GUEST_CS_BASE: case GUEST_SS_BASE: case GUEST_DS_BASE: case GUEST_FS_BASE: case GUEST_GS_BASE: case GUEST_LDTR_BASE: case GUEST_TR_BASE: case GUEST_GDTR_BASE: case GUEST_IDTR_BASE: case GUEST_PENDING_DBG_EXCEPTIONS: case GUEST_BNDCFGS: return true; default: break; } return false; } static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR); vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR); vmcs12->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR); vmcs12->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR); vmcs12->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR); vmcs12->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR); vmcs12->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR); vmcs12->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR); vmcs12->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT); vmcs12->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT); vmcs12->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT); vmcs12->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT); vmcs12->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT); vmcs12->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT); vmcs12->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT); vmcs12->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT); vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT); vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT); vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES); vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES); vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES); vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES); vmcs12->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES); vmcs12->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES); vmcs12->guest_es_base = vmcs_readl(GUEST_ES_BASE); vmcs12->guest_cs_base = vmcs_readl(GUEST_CS_BASE); vmcs12->guest_ss_base = vmcs_readl(GUEST_SS_BASE); vmcs12->guest_ds_base = vmcs_readl(GUEST_DS_BASE); vmcs12->guest_fs_base = vmcs_readl(GUEST_FS_BASE); vmcs12->guest_gs_base = vmcs_readl(GUEST_GS_BASE); vmcs12->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE); vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE); vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE); vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE); vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false; } static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; if (!vmx->nested.need_sync_vmcs02_to_vmcs12_rare) return; WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01); cpu = get_cpu(); vmx->loaded_vmcs = &vmx->nested.vmcs02; vmx_vcpu_load_vmcs(vcpu, cpu); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->loaded_vmcs = &vmx->vmcs01; vmx_vcpu_load_vmcs(vcpu, cpu); put_cpu(); } /* * Update the guest state fields of vmcs12 to reflect changes that * occurred while L2 was running. (The "IA-32e mode guest" bit of the * VM-entry controls is also updated, since this is really a guest * state bit.) */ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (nested_vmx_is_evmptr12_valid(vmx)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = !nested_vmx_is_evmptr12_valid(vmx); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); vmcs12->guest_rsp = kvm_rsp_read(vcpu); vmcs12->guest_rip = kvm_rip_read(vcpu); vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS); vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES); vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES); vmcs12->guest_interruptibility_info = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT; else if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) vmcs12->guest_activity_state = GUEST_ACTIVITY_WAIT_SIPI; else vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; if (nested_cpu_has_preemption_timer(vmcs12) && vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER && !vmx->nested.nested_run_pending) vmcs12->vmx_preemption_timer_value = vmx_get_preemption_timer_value(vcpu); /* * In some cases (usually, nested EPT), L2 is allowed to change its * own CR3 without exiting. If it has changed it, we must keep it. * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12. * * Additionally, restore L2's PDPTR to vmcs12. */ if (enable_ept) { vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3); if (nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); } } vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); if (nested_cpu_has_vid(vmcs12)) vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS); vmcs12->vm_entry_controls = (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); /* * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. * Writes to DEBUGCTL that aren't intercepted by L1 are immediately * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into * vmcs02 doesn't strictly track vmcs12. */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) vmcs12->guest_dr7 = vcpu->arch.dr7; if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; vmcs_read_cet_state(&vmx->vcpu, &vmcs12->guest_s_cet, &vmcs12->guest_ssp, &vmcs12->guest_ssp_tbl); } /* * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), * and this function updates it to reflect the changes to the guest state while * L2 was running (and perhaps made some exits which were handled directly by L0 * without going back to L1), and to reflect the exit reason. * Note that we do not have to copy here all VMCS fields, just those that * could have changed by the L2 guest or the exit - i.e., the guest-state and * exit-information fields only. Other fields are modified by L1 with VMWRITE, * which already writes to vmcs12 directly. */ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 vm_exit_reason, u32 exit_intr_info, unsigned long exit_qualification, u32 exit_insn_len) { /* update exit information fields: */ vmcs12->vm_exit_reason = vm_exit_reason; if (vmx_get_exit_reason(vcpu).enclave_mode) vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE; vmcs12->exit_qualification = exit_qualification; /* * On VM-Exit due to a failed VM-Entry, the VMCS isn't marked launched * and only EXIT_REASON and EXIT_QUALIFICATION are updated, all other * exit info fields are unmodified. */ if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { vmcs12->launch_state = 1; /* vm_entry_intr_info_field is cleared on exit. Emulate this * instead of reading the real value. */ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK; /* * Transfer the event that L0 or L1 may wanted to inject into * L2 to IDT_VECTORING_INFO_FIELD. */ vmcs12_save_pending_event(vcpu, vmcs12, vm_exit_reason, exit_intr_info); vmcs12->vm_exit_intr_info = exit_intr_info; vmcs12->vm_exit_instruction_len = exit_insn_len; vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); /* * According to spec, there's no need to store the guest's * MSRs if the exit is due to a VM-entry failure that occurs * during or after loading the guest state. Since this exit * does not fall in that category, we need to save the MSRs. */ if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr, vmcs12->vm_exit_msr_store_count)) nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } } /* * A part of what we need to when the nested L2 guest exits and we want to * run its L1 parent, is to reset L1's guest state to the host state specified * in vmcs12. * This function is to be called not only on normal nested exit, but also on * a nested entry failure, as explained in Intel's spec, 3B.23.7 ("VM-Entry * Failures During or After Loading Guest State"). * This function should be called when the active VMCS is L1's (vmcs01). */ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { enum vm_entry_failure_code ignored; struct kvm_segment seg; if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); else vcpu->arch.efer &= ~(EFER_LMA | EFER_LME); vmx_set_efer(vcpu, vcpu->arch.efer); kvm_rsp_write(vcpu, vmcs12->host_rsp); kvm_rip_write(vcpu, vmcs12->host_rip); vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); vmx_set_interrupt_shadow(vcpu, 0); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't * actually changed, because vmx_set_cr0 refers to efer set above. * * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); vmx_set_cr4(vcpu, vmcs12->host_cr4); nested_ept_uninit_mmu_context(vcpu); /* * Only PDPTE load can fail as the value of cr3 was checked on entry and * couldn't have changed. */ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, true, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip); vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base); vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF); vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF); /* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1. */ if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, 0); /* * Load CET state from host state if VM_EXIT_LOAD_CET_STATE is set. * otherwise CET state should be retained across VM-exit, i.e., * guest values should be propagated from vmcs12 to vmcs01. */ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) vmcs_write_cet_state(vcpu, vmcs12->host_s_cet, vmcs12->host_ssp, vmcs12->host_ssp_tbl); else vmcs_write_cet_state(vcpu, vmcs12->guest_s_cet, vmcs12->guest_ssp, vmcs12->guest_ssp_tbl); if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat); vcpu->arch.pat = vmcs12->host_ia32_pat; } if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu))) WARN_ON_ONCE(__kvm_emulate_msr_write(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, vmcs12->host_ia32_perf_global_ctrl)); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ seg = (struct kvm_segment) { .base = 0, .limit = 0xFFFFFFFF, .selector = vmcs12->host_cs_selector, .type = 11, .present = 1, .s = 1, .g = 1 }; if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) seg.l = 1; else seg.db = 1; __vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); seg = (struct kvm_segment) { .base = 0, .limit = 0xFFFFFFFF, .type = 3, .present = 1, .s = 1, .db = 1, .g = 1 }; seg.selector = vmcs12->host_ds_selector; __vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); seg.selector = vmcs12->host_es_selector; __vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); seg.selector = vmcs12->host_ss_selector; __vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); seg.selector = vmcs12->host_fs_selector; seg.base = vmcs12->host_fs_base; __vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); seg.selector = vmcs12->host_gs_selector; seg.base = vmcs12->host_gs_base; __vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); seg = (struct kvm_segment) { .base = vmcs12->host_tr_base, .limit = 0x67, .selector = vmcs12->host_tr_selector, .type = 11, .present = 1 }; __vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); memset(&seg, 0, sizeof(seg)); seg.unusable = 1; __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); kvm_set_dr(vcpu, 7, 0x400); vmx_guest_debugctl_write(vcpu, 0); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); to_vt(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) { struct vmx_uret_msr *efer_msr; unsigned int i; if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER) return vmcs_read64(GUEST_IA32_EFER); if (cpu_has_load_ia32_efer()) return kvm_host.efer; for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) { if (vmx->msr_autoload.guest.val[i].index == MSR_EFER) return vmx->msr_autoload.guest.val[i].value; } efer_msr = vmx_find_uret_msr(vmx, MSR_EFER); if (efer_msr) return efer_msr->data; return kvm_host.efer; } static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_msr_entry g, h; gpa_t gpa; u32 i, j; vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT); if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { /* * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set * as vmcs01.GUEST_DR7 contains a userspace defined value * and vcpu->arch.dr7 is not squirreled away before the * nested VMENTER (not worth adding a variable in nested_vmx). */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) kvm_set_dr(vcpu, 7, DR7_FIXED_1); else WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); } /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */ vmx_reload_guest_debugctl(vcpu); /* * Note that calling vmx_set_{efer,cr0,cr4} is important as they * handle a variety of side effects to KVM's software model. */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs * from vmcs01 (if necessary). The PDPTRs are not loaded on * VMFail, like everything else we just need to ensure our * software model is up-to-date. */ if (enable_ept && is_pae_paging(vcpu)) ept_save_pdptrs(vcpu); kvm_mmu_reset_context(vcpu); /* * This nasty bit of open coding is a compromise between blindly * loading L1's MSRs using the exit load lists (incorrect emulation * of VMFail), leaving the nested VM's MSRs in the software model * (incorrect behavior) and snapshotting the modified MSRs (too * expensive since the lists are unbound by hardware). For each * MSR that was (prematurely) loaded from the nested VMEntry load * list, reload it from the exit load list if it exists and differs * from the guest value. The intent is to stuff host state as * silently as possible, not to fully process the exit load list. */ for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) { gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g)); if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) { pr_debug_ratelimited( "%s read MSR index failed (%u, 0x%08llx)\n", __func__, i, gpa); goto vmabort; } for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) { gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h)); if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) { pr_debug_ratelimited( "%s read MSR failed (%u, 0x%08llx)\n", __func__, j, gpa); goto vmabort; } if (h.index != g.index) continue; if (h.value == g.value) break; if (nested_vmx_load_msr_check(vcpu, &h)) { pr_debug_ratelimited( "%s check failed (%u, 0x%x, 0x%x)\n", __func__, j, h.index, h.reserved); goto vmabort; } if (kvm_emulate_msr_write(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); goto vmabort; } } } return; vmabort: nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); } /* * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1 * and modify vmcs12 to make it see what it would expect to see there if * L2 was its real guest. Must only be called when in L2 (is_guest_mode()) */ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, u32 exit_intr_info, unsigned long exit_qualification, u32 exit_insn_len) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); /* Pending MTF traps are discarded on VM-Exit. */ vmx->nested.mtf_pending = false; /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); #ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map * Enlightened VMCS after migration and we still need to * do that when something is forcing L2->L1 exit prior to * the first L2 run. */ (void)nested_get_evmcs_page(vcpu); } #endif /* Service pending TLB flush requests for L2 before switching to L1. */ kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between * now and the new vmentry. Ensure that the VMCS02 PDPTR fields are * up-to-date before switching to L1. */ if (enable_ept && is_pae_paging(vcpu)) vmx_ept_load_pdptrs(vcpu); leave_guest_mode(vcpu); if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) { vcpu->arch.tsc_offset = vcpu->arch.l1_tsc_offset; if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; } if (likely(!vmx->fail)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); if (vm_exit_reason != -1) prepare_vmcs12(vcpu, vmcs12, vm_exit_reason, exit_intr_info, exit_qualification, exit_insn_len); /* * Must happen outside of sync_vmcs02_to_vmcs12() as it will * also be used to capture vmcs12 cache as part of * capturing nVMX state for snapshot (migration). * * Otherwise, this flush will dirty guest memory at a * point it is already assumed by user-space to be * immutable. */ nested_flush_cached_shadow_vmcs12(vcpu, vmcs12); } else { /* * The only expected VM-instruction error is "VM entry with * invalid control field(s)." Anything else indicates a * problem with L0. And we should never get here with a * VMFail of any type if early consistency checks are enabled. */ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != VMXERR_ENTRY_INVALID_CONTROL_FIELD); WARN_ON_ONCE(nested_early_check); } /* * Drop events/exceptions that were queued for re-injection to L2 * (picked up via vmx_complete_interrupts()), as well as exceptions * that were pending for L2. Note, this must NOT be hoisted above * prepare_vmcs12(), events/exceptions queued for re-injection need to * be captured in vmcs12 (see vmcs12_save_pending_event()). */ vcpu->arch.nmi_injected = false; kvm_clear_exception_queue(vcpu); kvm_clear_interrupt_queue(vcpu); vmx_switch_vmcs(vcpu, &vmx->vmcs01); kvm_nested_vmexit_handle_ibrs(vcpu); /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); if (vmx->nested.l1_tpr_threshold != -1) vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); if (vmx->nested.change_vmcs01_virtual_apic_mode) { vmx->nested.change_vmcs01_virtual_apic_mode = false; vmx_set_virtual_apic_mode(vcpu); } if (vmx->nested.update_vmcs01_cpu_dirty_logging) { vmx->nested.update_vmcs01_cpu_dirty_logging = false; vmx_update_cpu_dirty_logging(vcpu); } nested_put_vmcs12_pages(vcpu); if (vmx->nested.reload_vmcs01_apic_access_page) { vmx->nested.reload_vmcs01_apic_access_page = false; kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } if (vmx->nested.update_vmcs01_apicv_status) { vmx->nested.update_vmcs01_apicv_status = false; kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } if (vmx->nested.update_vmcs01_hwapic_isr) { vmx->nested.update_vmcs01_hwapic_isr = false; kvm_apic_update_hwapic_isr(vcpu); } if ((vm_exit_reason != -1) && (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); if (likely(!vmx->fail)) { if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, vmcs12->idt_vectoring_info_field, vmcs12->vm_exit_intr_info, vmcs12->vm_exit_intr_error_code, KVM_ISA_VMX); load_vmcs12_host_state(vcpu, vmcs12); /* * Process events if an injectable IRQ or NMI is pending, even * if the event is blocked (RFLAGS.IF is cleared on VM-Exit). * If an event became pending while L2 was active, KVM needs to * either inject the event or request an IRQ/NMI window. SMIs * don't need to be processed as SMM is mutually exclusive with * non-root mode. INIT/SIPI don't need to be checked as INIT * is blocked post-VMXON, and SIPIs are ignored. */ if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending) kvm_make_request(KVM_REQ_EVENT, vcpu); return; } /* * After an early L2 VM-entry failure, we're now back * in L1 which thinks it just finished a VMLAUNCH or * VMRESUME instruction, so we need to set the failure * flag and the VM-instruction error field of the VMCS * accordingly, and skip the emulated instruction. */ (void)nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); /* * Restore L1's host state to KVM's software model. We're here * because a consistency check was caught by hardware, which * means some amount of guest state has been propagated to KVM's * model and needs to be unwound to the host's state. */ nested_vmx_restore_host_state(vcpu); vmx->fail = 0; } static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } /* * Decode the memory-address operand of a vmx instruction, as recorded on an * exit caused by such an instruction (run by a guest hypervisor). * On success, returns 0. When the operand is invalid, returns 1 and throws * #UD, #GP, or #SS. */ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret) { gva_t off; bool exn; struct kvm_segment s; /* * According to Vol. 3B, "Information for VM Exits Due to Instruction * Execution", on an exit, vmx_instruction_info holds most of the * addressing components of the operand. Only the displacement part * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). * For how an actual address is calculated from all these components, * refer to Vol. 1, "Operand Addressing". */ int scaling = vmx_instruction_info & 3; int addr_size = (vmx_instruction_info >> 7) & 7; bool is_reg = vmx_instruction_info & (1u << 10); int seg_reg = (vmx_instruction_info >> 15) & 7; int index_reg = (vmx_instruction_info >> 18) & 0xf; bool index_is_valid = !(vmx_instruction_info & (1u << 22)); int base_reg = (vmx_instruction_info >> 23) & 0xf; bool base_is_valid = !(vmx_instruction_info & (1u << 27)); if (is_reg) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ off = exit_qualification; /* holds the displacement */ if (addr_size == 1) off = (gva_t)sign_extend64(off, 31); else if (addr_size == 0) off = (gva_t)sign_extend64(off, 15); if (base_is_valid) off += kvm_register_read(vcpu, base_reg); if (index_is_valid) off += kvm_register_read(vcpu, index_reg) << scaling; vmx_get_segment(vcpu, &s, seg_reg); /* * The effective address, i.e. @off, of a memory operand is truncated * based on the address size of the instruction. Note that this is * the *effective address*, i.e. the address prior to accounting for * the segment's base. */ if (addr_size == 1) /* 32 bit */ off &= 0xffffffff; else if (addr_size == 0) /* 16 bit */ off &= 0xffff; /* Checks for #GP/#SS exceptions. */ exn = false; if (is_long_mode(vcpu)) { /* * The virtual/linear address is never truncated in 64-bit * mode, e.g. a 32-bit address size can yield a 64-bit virtual * address when using FS/GS with a non-zero base. */ if (seg_reg == VCPU_SREG_FS || seg_reg == VCPU_SREG_GS) *ret = s.base + off; else *ret = off; *ret = vmx_get_untagged_addr(vcpu, *ret, 0); /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! */ exn = is_noncanonical_address(*ret, vcpu, 0); } else { /* * When not in long mode, the virtual/linear address is * unconditionally truncated to 32 bits regardless of the * address size. */ *ret = (s.base + off) & 0xffffffff; /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) * - usability check (#GP(0)/#SS(0)) * - limit check (#GP(0)/#SS(0)) */ if (wr) /* #GP(0) if the destination operand is located in a * read-only data segment or any code segment. */ exn = ((s.type & 0xa) == 0 || (s.type & 8)); else /* #GP(0) if the source operand is located in an * execute-only code segment */ exn = ((s.type & 0xa) == 8); if (exn) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); /* * Protected mode: #GP(0)/#SS(0) if the memory operand is * outside the segment limit. All CPUs that support VMX ignore * limit checks for flat segments, i.e. segments with base==0, * limit==0xffffffff and of type expand-up data or code. */ if (!(s.base == 0 && s.limit == 0xffffffff && ((s.type & 8) || !(s.type & 4)))) exn = exn || ((u64)off + len - 1 > s.limit); } if (exn) { kvm_queue_exception_e(vcpu, seg_reg == VCPU_SREG_SS ? SS_VECTOR : GP_VECTOR, 0); return 1; } return 0; } static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer, int *ret) { gva_t gva; struct x86_exception e; int r; if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmcs_read32(VMX_INSTRUCTION_INFO), false, sizeof(*vmpointer), &gva)) { *ret = 1; return -EINVAL; } r = kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e); if (r != X86EMUL_CONTINUE) { *ret = kvm_handle_memory_failure(vcpu, r, &e); return -EINVAL; } return 0; } /* * Allocate a shadow VMCS and associate it with the currently loaded * VMCS, unless such a shadow VMCS already exists. The newly allocated * VMCS is also VMCLEARed, so that it is ready for use. */ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs; /* * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it * when L1 executes VMXOFF or the vCPU is forced out of nested * operation. VMXON faults if the CPU is already post-VMXON, so it * should be impossible to already have an allocated shadow VMCS. KVM * doesn't support virtualization of VMCS shadowing, so vmcs01 should * always be the loaded VMCS. */ if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs)) return loaded_vmcs->shadow_vmcs; loaded_vmcs->shadow_vmcs = alloc_vmcs(true); if (loaded_vmcs->shadow_vmcs) vmcs_clear(loaded_vmcs->shadow_vmcs); return loaded_vmcs->shadow_vmcs; } static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = alloc_loaded_vmcs(&vmx->nested.vmcs02); if (r < 0) goto out_vmcs02; vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu)) goto out_shadow_vmcs; hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); vmx->nested.vpid02 = allocate_vpid(); vmx->nested.vmcs02_initialized = false; vmx->nested.vmxon = true; if (vmx_pt_mode_is_host_guest()) { vmx->pt_desc.guest.ctl = 0; pt_update_intercept_for_msr(vcpu); } return 0; out_shadow_vmcs: kfree(vmx->nested.cached_shadow_vmcs12); out_cached_shadow_vmcs12: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: free_loaded_vmcs(&vmx->nested.vmcs02); out_vmcs02: return -ENOMEM; } /* Emulate the VMXON instruction. */ static int handle_vmxon(struct kvm_vcpu *vcpu) { int ret; gpa_t vmptr; uint32_t revision; struct vcpu_vmx *vmx = to_vmx(vcpu); const u64 VMXON_NEEDED_FEATURES = FEAT_CTL_LOCKED | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter * the guest and so cannot rely on hardware to perform the check, * which has higher priority than VM-Exit (see Intel SDM's pseudocode * for VMXON). * * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't * force any of the relevant guest state. For a restricted guest, KVM * does force CR0.PE=1, but only to also force VM86 in order to emulate * Real Mode, and so there's no need to check CR0.PE manually. */ if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* * The CPL is checked for "not in VMX operation" and for "in VMX root", * and has higher priority than the VM-Fail due to being post-VMXON, * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits * from L2 to L1, i.e. there's no need to check for the vCPU being in * VMX non-root. * * Forwarding the VM-Exit unconditionally, i.e. without performing the * #UD checks (see above), is functionally ok because KVM doesn't allow * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are * missed by hardware due to shadowing CR0 and/or CR4. */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); /* * Invalid CR0/CR4 generates #GP. These checks are performed if and * only if the vCPU isn't already in VMX operation, i.e. effectively * have lower priority than the VM-Fail above. */ if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { kvm_inject_gp(vcpu, 0); return 1; } if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); return 1; } if (nested_vmx_get_vmptr(vcpu, &vmptr, &ret)) return ret; /* * SDM 3: 24.11.5 * The first 4 bytes of VMXON region contain the supported * VMCS revision identifier * * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case; * which replaces physical address width with 32 */ if (!page_address_valid(vcpu, vmptr)) return nested_vmx_failInvalid(vcpu); if (kvm_read_guest(vcpu->kvm, vmptr, &revision, sizeof(revision)) || revision != VMCS12_REVISION) return nested_vmx_failInvalid(vcpu); vmx->nested.vmxon_ptr = vmptr; ret = enter_vmx_operation(vcpu); if (ret) return ret; return nested_vmx_succeed(vcpu); } static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (vmx->nested.current_vmptr == INVALID_GPA) return; copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (enable_shadow_vmcs) { /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; /* Flush VMCS12 to guest memory */ kvm_vcpu_write_guest_page(vcpu, vmx->nested.current_vmptr >> PAGE_SHIFT, vmx->nested.cached_vmcs12, 0, VMCS12_SIZE); kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); vmx->nested.current_vmptr = INVALID_GPA; } /* Emulate the VMXOFF instruction */ static int handle_vmxoff(struct kvm_vcpu *vcpu) { if (!nested_vmx_check_permission(vcpu)) return 1; free_nested(vcpu); if (kvm_apic_has_pending_init_or_sipi(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); return nested_vmx_succeed(vcpu); } /* Emulate the VMCLEAR instruction */ static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 zero = 0; gpa_t vmptr; int r; if (!nested_vmx_check_permission(vcpu)) return 1; if (nested_vmx_get_vmptr(vcpu, &vmptr, &r)) return r; if (!page_address_valid(vcpu, vmptr)) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); /* * Silently ignore memory errors on VMCLEAR, Intel's pseudocode * for VMCLEAR includes a "ensure that data for VMCS referenced * by the operand is in memory" clause that guards writes to * memory, i.e. doing nothing for I/O is architecturally valid. * * FIXME: Suppress failures if and only if no memslot is found, * i.e. exit to userspace if __copy_to_user() fails. */ (void)kvm_vcpu_write_guest(vcpu, vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); } return nested_vmx_succeed(vcpu); } /* Emulate the VMLAUNCH instruction */ static int handle_vmlaunch(struct kvm_vcpu *vcpu) { return nested_vmx_run(vcpu, true); } /* Emulate the VMRESUME instruction */ static int handle_vmresume(struct kvm_vcpu *vcpu) { return nested_vmx_run(vcpu, false); } static int handle_vmread(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) : get_vmcs12(vcpu); unsigned long exit_qualification = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct x86_exception e; unsigned long field; u64 value; gva_t gva = 0; short offset; int len, r; if (!nested_vmx_check_permission(vcpu)) return 1; /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); if (!nested_vmx_is_evmptr12_valid(vmx)) { /* * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMREAD sets the ALU flags for VMfailInvalid. */ if (vmx->nested.current_vmptr == INVALID_GPA || (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); offset = get_vmcs12_field_offset(field); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* Read the field, zero-extended to a u64 value */ value = vmcs12_read_any(vmcs12, field, offset); } else { /* * Hyper-V TLFS (as of 6.0b) explicitly states, that while an * enlightened VMCS is active VMREAD/VMWRITE instructions are * unsupported. Unfortunately, certain versions of Windows 11 * don't comply with this requirement which is not enforced in * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a * workaround, as misbehaving guests will panic on VM-Fail. * Note, enlightened VMCS is incompatible with shadow VMCS so * all VMREADs from L2 should go to L1. */ if (WARN_ON_ONCE(is_guest_mode(vcpu))) return nested_vmx_failInvalid(vcpu); offset = evmcs_field_offset(field, NULL); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* Read the field, zero-extended to a u64 value */ value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset); } /* * Now copy part of this value to register or memory, as requested. * Note that the number of bits actually copied is 32 or 64 depending * on the guest's mode (32 or 64 bit), not on the given field's length. */ if (instr_info & BIT(10)) { kvm_register_write(vcpu, (((instr_info) >> 3) & 0xf), value); } else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, instr_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ r = kvm_write_guest_virt_system(vcpu, gva, &value, len, &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); } return nested_vmx_succeed(vcpu); } static bool is_shadow_field_rw(unsigned long field) { switch (field) { #define SHADOW_FIELD_RW(x, y) case x: #include "vmcs_shadow_fields.h" return true; default: break; } return false; } static bool is_shadow_field_ro(unsigned long field) { switch (field) { #define SHADOW_FIELD_RO(x, y) case x: #include "vmcs_shadow_fields.h" return true; default: break; } return false; } static int handle_vmwrite(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) : get_vmcs12(vcpu); unsigned long exit_qualification = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct x86_exception e; unsigned long field; short offset; gva_t gva; int len, r; /* * The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 * bit (value), and then copies only the appropriate number of * bits into the vmcs12 field. */ u64 value = 0; if (!nested_vmx_check_permission(vcpu)) return 1; /* * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMWRITE sets the ALU flags for VMfailInvalid. */ if (vmx->nested.current_vmptr == INVALID_GPA || (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); if (instr_info & BIT(10)) value = kvm_register_read(vcpu, (((instr_info) >> 3) & 0xf)); else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, instr_info, false, len, &gva)) return 1; r = kvm_read_guest_virt(vcpu, gva, &value, len, &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); } field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); offset = get_vmcs12_field_offset(field); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* * If the vCPU supports "VMWRITE to any supported field in the * VMCS," then the "read-only" fields are actually read/write. */ if (vmcs_field_readonly(field) && !nested_cpu_has_vmwrite_any_field(vcpu)) return nested_vmx_fail(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); /* * Ensure vmcs12 is up-to-date before any VMWRITE that dirties * vmcs12, else we may crush a field or consume a stale value. */ if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* * Some Intel CPUs intentionally drop the reserved bits of the AR byte * fields on VMWRITE. Emulate this behavior to ensure consistent KVM * behavior regardless of the underlying hardware, e.g. if an AR_BYTE * field is intercepted for VMWRITE but not VMREAD (in L1), then VMREAD * from L1 will return a different value than VMREAD from L2 (L1 sees * the stripped down value, L2 sees the full value as stored by KVM). */ if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES) value &= 0x1f0ff; vmcs12_write_any(vmcs12, field, offset, value); /* * Do not track vmcs12 dirty-state if in guest-mode as we actually * dirty shadow vmcs12 instead of vmcs12. Fields that can be updated * by L1 without a vmexit are always updated in the vmcs02, i.e. don't * "dirty" vmcs12, all others go down the prepare_vmcs02() slow path. */ if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) { /* * L1 can read these fields without exiting, ensure the * shadow VMCS is up-to-date. */ if (enable_shadow_vmcs && is_shadow_field_ro(field)) { preempt_disable(); vmcs_load(vmx->vmcs01.shadow_vmcs); __vmcs_writel(field, value); vmcs_clear(vmx->vmcs01.shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); preempt_enable(); } vmx->nested.dirty_vmcs12 = true; } return nested_vmx_succeed(vcpu); } static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) { vmx->nested.current_vmptr = vmptr; if (enable_shadow_vmcs) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, __pa(vmx->vmcs01.shadow_vmcs)); vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); gpa_t vmptr; int r; if (!nested_vmx_check_permission(vcpu)) return 1; if (nested_vmx_get_vmptr(vcpu, &vmptr, &r)) return r; if (!page_address_valid(vcpu, vmptr)) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ if (nested_vmx_is_evmptr12_valid(vmx)) return 1; if (vmx->nested.current_vmptr != vmptr) { struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; struct vmcs_hdr hdr; if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the * given physical address won't match the required * VMCS12_REVISION identifier. */ return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, offsetof(struct vmcs12, hdr), sizeof(hdr))) { return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } if (hdr.revision_id != VMCS12_REVISION || (hdr.shadow_vmcs && !nested_cpu_has_vmx_shadow_vmcs(vcpu))) { return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } nested_release_vmcs12(vcpu); /* * Load VMCS12 from guest memory since it is not already * cached. */ if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12, VMCS12_SIZE)) { return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } set_current_vmptr(vmx, vmptr); } return nested_vmx_succeed(vcpu); } /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { unsigned long exit_qual = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; gva_t gva; int r; if (!nested_vmx_check_permission(vcpu)) return 1; if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu)))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, sizeof(gpa_t), &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ r = kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, sizeof(gpa_t), &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); return nested_vmx_succeed(vcpu); } /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmx_instruction_info, types; unsigned long type, roots_to_free; struct kvm_mmu *mmu; gva_t gva; struct x86_exception e; struct { u64 eptp, gpa; } operand; int i, r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || !(vmx->nested.msrs.ept_caps & VMX_EPT_INVEPT_BIT)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } if (!nested_vmx_check_permission(vcpu)) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; if (type >= 32 || !(types & (1 << type))) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); /* According to the Intel VMX instruction reference, the memory * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); /* * Nested EPT roots are always held through guest_mmu, * not root_mmu. */ mmu = &vcpu->arch.guest_mmu; switch (type) { case VMX_EPT_EXTENT_CONTEXT: if (!nested_vmx_check_eptp(vcpu, operand.eptp)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); roots_to_free = 0; if (nested_ept_root_matches(mmu->root.hpa, mmu->root.pgd, operand.eptp)) roots_to_free |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (nested_ept_root_matches(mmu->prev_roots[i].hpa, mmu->prev_roots[i].pgd, operand.eptp)) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } break; case VMX_EPT_EXTENT_GLOBAL: roots_to_free = KVM_MMU_ROOTS_ALL; break; default: BUG(); break; } if (roots_to_free) kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); return nested_vmx_succeed(vcpu); } static int handle_invvpid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmx_instruction_info; unsigned long type, types; gva_t gva; struct x86_exception e; struct { u64 vpid; u64 gla; } operand; u16 vpid02; int r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || !(vmx->nested.msrs.vpid_caps & VMX_VPID_INVVPID_BIT)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } if (!nested_vmx_check_permission(vcpu)) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.vpid_caps & VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; if (type >= 32 || !(types & (1 << type))) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); /* according to the intel vmx instruction reference, the memory * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); if (operand.vpid >> 16) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); /* * Always flush the effective vpid02, i.e. never flush the current VPID * and never explicitly flush vpid01. INVVPID targets a VPID, not a * VMCS, and so whether or not the current vmcs12 has VPID enabled is * irrelevant (and there may not be a loaded vmcs12). */ vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: /* * LAM doesn't apply to addresses that are inputs to TLB * invalidation. */ if (!operand.vpid || is_noncanonical_invlpg_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_vcpu_addr(vpid02, operand.gla); break; case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: if (!operand.vpid) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_context(vpid02); break; case VMX_VPID_EXTENT_ALL_CONTEXT: vpid_sync_context(vpid02); break; default: WARN_ON_ONCE(1); return kvm_skip_emulated_instruction(vcpu); } /* * Sync the shadow page tables if EPT is disabled, L1 is invalidating * linear mappings for L2 (tagged with L2's VPID). Free all guest * roots as VPIDs are not tracked in the MMU role. * * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share * an MMU when EPT is disabled. * * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR. */ if (!enable_ept) kvm_mmu_free_guest_mode_roots(vcpu->kvm, &vcpu->arch.root_mmu); return nested_vmx_succeed(vcpu); } static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { u32 index = kvm_rcx_read(vcpu); u64 new_eptp; if (WARN_ON_ONCE(!nested_cpu_has_ept(vmcs12))) return 1; if (index >= VMFUNC_EPTP_ENTRIES) return 1; if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT, &new_eptp, index * 8, 8)) return 1; /* * If the (L2) guest does a vmfunc to the currently * active ept pointer, we don't have to do anything else */ if (vmcs12->ept_pointer != new_eptp) { if (!nested_vmx_check_eptp(vcpu, new_eptp)) return 1; vmcs12->ept_pointer = new_eptp; nested_ept_new_eptp(vcpu); if (!nested_cpu_has_vpid(vmcs12)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } return 0; } static int handle_vmfunc(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; u32 function = kvm_rax_read(vcpu); /* * VMFUNC should never execute cleanly while L1 is active; KVM supports * VMFUNC for nested VMs, but not for L1. */ if (WARN_ON_ONCE(!is_guest_mode(vcpu))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } vmcs12 = get_vmcs12(vcpu); /* * #UD on out-of-bounds function has priority over VM-Exit, and VMFUNC * is enabled in vmcs02 if and only if it's enabled in vmcs12. */ if (WARN_ON_ONCE((function > 63) || !nested_cpu_has_vmfunc(vmcs12))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } if (!(vmcs12->vm_function_control & BIT_ULL(function))) goto fail; switch (function) { case 0: if (nested_vmx_eptp_switching(vcpu, vmcs12)) goto fail; break; default: goto fail; } return kvm_skip_emulated_instruction(vcpu); fail: /* * This is effectively a reflected VM-Exit, as opposed to a synthesized * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode * EXIT_REASON_VMFUNC as the exit reason. */ nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full, vmx_get_intr_info(vcpu), vmx_get_exit_qual(vcpu)); return 1; } /* * Return true if an IO instruction with the specified port and size should cause * a VM-exit into L1. */ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, int size) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; u8 b; last_bitmap = INVALID_GPA; b = -1; while (size > 0) { if (port < 0x8000) bitmap = vmcs12->io_bitmap_a; else if (port < 0x10000) bitmap = vmcs12->io_bitmap_b; else return true; bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1)) return true; if (b & (1 << (port & 7))) return true; port++; size--; last_bitmap = bitmap; } return false; } static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { unsigned long exit_qualification; unsigned short port; int size; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); exit_qualification = vmx_get_exit_qual(vcpu); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; return nested_vmx_check_io_bitmaps(vcpu, port, size); } /* * Return 1 if we should exit from L2 to L1 to handle an MSR access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed * disinterest in the current event (read or write a specific MSR) by using an * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. */ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, union vmx_exit_reason exit_reason) { u32 msr_index; gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return true; if (exit_reason.basic == EXIT_REASON_MSR_READ_IMM || exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM) msr_index = vmx_get_exit_qual(vcpu); else msr_index = kvm_rcx_read(vcpu); /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, * for the four combinations of read/write and low/high MSR numbers. * First we need to figure out which of the four to use: */ bitmap = vmcs12->msr_bitmap; if (exit_reason.basic == EXIT_REASON_MSR_WRITE || exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM) bitmap += 2048; if (msr_index >= 0xc0000000) { msr_index -= 0xc0000000; bitmap += 1024; } /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1)) return true; return 1 & (b >> (msr_index & 7)); } else return true; /* let L1 handle the wrong parameter */ } /* * Return 1 if we should exit from L2 to L1 to handle a CR access exit, * rather than handle it ourselves in L0. I.e., check if L1 wanted to * intercept (via guest_host_mask etc.) the current event. */ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int cr = exit_qualification & 15; int reg; unsigned long val; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ reg = (exit_qualification >> 8) & 15; val = kvm_register_read(vcpu, reg); switch (cr) { case 0: if (vmcs12->cr0_guest_host_mask & (val ^ vmcs12->cr0_read_shadow)) return true; break; case 3: if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) return true; break; case 4: if (vmcs12->cr4_guest_host_mask & (vmcs12->cr4_read_shadow ^ val)) return true; break; case 8: if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING)) return true; break; } break; case 2: /* clts */ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) && (vmcs12->cr0_read_shadow & X86_CR0_TS)) return true; break; case 1: /* mov from cr */ switch (cr) { case 3: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR3_STORE_EXITING) return true; break; case 8: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR8_STORE_EXITING) return true; break; } break; case 3: /* lmsw */ /* * lmsw can change bits 1..3 of cr0, and only set bit 0 of * cr0. Other attempted changes are ignored, with no exit. */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) return true; if ((vmcs12->cr0_guest_host_mask & 0x1) && !(vmcs12->cr0_read_shadow & 0x1) && (val & 0x1)) return true; break; } return false; } static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { u32 encls_leaf; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING)) return false; encls_leaf = kvm_rax_read(vcpu); if (encls_leaf > 62) encls_leaf = 63; return vmcs12->encls_exiting_bitmap & BIT_ULL(encls_leaf); } static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, gpa_t bitmap) { u32 vmx_instruction_info; unsigned long field; u8 b; if (!nested_cpu_has_shadow_vmcs(vmcs12)) return true; /* Decode instruction info and find the field to access */ vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* Out-of-range fields always cause a VM exit from L2 to L1 */ if (field >> 15) return true; if (kvm_vcpu_read_guest(vcpu, bitmap + field/8, &b, 1)) return true; return 1 & (b >> (field & 7)); } static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) { u32 entry_intr_info = vmcs12->vm_entry_intr_info_field; if (nested_cpu_has_mtf(vmcs12)) return true; /* * An MTF VM-exit may be injected into the guest by setting the * interruption-type to 7 (other event) and the vector field to 0. Such * is the case regardless of the 'monitor trap flag' VM-execution * control. */ return entry_intr_info == (INTR_INFO_VALID_MASK | INTR_TYPE_OTHER_EVENT); } /* * Return true if L0 wants to handle an exit from L2 regardless of whether or not * L1 wants the exit. Only call this when in is_guest_mode (L2). */ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, union vmx_exit_reason exit_reason) { u32 intr_info; switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) return vcpu->arch.apf.host_apf_flags || vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) return true; else if (is_breakpoint(intr_info) && vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return true; else if (is_alignment_check(intr_info) && !vmx_guest_inject_ac(vcpu)) return true; else if (is_ve_fault(intr_info)) return true; return false; case EXIT_REASON_EXTERNAL_INTERRUPT: return true; case EXIT_REASON_MCE_DURING_VMENTRY: return true; case EXIT_REASON_EPT_VIOLATION: /* * L0 always deals with the EPT violation. If nested EPT is * used, and the nested mmu code discovers that the address is * missing in the guest EPT table (EPT12), the EPT violation * will be injected with nested_ept_inject_page_fault() */ return true; case EXIT_REASON_EPT_MISCONFIG: /* * L2 never uses directly L1's EPT, but rather L0's own EPT * table (shadow on EPT) or a merged EPT table that L0 built * (EPT on EPT). So any problems with the structure of the * table is L0's fault. */ return true; case EXIT_REASON_PREEMPTION_TIMER: return true; case EXIT_REASON_PML_FULL: /* * PML is emulated for an L1 VMM and should never be enabled in * vmcs02, always "handle" PML_FULL by exiting to userspace. */ return true; case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; case EXIT_REASON_BUS_LOCK: /* * At present, bus lock VM exit is never exposed to L1. * Handle L2's bus locks in L0 directly. */ return true; #ifdef CONFIG_KVM_HYPERV case EXIT_REASON_VMCALL: /* Hyper-V L2 TLB flush hypercall is handled by L0 */ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && nested_evmcs_l2_tlb_flush_enabled(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu); #endif default: break; } return false; } /* * Return 1 if L1 wants to intercept an exit from L2. Only call this when in * is_guest_mode (L2). */ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, union vmx_exit_reason exit_reason) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 intr_info; switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) return true; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: return nested_exit_on_intr(vcpu); case EXIT_REASON_TRIPLE_FAULT: return true; case EXIT_REASON_INTERRUPT_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING); case EXIT_REASON_NMI_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING); case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); case EXIT_REASON_INVD: return true; case EXIT_REASON_INVLPG: return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); case EXIT_REASON_RDRAND: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND_EXITING); case EXIT_REASON_RDSEED: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING); case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMREAD: return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12, vmcs12->vmread_bitmap); case EXIT_REASON_VMWRITE: return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12, vmcs12->vmwrite_bitmap); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: case EXIT_REASON_VMPTRST: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! */ return true; case EXIT_REASON_CR_ACCESS: return nested_vmx_exit_handled_cr(vcpu, vmcs12); case EXIT_REASON_DR_ACCESS: return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING); case EXIT_REASON_IO_INSTRUCTION: return nested_vmx_exit_handled_io(vcpu, vmcs12); case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC); case EXIT_REASON_MSR_READ: case EXIT_REASON_MSR_WRITE: case EXIT_REASON_MSR_READ_IMM: case EXIT_REASON_MSR_WRITE_IMM: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_TRAP_FLAG: return nested_vmx_exit_handled_mtf(vmcs12); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING) || nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: return true; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: /* * The controls for "virtualize APIC accesses," "APIC- * register virtualization," and "virtual-interrupt * delivery" only come from vmcs12. */ return true; case EXIT_REASON_INVPCID: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) && nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: return true; case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: /* * Always forward XSAVES/XRSTORS to L1 as KVM doesn't utilize * XSS-bitmap, and always loads vmcs02 with vmcs12's XSS-bitmap * verbatim, i.e. any exit is due to L1's bitmap. WARN if * XSAVES isn't enabled, as the CPU is supposed to inject #UD * in that case, before consulting the XSS-bitmap. */ WARN_ON_ONCE(!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES)); return true; case EXIT_REASON_UMWAIT: case EXIT_REASON_TPAUSE: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE); case EXIT_REASON_ENCLS: return nested_vmx_exit_handled_encls(vcpu, vmcs12); case EXIT_REASON_NOTIFY: /* Notify VM exit is not exposed to L1 */ return false; default: return true; } } /* * Conditionally reflect a VM-Exit into L1. Returns %true if the VM-Exit was * reflected into L1. */ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); union vmx_exit_reason exit_reason = vmx->vt.exit_reason; unsigned long exit_qual; u32 exit_intr_info; WARN_ON_ONCE(vmx->nested.nested_run_pending); /* * Late nested VM-Fail shares the same flow as nested VM-Exit since KVM * has already loaded L2's state. */ if (unlikely(vmx->fail)) { trace_kvm_nested_vmenter_failed( "hardware VM-instruction error: ", vmcs_read32(VM_INSTRUCTION_ERROR)); exit_intr_info = 0; exit_qual = 0; goto reflect_vmexit; } trace_kvm_nested_vmexit(vcpu, KVM_ISA_VMX); /* If L0 (KVM) wants the exit, it trumps L1's desires. */ if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) return false; /* If L1 doesn't want the exit, handle it in L0. */ if (!nested_vmx_l1_wants_exit(vcpu, exit_reason)) return false; /* * vmcs.VM_EXIT_INTR_INFO is only valid for EXCEPTION_NMI exits. For * EXTERNAL_INTERRUPT, the value for vmcs12->vm_exit_intr_info would * need to be synthesized by querying the in-kernel LAPIC, but external * interrupts are never reflected to L1 so it's a non-issue. */ exit_intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(exit_intr_info)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); vmcs12->vm_exit_intr_error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); } exit_qual = vmx_get_exit_qual(vcpu); reflect_vmexit: nested_vmx_vmexit(vcpu, exit_reason.full, exit_intr_info, exit_qual); return true; } static int vmx_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) { struct vcpu_vmx *vmx; struct vmcs12 *vmcs12; struct kvm_nested_state kvm_state = { .flags = 0, .format = KVM_STATE_NESTED_FORMAT_VMX, .size = sizeof(kvm_state), .hdr.vmx.flags = 0, .hdr.vmx.vmxon_pa = INVALID_GPA, .hdr.vmx.vmcs12_pa = INVALID_GPA, .hdr.vmx.preemption_timer_deadline = 0, }; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; if (!vcpu) return kvm_state.size + sizeof(*user_vmx_nested_state); vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; if (vmx_has_valid_vmcs12(vcpu)) { kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ if (nested_vmx_is_evmptr12_set(vmx)) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12); } if (vmx->nested.smm.vmxon) kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON; if (vmx->nested.smm.guest_mode) kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE; if (is_guest_mode(vcpu)) { kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE; if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; if (vmx->nested.mtf_pending) kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; if (nested_cpu_has_preemption_timer(vmcs12) && vmx->nested.has_preemption_timer_deadline) { kvm_state.hdr.vmx.flags |= KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE; kvm_state.hdr.vmx.preemption_timer_deadline = vmx->nested.preemption_timer_deadline; } } } if (user_data_size < kvm_state.size) goto out; if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state))) return -EFAULT; if (!vmx_has_valid_vmcs12(vcpu)) goto out; /* * When running L2, the authoritative vmcs12 state is in the * vmcs02. When running L1, the authoritative vmcs12 state is * in the shadow or enlightened vmcs linked to vmcs01, unless * need_vmcs12_to_shadow_sync is set, in which case, the authoritative * vmcs12 state is in the vmcs12 already. */ if (is_guest_mode(vcpu)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { if (nested_vmx_is_evmptr12_valid(vmx)) /* * L1 hypervisor is not obliged to keep eVMCS * clean fields data always up-to-date while * not in guest mode, 'hv_clean_fields' is only * supposed to be actual upon vmentry so we need * to ignore it here and do full copy. */ copy_enlightened_to_vmcs12(vmx, 0); else if (enable_shadow_vmcs) copy_shadow_to_vmcs12(vmx); } } BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE); BUILD_BUG_ON(sizeof(user_vmx_nested_state->shadow_vmcs12) < VMCS12_SIZE); /* * Copy over the full allocated size of vmcs12 rather than just the size * of the struct. */ if (copy_to_user(user_vmx_nested_state->vmcs12, vmcs12, VMCS12_SIZE)) return -EFAULT; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) { if (copy_to_user(user_vmx_nested_state->shadow_vmcs12, get_shadow_vmcs12(vcpu), VMCS12_SIZE)) return -EFAULT; } out: return kvm_state.size; } void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.nested_run_pending = 0; nested_vmx_vmexit(vcpu, -1, 0, 0); } free_nested(vcpu); } static int vmx_set_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; enum vm_entry_failure_code ignored; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; int ret; if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX) return -EINVAL; if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) { if (kvm_state->hdr.vmx.smm.flags) return -EINVAL; if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) return -EINVAL; /* * KVM_STATE_NESTED_EVMCS used to signal that KVM should * enable eVMCS capability on vCPU. However, since then * code was changed such that flag signals vmcs12 should * be copied into eVMCS in guest memory. * * To preserve backwards compatibility, allow user * to set this flag even when there is no VMXON region. */ if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) return -EINVAL; } if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) return -EINVAL; if (kvm_state->hdr.vmx.smm.flags & ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) return -EINVAL; /* * SMM temporarily disables VMX, so we cannot be in guest mode, * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags * must be zero. */ if (is_smm(vcpu) ? (kvm_state->flags & (KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING)) : kvm_state->hdr.vmx.smm.flags) return -EINVAL; if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && !(kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) || !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; vmx_leave_nested(vcpu); if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) return 0; vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa; ret = enter_vmx_operation(vcpu); if (ret) return ret; /* Empty 'VMXON' state is permitted if no VMCS loaded */ if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) { /* See vmx_has_valid_vmcs12. */ if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) || (kvm_state->flags & KVM_STATE_NESTED_EVMCS) || (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA)) return -EINVAL; else return 0; } if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) { if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa || !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa)) return -EINVAL; set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); #ifdef CONFIG_KVM_HYPERV } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* * nested_vmx_handle_enlightened_vmptrld() cannot be called * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be * restored yet. EVMCS will be mapped from * nested_get_vmcs12_pages(). */ vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); #endif } else { return -EINVAL; } if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) { vmx->nested.smm.vmxon = true; vmx->nested.vmxon = false; if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) vmx->nested.smm.guest_mode = true; } vmcs12 = get_vmcs12(vcpu); if (copy_from_user(vmcs12, user_vmx_nested_state->vmcs12, sizeof(*vmcs12))) return -EFAULT; if (vmcs12->hdr.revision_id != VMCS12_REVISION) return -EINVAL; if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) return 0; vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); vmx->nested.mtf_pending = !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); if (kvm_state->size < sizeof(*kvm_state) + sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12)) goto error_guest_mode; if (copy_from_user(shadow_vmcs12, user_vmx_nested_state->shadow_vmcs12, sizeof(*shadow_vmcs12))) { ret = -EFAULT; goto error_guest_mode; } if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || !shadow_vmcs12->hdr.shadow_vmcs) goto error_guest_mode; } vmx->nested.has_preemption_timer_deadline = false; if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) { vmx->nested.has_preemption_timer_deadline = true; vmx->nested.preemption_timer_deadline = kvm_state->hdr.vmx.preemption_timer_deadline; } if (nested_vmx_check_controls(vcpu, vmcs12) || nested_vmx_check_host_state(vcpu, vmcs12) || nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; if (vmx->nested.mtf_pending) kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; error_guest_mode: vmx->nested.nested_run_pending = 0; return ret; } void nested_vmx_set_vmcs_shadowing_bitmap(void) { if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } } /* * Indexing into the vmcs12 uses the VMCS encoding rotated left by 6. Undo * that madness to get the encoding for comparison. */ #define VMCS12_IDX_TO_ENC(idx) ((u16)(((u16)(idx) >> 6) | ((u16)(idx) << 10))) static u64 nested_vmx_calc_vmcs_enum_msr(void) { /* * Note these are the so called "index" of the VMCS field encoding, not * the index into vmcs12. */ unsigned int max_idx, idx; int i; /* * For better or worse, KVM allows VMREAD/VMWRITE to all fields in * vmcs12, regardless of whether or not the associated feature is * exposed to L1. Simply find the field with the highest index. */ max_idx = 0; for (i = 0; i < nr_vmcs12_fields; i++) { /* The vmcs12 table is very, very sparsely populated. */ if (!vmcs12_field_offsets[i]) continue; idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); if (idx > max_idx) max_idx = idx; } return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; } static void nested_vmx_setup_pinbased_ctls(struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl; msrs->pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; } static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl; msrs->exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_CET_STATE; msrs->exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && !kvm_cpu_cap_has(X86_FEATURE_IBT)) msrs->exit_ctls_high &= ~VM_EXIT_LOAD_CET_STATE; /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; } static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl; msrs->entry_ctls_high &= #ifdef CONFIG_X86_64 VM_ENTRY_IA32E_MODE | #endif VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS | VM_ENTRY_LOAD_CET_STATE; msrs->entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && !kvm_cpu_cap_has(X86_FEATURE_IBT)) msrs->entry_ctls_high &= ~VM_ENTRY_LOAD_CET_STATE; /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; } static void nested_vmx_setup_cpubased_ctls(struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl; msrs->procbased_ctls_high &= CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | #ifdef CONFIG_X86_64 CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the * hardware. For example, L1 can specify an MSR bitmap - and we * can use it to avoid exits to L1 - even when L0 runs L2 * without MSR bitmaps. */ msrs->procbased_ctls_high |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | CPU_BASED_USE_MSR_BITMAPS; /* We support free control of CR3 access interception. */ msrs->procbased_ctls_low &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); } static void nested_vmx_setup_secondary_ctls(u32 ept_caps, struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | SECONDARY_EXEC_ENABLE_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_ENABLE_XSAVES | SECONDARY_EXEC_TSC_SCALING | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware * doesn't support it. */ msrs->secondary_ctls_high |= SECONDARY_EXEC_SHADOW_VMCS; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ msrs->secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPT_PAGE_WALK_5_BIT | VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT | VMX_EPT_EXECUTE_ONLY_BIT; msrs->ept_caps &= ept_caps; msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_1GB_PAGE_BIT; if (enable_ept_ad_bits) { msrs->secondary_ctls_high |= SECONDARY_EXEC_ENABLE_PML; msrs->ept_caps |= VMX_EPT_AD_BIT; } /* * Advertise EPTP switching irrespective of hardware support, * KVM emulates it in software so long as VMFUNC is supported. */ if (cpu_has_vmx_vmfunc()) msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING; } /* * Old versions of KVM use the single-context version without * checking for support, so declare that it is supported even * though it is treated as global context. The alternative is * not failing the single-context invvpid, and it is worse. */ if (enable_vpid) { msrs->secondary_ctls_high |= SECONDARY_EXEC_ENABLE_VPID; msrs->vpid_caps = VMX_VPID_INVVPID_BIT | VMX_VPID_EXTENT_SUPPORTED_MASK; } if (enable_unrestricted_guest) msrs->secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; if (flexpriority_enabled) msrs->secondary_ctls_high |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (enable_sgx) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; } static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, struct nested_vmx_msrs *msrs) { msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; msrs->misc_high = 0; } static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) { /* * This MSR reports some information about VMX support. We * should return information about the VMX we emulate for the * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, X86_MEMTYPE_WB); msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; if (cpu_has_vmx_basic_no_hw_errcode_cc()) msrs->basic |= VMX_BASIC_NO_HW_ERROR_CODE_CC; } static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) { /* * These MSRs specify bits which the guest must keep fixed on * while L1 is in VMXON mode (in L1's root mode, or running an L2). * We picked the standard core2 setting. */ #define VMXON_CR0_ALWAYSON (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE) #define VMXON_CR4_ALWAYSON X86_CR4_VMXE msrs->cr0_fixed0 = VMXON_CR0_ALWAYSON; msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON; /* These MSRs specify bits which the guest must keep fixed off. */ rdmsrq(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); rdmsrq(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); if (vmx_umip_emulated()) msrs->cr4_fixed1 |= X86_CR4_UMIP; } /* * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be * returned for the various VMX controls MSRs when nested VMX is enabled. * The same values should also be used to verify that vmcs12 control fields are * valid during nested entry from L1 to L2. * Each of these control msrs has a low and high 32-bit half: A low bit is on * if the corresponding bit in the (32-bit) control field *must* be on, and a * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) { struct nested_vmx_msrs *msrs = &vmcs_conf->nested; /* * Note that as a general rule, the high half of the MSRs (bits in * the control fields which may be 1) should be initialized by the * intersection of the underlying hardware's MSR (i.e., features which * can be supported) and the list of features we want to expose - * because they are known to be properly supported in our code. * Also, usually, the low half of the MSRs (bits which must be 1) can * be set to 0, meaning that L1 may turn off any of these bits. The * reason is that if one of these bits is necessary, it will appear * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control * fields of vmcs01 and vmcs02, will turn these bits off - and * nested_vmx_l1_wants_exit() will not pass related exits to L1. * These rules have exceptions below. */ nested_vmx_setup_pinbased_ctls(vmcs_conf, msrs); nested_vmx_setup_exit_ctls(vmcs_conf, msrs); nested_vmx_setup_entry_ctls(vmcs_conf, msrs); nested_vmx_setup_cpubased_ctls(vmcs_conf, msrs); nested_vmx_setup_secondary_ctls(ept_caps, vmcs_conf, msrs); nested_vmx_setup_misc_data(vmcs_conf, msrs); nested_vmx_setup_basic(msrs); nested_vmx_setup_cr_fixed(msrs); msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } void nested_vmx_hardware_unsetup(void) { int i; if (enable_shadow_vmcs) { for (i = 0; i < VMX_BITMAP_NR; i++) free_page((unsigned long)vmx_bitmap[i]); } } __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { for (i = 0; i < VMX_BITMAP_NR; i++) { /* * The vmx_bitmap is not tied to a VM and so should * not be charged to a memcg. */ vmx_bitmap[i] = (unsigned long *) __get_free_page(GFP_KERNEL); if (!vmx_bitmap[i]) { nested_vmx_hardware_unsetup(); return -ENOMEM; } } init_vmcs_shadow_fields(); } exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear; exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch; exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld; exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst; exit_handlers[EXIT_REASON_VMREAD] = handle_vmread; exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume; exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite; exit_handlers[EXIT_REASON_VMOFF] = handle_vmxoff; exit_handlers[EXIT_REASON_VMON] = handle_vmxon; exit_handlers[EXIT_REASON_INVEPT] = handle_invept; exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; return 0; } struct kvm_x86_nested_ops vmx_nested_ops = { .leave_nested = vmx_leave_nested, .is_exception_vmexit = nested_vmx_is_exception_vmexit, .check_events = vmx_check_nested_events, .has_events = vmx_has_nested_events, .triple_fault = nested_vmx_triple_fault, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, #ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, #endif }; |
| 92 93 93 93 87 93 6 6 6 87 87 87 87 111 110 12 12 10 99 99 99 99 99 99 99 99 99 99 99 4 4 4 4 4 4 4 4 4 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 87 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 99 87 87 87 87 87 87 87 87 87 87 86 87 87 87 87 87 86 87 87 87 99 99 99 99 99 99 99 99 99 99 99 99 99 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006 Thomas Gleixner * * This file contains driver APIs to the irq subsystem. */ #define pr_fmt(fmt) "genirq: " fmt #include <linux/irq.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/random.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> #include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> #include "internals.h" #if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT) DEFINE_STATIC_KEY_FALSE(force_irqthreads_key); static int __init setup_forced_irqthreads(char *arg) { static_branch_enable(&force_irqthreads_key); return 0; } early_param("threadirqs", setup_forced_irqthreads); #endif static int __irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *state); static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip) { struct irq_data *irqd = irq_desc_get_irq_data(desc); bool inprogress; do { /* * Wait until we're out of the critical section. This might * give the wrong answer due to the lack of memory barriers. */ while (irqd_irq_inprogress(&desc->irq_data)) cpu_relax(); /* Ok, that indicated we're done: double-check carefully. */ guard(raw_spinlock_irqsave)(&desc->lock); inprogress = irqd_irq_inprogress(&desc->irq_data); /* * If requested and supported, check at the chip whether it * is in flight at the hardware level, i.e. already pending * in a CPU and waiting for service and acknowledge. */ if (!inprogress && sync_chip) { /* * Ignore the return code. inprogress is only updated * when the chip supports it. */ __irq_get_irqchip_state(irqd, IRQCHIP_STATE_ACTIVE, &inprogress); } /* Oops, that failed? */ } while (inprogress); } /** * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) * @irq: interrupt number to wait for * * This function waits for any pending hard IRQ handlers for this interrupt * to complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. It does not take * associated threaded handlers into account. * * Do not use this for shutdown scenarios where you must be sure that all * parts (hardirq and threaded handler) have completed. * * Returns: false if a threaded handler is active. * * This function may be called - with care - from IRQ context. * * It does not check whether there is an interrupt in flight at the * hardware level, but not serviced yet, as this might deadlock when called * with interrupts disabled and the target CPU of the interrupt is the * current CPU. */ bool synchronize_hardirq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { __synchronize_hardirq(desc, false); return !atomic_read(&desc->threads_active); } return true; } EXPORT_SYMBOL(synchronize_hardirq); static void __synchronize_irq(struct irq_desc *desc) { __synchronize_hardirq(desc, true); /* * We made sure that no hardirq handler is running. Now verify that no * threaded handlers are active. */ wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active)); } /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for * * This function waits for any pending IRQ handlers for this interrupt to * complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. * * Can only be called from preemptible code as it might sleep when * an interrupt thread is associated to @irq. * * It optionally makes sure (when the irq chip supports that method) * that the interrupt is not pending in any CPU and waiting for * service. */ void synchronize_irq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (desc) __synchronize_irq(desc); } EXPORT_SYMBOL(synchronize_irq); #ifdef CONFIG_SMP cpumask_var_t irq_default_affinity; static bool __irq_can_set_affinity(struct irq_desc *desc) { if (!desc || !irqd_can_balance(&desc->irq_data) || !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity) return false; return true; } /** * irq_can_set_affinity - Check if the affinity of a given irq can be set * @irq: Interrupt to check * */ int irq_can_set_affinity(unsigned int irq) { return __irq_can_set_affinity(irq_to_desc(irq)); } /** * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space * @irq: Interrupt to check * * Like irq_can_set_affinity() above, but additionally checks for the * AFFINITY_MANAGED flag. */ bool irq_can_set_affinity_usr(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); return __irq_can_set_affinity(desc) && !irqd_affinity_is_managed(&desc->irq_data); } /** * irq_set_thread_affinity - Notify irq threads to adjust affinity * @desc: irq descriptor which has affinity changed * * Just set IRQTF_AFFINITY and delegate the affinity setting to the * interrupt thread itself. We can not call set_cpus_allowed_ptr() here as * we hold desc->lock and this code can be called from hard interrupt * context. */ static void irq_set_thread_affinity(struct irq_desc *desc) { struct irqaction *action; for_each_action_of_desc(desc, action) { if (action->thread) { set_bit(IRQTF_AFFINITY, &action->thread_flags); wake_up_process(action->thread); } if (action->secondary && action->secondary->thread) { set_bit(IRQTF_AFFINITY, &action->secondary->thread_flags); wake_up_process(action->secondary->thread); } } } #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); if (!cpumask_empty(m)) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); } #else static inline void irq_validate_effective_affinity(struct irq_data *data) { } #endif static DEFINE_PER_CPU(struct cpumask, __tmp_mask); int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct cpumask *tmp_mask = this_cpu_ptr(&__tmp_mask); struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); const struct cpumask *prog_mask; int ret; if (!chip || !chip->irq_set_affinity) return -EINVAL; /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with * a housekeeping CPU. If so, then remove the isolated CPUs from * the mask and just keep the housekeeping CPU(s). This prevents * the affinity setter from routing the interrupt to an isolated * CPU to avoid that I/O submitted from a housekeeping CPU causes * interrupts on an isolated one. * * If the masks do not intersect or include online CPU(s) then * keep the requested mask. The isolated target CPUs are only * receiving interrupts when the I/O operation was submitted * directly from them. * * If all housekeeping CPUs in the affinity mask are offline, the * interrupt will be migrated by the CPU hotplug code once a * housekeeping CPU which belongs to the affinity mask comes * online. */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); cpumask_and(tmp_mask, mask, hk_mask); if (!cpumask_intersects(tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = tmp_mask; } else { prog_mask = mask; } /* * Make sure we only provide online CPUs to the irqchip, * unless we are being asked to force the affinity (in which * case we do as we are told). */ cpumask_and(tmp_mask, prog_mask, cpu_online_mask); if (!force && !cpumask_empty(tmp_mask)) ret = chip->irq_set_affinity(data, tmp_mask, force); else if (force) ret = chip->irq_set_affinity(data, mask, force); else ret = -EINVAL; switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); fallthrough; case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } return ret; } #ifdef CONFIG_GENERIC_PENDING_IRQ static inline int irq_set_affinity_pending(struct irq_data *data, const struct cpumask *dest) { struct irq_desc *desc = irq_data_to_desc(data); irqd_set_move_pending(data); irq_copy_pending(desc, dest); return 0; } #else static inline int irq_set_affinity_pending(struct irq_data *data, const struct cpumask *dest) { return -EBUSY; } #endif static int irq_try_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force) { int ret = irq_do_set_affinity(data, dest, force); /* * In case that the underlying vector management is busy and the * architecture supports the generic pending mechanism then utilize * this to avoid returning an error to user space. */ if (ret == -EBUSY && !force) ret = irq_set_affinity_pending(data, dest); return ret; } static bool irq_set_affinity_deactivated(struct irq_data *data, const struct cpumask *mask) { struct irq_desc *desc = irq_data_to_desc(data); /* * Handle irq chips which can handle affinity only in activated * state correctly * * If the interrupt is not yet activated, just store the affinity * mask and do not call the chip driver at all. On activation the * driver has to make sure anyway that the interrupt is in a * usable state so startup works. */ if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data) || !irqd_affinity_on_activate(data)) return false; cpumask_copy(desc->irq_common_data.affinity, mask); irq_data_update_effective_affinity(data, mask); irqd_set(data, IRQD_AFFINITY_SET); return true; } int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_chip *chip = irq_data_get_irq_chip(data); struct irq_desc *desc = irq_data_to_desc(data); int ret = 0; if (!chip || !chip->irq_set_affinity) return -EINVAL; if (irq_set_affinity_deactivated(data, mask)) return 0; if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { ret = irq_try_set_affinity(data, mask, force); } else { irqd_set_move_pending(data); irq_copy_pending(desc, mask); } if (desc->affinity_notify) { kref_get(&desc->affinity_notify->kref); if (!schedule_work(&desc->affinity_notify->work)) { /* Work was already scheduled, drop our extra ref */ kref_put(&desc->affinity_notify->kref, desc->affinity_notify->release); } } irqd_set(data, IRQD_AFFINITY_SET); return ret; } /** * irq_update_affinity_desc - Update affinity management for an interrupt * @irq: The interrupt number to update * @affinity: Pointer to the affinity descriptor * * This interface can be used to configure the affinity management of * interrupts which have been allocated already. * * There are certain limitations on when it may be used - attempts to use it * for when the kernel is configured for generic IRQ reservation mode (in * config GENERIC_IRQ_RESERVATION_MODE) will fail, as it may conflict with * managed/non-managed interrupt accounting. In addition, attempts to use it on * an interrupt which is already started or which has already been configured * as managed will also fail, as these mean invalid init state or double init. */ int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity) { /* * Supporting this with the reservation scheme used by x86 needs * some more thought. Fail it for now. */ if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) return -EOPNOTSUPP; scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; bool activated; /* Requires the interrupt to be shut down */ if (irqd_is_started(&desc->irq_data)) return -EBUSY; /* Interrupts which are already managed cannot be modified */ if (irqd_affinity_is_managed(&desc->irq_data)) return -EBUSY; /* * Deactivate the interrupt. That's required to undo * anything an earlier activation has established. */ activated = irqd_is_activated(&desc->irq_data); if (activated) irq_domain_deactivate_irq(&desc->irq_data); if (affinity->is_managed) { irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED); irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN); } cpumask_copy(desc->irq_common_data.affinity, &affinity->mask); /* Restore the activation state */ if (activated) irq_domain_activate_irq(&desc->irq_data, false); return 0; } return -EINVAL; } static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) { struct irq_desc *desc = irq_to_desc(irq); if (!desc) return -EINVAL; guard(raw_spinlock_irqsave)(&desc->lock); return irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); } /** * irq_set_affinity - Set the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Fails if cpumask does not contain an online CPU */ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, false); } EXPORT_SYMBOL_GPL(irq_set_affinity); /** * irq_force_affinity - Force the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Same as irq_set_affinity, but without checking the mask against * online cpus. * * Solely for low level cpu hotplug code, where we need to make per * cpu interrupts affine before the cpu becomes online. */ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, true); } EXPORT_SYMBOL_GPL(irq_force_affinity); int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, bool setaffinity) { int ret = -EINVAL; scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { scoped_irqdesc->affinity_hint = m; ret = 0; } if (!ret && m && setaffinity) __irq_set_affinity(irq, m, false); return ret; } EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint); static void irq_affinity_notify(struct work_struct *work) { struct irq_affinity_notify *notify = container_of(work, struct irq_affinity_notify, work); struct irq_desc *desc = irq_to_desc(notify->irq); cpumask_var_t cpumask; if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL)) goto out; scoped_guard(raw_spinlock_irqsave, &desc->lock) { if (irq_move_pending(&desc->irq_data)) irq_get_pending(cpumask, desc); else cpumask_copy(cpumask, desc->irq_common_data.affinity); } notify->notify(notify, cpumask); free_cpumask_var(cpumask); out: kref_put(¬ify->kref, notify->release); } /** * irq_set_affinity_notifier - control notification of IRQ affinity changes * @irq: Interrupt for which to enable/disable notification * @notify: Context for notification, or %NULL to disable * notification. Function pointers must be initialised; * the other fields will be initialised by this function. * * Must be called in process context. Notification may only be enabled * after the IRQ is allocated and must be disabled before the IRQ is freed * using free_irq(). */ int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { struct irq_desc *desc = irq_to_desc(irq); struct irq_affinity_notify *old_notify; /* The release function is promised process context */ might_sleep(); if (!desc || irq_is_nmi(desc)) return -EINVAL; /* Complete initialisation of *notify */ if (notify) { notify->irq = irq; kref_init(¬ify->kref); INIT_WORK(¬ify->work, irq_affinity_notify); } scoped_guard(raw_spinlock_irqsave, &desc->lock) { old_notify = desc->affinity_notify; desc->affinity_notify = notify; } if (old_notify) { if (cancel_work_sync(&old_notify->work)) { /* Pending work had a ref, put that one too */ kref_put(&old_notify->kref, old_notify->release); } kref_put(&old_notify->kref, old_notify->release); } return 0; } EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. */ int irq_setup_affinity(struct irq_desc *desc) { struct cpumask *set = irq_default_affinity; int node = irq_desc_get_node(desc); static DEFINE_RAW_SPINLOCK(mask_lock); static struct cpumask mask; /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!__irq_can_set_affinity(desc)) return 0; guard(raw_spinlock)(&mask_lock); /* * Preserve the managed affinity setting and a userspace affinity * setup, but make sure that one of the targets is online. */ if (irqd_affinity_is_managed(&desc->irq_data) || irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { if (cpumask_intersects(desc->irq_common_data.affinity, cpu_online_mask)) set = desc->irq_common_data.affinity; else irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } cpumask_and(&mask, cpu_online_mask, set); if (cpumask_empty(&mask)) cpumask_copy(&mask, cpu_online_mask); if (node != NUMA_NO_NODE) { const struct cpumask *nodemask = cpumask_of_node(node); /* make sure at least one of the cpus in nodemask is online */ if (cpumask_intersects(&mask, nodemask)) cpumask_and(&mask, &mask, nodemask); } return irq_do_set_affinity(&desc->irq_data, &mask, false); } #else /* Wrapper for ALPHA specific affinity selector magic */ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } #endif /* CONFIG_AUTO_IRQ_AFFINITY */ #endif /* CONFIG_SMP */ /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt * @irq: interrupt number to set affinity * @vcpu_info: vCPU specific data or pointer to a percpu array of vCPU * specific data for percpu_devid interrupts * * This function uses the vCPU specific data to set the vCPU affinity for * an irq. The vCPU specific data is passed from outside, such as KVM. One * example code path is as below: KVM -> IOMMU -> irq_set_vcpu_affinity(). */ int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) { scoped_irqdesc_get_and_lock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; struct irq_data *data; struct irq_chip *chip; data = irq_desc_get_irq_data(desc); do { chip = irq_data_get_irq_chip(data); if (chip && chip->irq_set_vcpu_affinity) break; data = irqd_get_parent_data(data); } while (data); if (!data) return -ENOSYS; return chip->irq_set_vcpu_affinity(data, vcpu_info); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); void __disable_irq(struct irq_desc *desc) { if (!desc->depth++) irq_disable(desc); } static int __disable_irq_nosync(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { __disable_irq(scoped_irqdesc); return 0; } return -EINVAL; } /** * disable_irq_nosync - disable an irq without waiting * @irq: Interrupt to disable * * Disable the selected interrupt line. Disables and Enables are * nested. * Unlike disable_irq(), this function does not ensure existing * instances of the IRQ handler have completed before returning. * * This function may be called from IRQ context. */ void disable_irq_nosync(unsigned int irq) { __disable_irq_nosync(irq); } EXPORT_SYMBOL(disable_irq_nosync); /** * disable_irq - disable an irq and wait for completion * @irq: Interrupt to disable * * Disable the selected interrupt line. Enables and Disables are nested. * * This function waits for any pending IRQ handlers for this interrupt to * complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. * * Can only be called from preemptible code as it might sleep when an * interrupt thread is associated to @irq. * */ void disable_irq(unsigned int irq) { might_sleep(); if (!__disable_irq_nosync(irq)) synchronize_irq(irq); } EXPORT_SYMBOL(disable_irq); /** * disable_hardirq - disables an irq and waits for hardirq completion * @irq: Interrupt to disable * * Disable the selected interrupt line. Enables and Disables are nested. * * This function waits for any pending hard IRQ handlers for this interrupt * to complete before returning. If you use this function while holding a * resource the hard IRQ handler may need you will deadlock. * * When used to optimistically disable an interrupt from atomic context the * return value must be checked. * * Returns: false if a threaded handler is active. * * This function may be called - with care - from IRQ context. */ bool disable_hardirq(unsigned int irq) { if (!__disable_irq_nosync(irq)) return synchronize_hardirq(irq); return false; } EXPORT_SYMBOL_GPL(disable_hardirq); /** * disable_nmi_nosync - disable an nmi without waiting * @irq: Interrupt to disable * * Disable the selected interrupt line. Disables and enables are nested. * * The interrupt to disable must have been requested through request_nmi. * Unlike disable_nmi(), this function does not ensure existing * instances of the IRQ handler have completed before returning. */ void disable_nmi_nosync(unsigned int irq) { disable_irq_nosync(irq); } void __enable_irq(struct irq_desc *desc) { switch (desc->depth) { case 0: err_out: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq_desc_get_irq(desc)); break; case 1: { if (desc->istate & IRQS_SUSPENDED) goto err_out; /* Prevent probing on this irq: */ irq_settings_set_noprobe(desc); /* * Call irq_startup() not irq_enable() here because the * interrupt might be marked NOAUTOEN so irq_startup() * needs to be invoked when it gets enabled the first time. * This is also required when __enable_irq() is invoked for * a managed and shutdown interrupt from the S3 resume * path. * * If it was already started up, then irq_startup() will * invoke irq_enable() under the hood. */ irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); break; } default: desc->depth--; } } /** * enable_irq - enable handling of an irq * @irq: Interrupt to enable * * Undoes the effect of one call to disable_irq(). If this matches the * last disable, processing of interrupts on this IRQ line is re-enabled. * * This function may be called from IRQ context only when * desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL ! */ void enable_irq(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; if (WARN(!desc->irq_data.chip, "enable_irq before setup/request_irq: irq %u\n", irq)) return; __enable_irq(desc); } } EXPORT_SYMBOL(enable_irq); /** * enable_nmi - enable handling of an nmi * @irq: Interrupt to enable * * The interrupt to enable must have been requested through request_nmi. * Undoes the effect of one call to disable_nmi(). If this matches the last * disable, processing of interrupts on this IRQ line is re-enabled. */ void enable_nmi(unsigned int irq) { enable_irq(irq); } static int set_irq_wake_real(unsigned int irq, unsigned int on) { struct irq_desc *desc = irq_to_desc(irq); int ret = -ENXIO; if (irq_desc_get_chip(desc)->flags & IRQCHIP_SKIP_SET_WAKE) return 0; if (desc->irq_data.chip->irq_set_wake) ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on); return ret; } /** * irq_set_irq_wake - control irq power management wakeup * @irq: interrupt to control * @on: enable/disable power management wakeup * * Enable/disable power management wakeup mode, which is disabled by * default. Enables and disables must match, just as they match for * non-wakeup mode support. * * Wakeup mode lets this IRQ wake the system from sleep states like * "suspend to RAM". * * Note: irq enable/disable state is completely orthogonal to the * enable/disable state of irq wake. An irq can be disabled with * disable_irq() and still wake the system as long as the irq has wake * enabled. If this does not hold, then the underlying irq chip and the * related driver need to be investigated. */ int irq_set_irq_wake(unsigned int irq, unsigned int on) { scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; int ret = 0; /* Don't use NMIs as wake up interrupts please */ if (irq_is_nmi(desc)) return -EINVAL; /* * wakeup-capable irqs can be shared between drivers that * don't need to have the same sleep mode behaviors. */ if (on) { if (desc->wake_depth++ == 0) { ret = set_irq_wake_real(irq, on); if (ret) desc->wake_depth = 0; else irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE); } } else { if (desc->wake_depth == 0) { WARN(1, "Unbalanced IRQ %d wake disable\n", irq); } else if (--desc->wake_depth == 0) { ret = set_irq_wake_real(irq, on); if (ret) desc->wake_depth = 1; else irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE); } } return ret; } return -EINVAL; } EXPORT_SYMBOL(irq_set_irq_wake); /* * Internal function that tells the architecture code whether a * particular irq has been exclusively allocated or is available * for driver use. */ bool can_request_irq(unsigned int irq, unsigned long irqflags) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; if (irq_settings_can_request(desc)) { if (!desc->action || irqflags & desc->action->flags & IRQF_SHARED) return true; } } return false; } int __irq_set_trigger(struct irq_desc *desc, unsigned long flags) { struct irq_chip *chip = desc->irq_data.chip; int ret, unmask = 0; if (!chip || !chip->irq_set_type) { /* * IRQF_TRIGGER_* but the PIC does not support multiple * flow-types? */ pr_debug("No set_type function for IRQ %d (%s)\n", irq_desc_get_irq(desc), chip ? (chip->name ? : "unknown") : "unknown"); return 0; } if (chip->flags & IRQCHIP_SET_TYPE_MASKED) { if (!irqd_irq_masked(&desc->irq_data)) mask_irq(desc); if (!irqd_irq_disabled(&desc->irq_data)) unmask = 1; } /* Mask all flags except trigger mode */ flags &= IRQ_TYPE_SENSE_MASK; ret = chip->irq_set_type(&desc->irq_data, flags); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); irqd_set(&desc->irq_data, flags); fallthrough; case IRQ_SET_MASK_OK_NOCOPY: flags = irqd_get_trigger_type(&desc->irq_data); irq_settings_set_trigger_mask(desc, flags); irqd_clear(&desc->irq_data, IRQD_LEVEL); irq_settings_clr_level(desc); if (flags & IRQ_TYPE_LEVEL_MASK) { irq_settings_set_level(desc); irqd_set(&desc->irq_data, IRQD_LEVEL); } ret = 0; break; default: pr_err("Setting trigger mode %lu for irq %u failed (%pS)\n", flags, irq_desc_get_irq(desc), chip->irq_set_type); } if (unmask) unmask_irq(desc); return ret; } #ifdef CONFIG_HARDIRQS_SW_RESEND int irq_set_parent(int irq, int parent_irq) { scoped_irqdesc_get_and_lock(irq, 0) { scoped_irqdesc->parent_irq = parent_irq; return 0; } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_parent); #endif /* * Default primary interrupt handler for threaded interrupts. Is * assigned as primary handler when request_threaded_irq is called * with handler == NULL. Useful for oneshot interrupts. */ static irqreturn_t irq_default_primary_handler(int irq, void *dev_id) { return IRQ_WAKE_THREAD; } /* * Primary handler for nested threaded interrupts. Should never be * called. */ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) { WARN(1, "Primary handler called for nested irq %d\n", irq); return IRQ_NONE; } static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) { WARN(1, "Secondary action handler called for irq %d\n", irq); return IRQ_NONE; } #ifdef CONFIG_SMP /* * Check whether we need to change the affinity of the interrupt thread. */ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { cpumask_var_t mask; bool valid = false; if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) return; __set_current_state(TASK_RUNNING); /* * In case we are out of memory we set IRQTF_AFFINITY again and * try again next time */ if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { set_bit(IRQTF_AFFINITY, &action->thread_flags); return; } scoped_guard(raw_spinlock_irq, &desc->lock) { /* * This code is triggered unconditionally. Check the affinity * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. */ if (cpumask_available(desc->irq_common_data.affinity)) { const struct cpumask *m; m = irq_data_get_effective_affinity_mask(&desc->irq_data); cpumask_copy(mask, m); valid = true; } } if (valid) set_cpus_allowed_ptr(current, mask); free_cpumask_var(mask); } #else static inline void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } #endif static int irq_wait_for_interrupt(struct irq_desc *desc, struct irqaction *action) { for (;;) { set_current_state(TASK_INTERRUPTIBLE); irq_thread_check_affinity(desc, action); if (kthread_should_stop()) { /* may need to run one last time */ if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { __set_current_state(TASK_RUNNING); return 0; } __set_current_state(TASK_RUNNING); return -1; } if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { __set_current_state(TASK_RUNNING); return 0; } schedule(); } } /* * Oneshot interrupts keep the irq line masked until the threaded * handler finished. unmask if the interrupt has not been disabled and * is marked MASKED. */ static void irq_finalize_oneshot(struct irq_desc *desc, struct irqaction *action) { if (!(desc->istate & IRQS_ONESHOT) || action->handler == irq_forced_secondary_handler) return; again: chip_bus_lock(desc); raw_spin_lock_irq(&desc->lock); /* * Implausible though it may be we need to protect us against * the following scenario: * * The thread is faster done than the hard interrupt handler * on the other CPU. If we unmask the irq line then the * interrupt can come in again and masks the line, leaves due * to IRQS_INPROGRESS and the irq line is masked forever. * * This also serializes the state of shared oneshot handlers * versus "desc->threads_oneshot |= action->thread_mask;" in * irq_wake_thread(). See the comment there which explains the * serialization. */ if (unlikely(irqd_irq_inprogress(&desc->irq_data))) { raw_spin_unlock_irq(&desc->lock); chip_bus_sync_unlock(desc); cpu_relax(); goto again; } /* * Now check again, whether the thread should run. Otherwise * we would clear the threads_oneshot bit of this thread which * was just set. */ if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) goto out_unlock; desc->threads_oneshot &= ~action->thread_mask; if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data)) unmask_threaded_irq(desc); out_unlock: raw_spin_unlock_irq(&desc->lock); chip_bus_sync_unlock(desc); } /* * Interrupts explicitly requested as threaded interrupts want to be * preemptible - many of them need to sleep and wait for slow busses to * complete. */ static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret = action->thread_fn(action->irq, action->dev_id); if (ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); irq_finalize_oneshot(desc, action); return ret; } /* * Interrupts which are not explicitly requested as threaded * interrupts rely on the implicit bh/preempt disable of the hard irq * context. So we need to disable bh here to avoid deadlocks and other * side effects. */ static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret; local_bh_disable(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); ret = irq_thread_fn(desc, action); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); local_bh_enable(); return ret; } void wake_threads_waitq(struct irq_desc *desc) { if (atomic_dec_and_test(&desc->threads_active)) wake_up(&desc->wait_for_threads); } static void irq_thread_dtor(struct callback_head *unused) { struct task_struct *tsk = current; struct irq_desc *desc; struct irqaction *action; if (WARN_ON_ONCE(!(current->flags & PF_EXITING))) return; action = kthread_data(tsk); pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", tsk->comm, tsk->pid, action->irq); desc = irq_to_desc(action->irq); /* * If IRQTF_RUNTHREAD is set, we need to decrement * desc->threads_active and wake possible waiters. */ if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) wake_threads_waitq(desc); /* Prevent a stale desc->threads_oneshot */ irq_finalize_oneshot(desc, action); } static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) { struct irqaction *secondary = action->secondary; if (WARN_ON_ONCE(!secondary)) return; guard(raw_spinlock_irq)(&desc->lock); __irq_wake_thread(desc, secondary); } /* * Internal function to notify that a interrupt thread is ready. */ static void irq_thread_set_ready(struct irq_desc *desc, struct irqaction *action) { set_bit(IRQTF_READY, &action->thread_flags); wake_up(&desc->wait_for_threads); } /* * Internal function to wake up a interrupt thread and wait until it is * ready. */ static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, struct irqaction *action) { if (!action || !action->thread) return; wake_up_process(action->thread); wait_event(desc->wait_for_threads, test_bit(IRQTF_READY, &action->thread_flags)); } /* * Interrupt handler thread */ static int irq_thread(void *data) { struct callback_head on_exit_work; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); irq_thread_set_ready(desc, action); sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; else handler_fn = irq_thread_fn; init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, TWA_NONE); while (!irq_wait_for_interrupt(desc, action)) { irqreturn_t action_ret; action_ret = handler_fn(desc, action); if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); wake_threads_waitq(desc); } /* * This is the regular exit path. __free_irq() is stopping the * thread via kthread_stop() after calling * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the * oneshot mask bit can be set. */ task_work_cancel_func(current, irq_thread_dtor); return 0; } /** * irq_wake_thread - wake the irq thread for the action identified by dev_id * @irq: Interrupt line * @dev_id: Device identity for which the thread should be woken */ void irq_wake_thread(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return; guard(raw_spinlock_irqsave)(&desc->lock); for_each_action_of_desc(desc, action) { if (action->dev_id == dev_id) { if (action->thread) __irq_wake_thread(desc, action); break; } } } EXPORT_SYMBOL_GPL(irq_wake_thread); static int irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads()) return 0; if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; /* * No further action required for interrupts which are requested as * threaded interrupts already */ if (new->handler == irq_default_primary_handler) return 0; new->flags |= IRQF_ONESHOT; /* * Handle the case where we have a real primary handler and a * thread handler. We force thread them as well by creating a * secondary action. */ if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!new->secondary) return -ENOMEM; new->secondary->handler = irq_forced_secondary_handler; new->secondary->thread_fn = new->thread_fn; new->secondary->dev_id = new->dev_id; new->secondary->irq = new->irq; new->secondary->name = new->name; } /* Deal with the primary handler */ set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); new->thread_fn = new->handler; new->handler = irq_default_primary_handler; return 0; } static int irq_request_resources(struct irq_desc *desc) { struct irq_data *d = &desc->irq_data; struct irq_chip *c = d->chip; return c->irq_request_resources ? c->irq_request_resources(d) : 0; } static void irq_release_resources(struct irq_desc *desc) { struct irq_data *d = &desc->irq_data; struct irq_chip *c = d->chip; if (c->irq_release_resources) c->irq_release_resources(d); } static bool irq_supports_nmi(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /* Only IRQs directly managed by the root irqchip can be set as NMI */ if (d->parent_data) return false; #endif /* Don't support NMIs for chips behind a slow bus */ if (d->chip->irq_bus_lock || d->chip->irq_bus_sync_unlock) return false; return d->chip->flags & IRQCHIP_SUPPORTS_NMI; } static int irq_nmi_setup(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); struct irq_chip *c = d->chip; return c->irq_nmi_setup ? c->irq_nmi_setup(d) : -EINVAL; } static void irq_nmi_teardown(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); struct irq_chip *c = d->chip; if (c->irq_nmi_teardown) c->irq_nmi_teardown(d); } static int setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) { struct task_struct *t; if (!secondary) { t = kthread_create(irq_thread, new, "irq/%d-%s", irq, new->name); } else { t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq, new->name); } if (IS_ERR(t)) return PTR_ERR(t); /* * We keep the reference to the task struct even if * the thread dies to avoid that the interrupt code * references an already freed task_struct. */ new->thread = get_task_struct(t); /* * Tell the thread to set its affinity. This is * important for shared interrupt handlers as we do * not invoke setup_affinity() for the secondary * handlers as everything is already set up. Even for * interrupts marked with IRQF_NO_BALANCE this is * correct as we want the thread to move to the cpu(s) * on which the requesting code placed the interrupt. */ set_bit(IRQTF_AFFINITY, &new->thread_flags); return 0; } /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. * * Locking rules: * * desc->request_mutex Provides serialization against a concurrent free_irq() * chip_bus_lock Provides serialization for slow bus operations * desc->lock Provides serialization against hard interrupts * * chip_bus_lock and desc->lock are sufficient for all other management and * interrupt related functions. desc->request_mutex solely serializes * request/free_irq(). */ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { struct irqaction *old, **old_ptr; unsigned long flags, thread_mask = 0; int ret, nested, shared = 0; if (!desc) return -EINVAL; if (desc->irq_data.chip == &no_irq_chip) return -ENOSYS; if (!try_module_get(desc->owner)) return -ENODEV; new->irq = irq; /* * If the trigger type is not specified by the caller, * then use the default for this interrupt. */ if (!(new->flags & IRQF_TRIGGER_MASK)) new->flags |= irqd_get_trigger_type(&desc->irq_data); /* * Check whether the interrupt nests into another interrupt * thread. */ nested = irq_settings_is_nested_thread(desc); if (nested) { if (!new->thread_fn) { ret = -EINVAL; goto out_mput; } /* * Replace the primary handler which was provided from * the driver for non nested interrupt handling by the * dummy function which warns when called. */ new->handler = irq_nested_primary_handler; } else { if (irq_settings_can_thread(desc)) { ret = irq_setup_forced_threading(new); if (ret) goto out_mput; } } /* * Create a handler thread when a thread function is supplied * and the interrupt does not nest into another interrupt * thread. */ if (new->thread_fn && !nested) { ret = setup_irq_thread(new, irq, false); if (ret) goto out_mput; if (new->secondary) { ret = setup_irq_thread(new->secondary, irq, true); if (ret) goto out_thread; } } /* * Drivers are often written to work w/o knowledge about the * underlying irq chip implementation, so a request for a * threaded irq without a primary hard irq context handler * requires the ONESHOT flag to be set. Some irq chips like * MSI based interrupts are per se one shot safe. Check the * chip flags, so we can avoid the unmask dance at the end of * the threaded handler for those. */ if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; /* * Protects against a concurrent __free_irq() call which might wait * for synchronize_hardirq() to complete without holding the optional * chip bus lock and desc->lock. Also protects against handing out * a recycled oneshot thread_mask bit while it's still in use by * its previous owner. */ mutex_lock(&desc->request_mutex); /* * Acquire bus lock as the irq_request_resources() callback below * might rely on the serialization or the magic power management * functions which are abusing the irq_bus_lock() callback, */ chip_bus_lock(desc); /* First installed action requests resources. */ if (!desc->action) { ret = irq_request_resources(desc); if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); goto out_bus_unlock; } } /* * The following block of code has to be executed atomically * protected against a concurrent interrupt and any of the other * management calls which are not serialized via * desc->request_mutex or the optional bus lock. */ raw_spin_lock_irqsave(&desc->lock, flags); old_ptr = &desc->action; old = *old_ptr; if (old) { /* * Can't share interrupts unless both agree to and are * the same type (level, edge, polarity). So both flag * fields must have IRQF_SHARED set and the bits which * set the trigger type must match. Also all must * agree on ONESHOT. * Interrupt lines used for NMIs cannot be shared. */ unsigned int oldtype; if (irq_is_nmi(desc)) { pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n", new->name, irq, desc->irq_data.chip->name); ret = -EINVAL; goto out_unlock; } /* * If nobody did set the configuration before, inherit * the one provided by the requester. */ if (irqd_trigger_type_was_set(&desc->irq_data)) { oldtype = irqd_get_trigger_type(&desc->irq_data); } else { oldtype = new->flags & IRQF_TRIGGER_MASK; irqd_set_trigger_type(&desc->irq_data, oldtype); } if (!((old->flags & new->flags) & IRQF_SHARED) || (oldtype != (new->flags & IRQF_TRIGGER_MASK))) goto mismatch; if ((old->flags & IRQF_ONESHOT) && (new->flags & IRQF_COND_ONESHOT)) new->flags |= IRQF_ONESHOT; else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ if ((old->flags & IRQF_PERCPU) != (new->flags & IRQF_PERCPU)) goto mismatch; /* add new interrupt at end of irq queue */ do { /* * Or all existing action->thread_mask bits, * so we can find the next zero bit for this * new action. */ thread_mask |= old->thread_mask; old_ptr = &old->next; old = *old_ptr; } while (old); shared = 1; } /* * Setup the thread mask for this irqaction for ONESHOT. For * !ONESHOT irqs the thread mask is 0 so we can avoid a * conditional in irq_wake_thread(). */ if (new->flags & IRQF_ONESHOT) { /* * Unlikely to have 32 resp 64 irqs sharing one line, * but who knows. */ if (thread_mask == ~0UL) { ret = -EBUSY; goto out_unlock; } /* * The thread_mask for the action is or'ed to * desc->thread_active to indicate that the * IRQF_ONESHOT thread handler has been woken, but not * yet finished. The bit is cleared when a thread * completes. When all threads of a shared interrupt * line have completed desc->threads_active becomes * zero and the interrupt line is unmasked. See * handle.c:irq_wake_thread() for further information. * * If no thread is woken by primary (hard irq context) * interrupt handlers, then desc->threads_active is * also checked for zero to unmask the irq line in the * affected hard irq flow handlers * (handle_[fasteoi|level]_irq). * * The new action gets the first zero bit of * thread_mask assigned. See the loop above which or's * all existing action->thread_mask bits. */ new->thread_mask = 1UL << ffz(thread_mask); } else if (new->handler == irq_default_primary_handler && !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { /* * The interrupt was requested with handler = NULL, so * we use the default primary handler for it. But it * does not have the oneshot flag set. In combination * with level interrupts this is deadly, because the * default primary handler just wakes the thread, then * the irq lines is reenabled, but the device still * has the level irq asserted. Rinse and repeat.... * * While this works for edge type interrupts, we play * it safe and reject unconditionally because we can't * say for sure which type this interrupt really * has. The type flags are unreliable as the * underlying chip implementation can override them. */ pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n", new->name, irq); ret = -EINVAL; goto out_unlock; } if (!shared) { /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); if (ret) goto out_unlock; } /* * Activate the interrupt. That activation must happen * independently of IRQ_NOAUTOEN. request_irq() can fail * and the callers are supposed to handle * that. enable_irq() of an interrupt requested with * IRQ_NOAUTOEN is not supposed to fail. The activation * keeps it in shutdown mode, it merily associates * resources if necessary and if that's not possible it * fails. Interrupts which are in managed shutdown mode * will simply ignore that activation request. */ ret = irq_activate(desc); if (ret) goto out_unlock; desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ IRQS_ONESHOT | IRQS_WAITING); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); if (new->flags & IRQF_PERCPU) { irqd_set(&desc->irq_data, IRQD_PER_CPU); irq_settings_set_per_cpu(desc); if (new->flags & IRQF_NO_DEBUG) irq_settings_set_no_debug(desc); } if (noirqdebug) irq_settings_set_no_debug(desc); if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; /* Exclude IRQ from balancing if requested */ if (new->flags & IRQF_NOBALANCING) { irq_settings_set_no_balancing(desc); irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } if (!(new->flags & IRQF_NO_AUTOEN) && irq_settings_can_autoenable(desc)) { irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else { /* * Shared interrupts do not go well with disabling * auto enable. The sharing interrupt might request * it while it's still disabled and then wait for * interrupts forever. */ WARN_ON_ONCE(new->flags & IRQF_SHARED); /* Undo nested disables: */ desc->depth = 1; } } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; unsigned int omsk = irqd_get_trigger_type(&desc->irq_data); if (nmsk != omsk) /* hope the handler works with current trigger mode */ pr_warn("irq %d uses trigger mode %u; requested %u\n", irq, omsk, nmsk); } *old_ptr = new; irq_pm_install_action(desc, new); /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; desc->irqs_unhandled = 0; /* * Check whether we disabled the irq via the spurious handler * before. Reenable it and give it another chance. */ if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) { desc->istate &= ~IRQS_SPURIOUS_DISABLED; __enable_irq(desc); } raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); irq_setup_timings(desc, new); wake_up_and_wait_for_irq_thread_ready(desc, new); wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; register_handler_proc(irq, new); return 0; mismatch: if (!(new->flags & IRQF_PROBE_SHARED)) { pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n", irq, new->flags, new->name, old->flags, old->name); #ifdef CONFIG_DEBUG_SHIRQ dump_stack(); #endif } ret = -EBUSY; out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); if (!desc->action) irq_release_resources(desc); out_bus_unlock: chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); out_thread: if (new->thread) { struct task_struct *t = new->thread; new->thread = NULL; kthread_stop_put(t); } if (new->secondary && new->secondary->thread) { struct task_struct *t = new->secondary->thread; new->secondary->thread = NULL; kthread_stop_put(t); } out_mput: module_put(desc->owner); return ret; } /* * Internal function to unregister an irqaction - used to free * regular and special interrupts that are part of the architecture. */ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) { unsigned irq = desc->irq_data.irq; struct irqaction *action, **action_ptr; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); /* * There can be multiple actions per IRQ descriptor, find the right * one based on the dev_id: */ action_ptr = &desc->action; for (;;) { action = *action_ptr; if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); return NULL; } if (action->dev_id == dev_id) break; action_ptr = &action->next; } /* Found it - now remove it from the list of entries: */ *action_ptr = action->next; irq_pm_remove_action(desc, action); /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { irq_settings_clr_disable_unlazy(desc); /* Only shutdown. Deactivate after synchronize_hardirq() */ irq_shutdown(desc); } #ifdef CONFIG_SMP /* make sure affinity_hint is cleaned up */ if (WARN_ON_ONCE(desc->affinity_hint)) desc->affinity_hint = NULL; #endif raw_spin_unlock_irqrestore(&desc->lock, flags); /* * Drop bus_lock here so the changes which were done in the chip * callbacks above are synced out to the irq chips which hang * behind a slow bus (I2C, SPI) before calling synchronize_hardirq(). * * Aside of that the bus_lock can also be taken from the threaded * handler in irq_finalize_oneshot() which results in a deadlock * because kthread_stop() would wait forever for the thread to * complete, which is blocked on the bus lock. * * The still held desc->request_mutex() protects against a * concurrent request_irq() of this irq so the release of resources * and timing data is properly serialized. */ chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); /* * Make sure it's not being used on another CPU and if the chip * supports it also make sure that there is no (not yet serviced) * interrupt in flight at the hardware level. */ __synchronize_irq(desc); #ifdef CONFIG_DEBUG_SHIRQ /* * It's a shared IRQ -- the driver ought to be prepared for an IRQ * event to happen even now it's being freed, so let's make sure that * is so by doing an extra call to the handler .... * * ( We do this after actually deregistering it, to make sure that a * 'real' IRQ doesn't run in parallel with our fake. ) */ if (action->flags & IRQF_SHARED) { local_irq_save(flags); action->handler(irq, dev_id); local_irq_restore(flags); } #endif /* * The action has already been removed above, but the thread writes * its oneshot mask bit when it completes. Though request_mutex is * held across this which prevents __setup_irq() from handing out * the same bit to a newly requested action. */ if (action->thread) { kthread_stop_put(action->thread); if (action->secondary && action->secondary->thread) kthread_stop_put(action->secondary->thread); } /* Last action releases resources */ if (!desc->action) { /* * Reacquire bus lock as irq_release_resources() might * require it to deallocate resources over the slow bus. */ chip_bus_lock(desc); /* * There is no interrupt on the fly anymore. Deactivate it * completely. */ scoped_guard(raw_spinlock_irqsave, &desc->lock) irq_domain_deactivate_irq(&desc->irq_data); irq_release_resources(desc); chip_bus_sync_unlock(desc); irq_remove_timings(desc); } mutex_unlock(&desc->request_mutex); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); kfree(action->secondary); return action; } /** * free_irq - free an interrupt allocated with request_irq * @irq: Interrupt line to free * @dev_id: Device identity to free * * Remove an interrupt handler. The handler is removed and if the interrupt * line is no longer in use by any driver it is disabled. On a shared IRQ * the caller must ensure the interrupt is disabled on the card it drives * before calling this function. The function does not return until any * executing interrupts for this IRQ have completed. * * This function must not be called from interrupt context. * * Returns the devname argument passed to request_irq. */ const void *free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; const char *devname; if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return NULL; #ifdef CONFIG_SMP if (WARN_ON(desc->affinity_notify)) desc->affinity_notify = NULL; #endif action = __free_irq(desc, dev_id); if (!action) return NULL; devname = action->name; kfree(action); return devname; } EXPORT_SYMBOL(free_irq); /* This function must be called with desc->lock held */ static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc) { const char *devname = NULL; desc->istate &= ~IRQS_NMI; if (!WARN_ON(desc->action == NULL)) { irq_pm_remove_action(desc, desc->action); devname = desc->action->name; unregister_handler_proc(irq, desc->action); kfree(desc->action); desc->action = NULL; } irq_settings_clr_disable_unlazy(desc); irq_shutdown_and_deactivate(desc); irq_release_resources(desc); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); return devname; } const void *free_nmi(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || WARN_ON(!irq_is_nmi(desc))) return NULL; if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) return NULL; /* NMI still enabled */ if (WARN_ON(desc->depth == 0)) disable_nmi_nosync(irq); guard(raw_spinlock_irqsave)(&desc->lock); irq_nmi_teardown(desc); return __cleanup_nmi(irq, desc); } /** * request_threaded_irq - allocate an interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Primary handler for threaded interrupts. * If handler is NULL and thread_fn != NULL * the default primary handler is installed. * @thread_fn: Function called from the irq handler thread * If NULL, no irq thread is created * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. From the point this call is made your handler function * may be invoked. Since your handler function must clear any interrupt the * board raises, you must take care both to initialise your hardware and to * set up the interrupt handler in the right order. * * If you want to set up a threaded irq handler for your device then you * need to supply @handler and @thread_fn. @handler is still called in hard * interrupt context and has to check whether the interrupt originates from * the device. If yes it needs to disable the interrupt on the device and * return IRQ_WAKE_THREAD which will wake up the handler thread and run * @thread_fn. This split handler design is necessary to support shared * interrupts. * * @dev_id must be globally unique. Normally the address of the device data * structure is used as the cookie. Since the handler receives this value * it makes sense to use it. * * If your interrupt is shared you must pass a non NULL dev_id as this is * required when freeing the interrupt. * * Flags: * * IRQF_SHARED Interrupt is shared * IRQF_TRIGGER_* Specify active edge(s) or level * IRQF_ONESHOT Run thread_fn with interrupt line masked */ int request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long irqflags, const char *devname, void *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out * which interrupt is which (messes up the interrupt freeing * logic etc). * * Also shared interrupts do not go well with disabling auto enable. * The sharing interrupt might request it while it's still disabled * and then wait for interrupts forever. * * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and * it cannot be set along with IRQF_NO_SUSPEND. */ if (((irqflags & IRQF_SHARED) && !dev_id) || ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) || (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) return -EINVAL; desc = irq_to_desc(irq); if (!desc) return -EINVAL; if (!irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return -EINVAL; if (!handler) { if (!thread_fn) return -EINVAL; handler = irq_default_primary_handler; } action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->thread_fn = thread_fn; action->flags = irqflags; action->name = devname; action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) { kfree(action); return retval; } retval = __setup_irq(irq, desc, action); if (retval) { irq_chip_pm_put(&desc->irq_data); kfree(action->secondary); kfree(action); } #ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it * to happen immediately, so let's make sure.... * We disable the irq to make sure that a 'real' IRQ doesn't * run in parallel with our fake. */ unsigned long flags; disable_irq(irq); local_irq_save(flags); handler(irq, dev_id); local_irq_restore(flags); enable_irq(irq); } #endif return retval; } EXPORT_SYMBOL(request_threaded_irq); /** * request_any_context_irq - allocate an interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Threaded handler for threaded interrupts. * @flags: Interrupt type flags * @name: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. It selects either a hardirq or threaded handling * method depending on the context. * * Returns: On failure, it returns a negative value. On success, it returns either * IRQC_IS_HARDIRQ or IRQC_IS_NESTED. */ int request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id) { struct irq_desc *desc; int ret; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; desc = irq_to_desc(irq); if (!desc) return -EINVAL; if (irq_settings_is_nested_thread(desc)) { ret = request_threaded_irq(irq, NULL, handler, flags, name, dev_id); return !ret ? IRQC_IS_NESTED : ret; } ret = request_irq(irq, handler, flags, name, dev_id); return !ret ? IRQC_IS_HARDIRQ : ret; } EXPORT_SYMBOL_GPL(request_any_context_irq); /** * request_nmi - allocate an interrupt line for NMI delivery * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Threaded handler for threaded interrupts. * @irqflags: Interrupt type flags * @name: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. It sets up the IRQ line to be handled as an NMI. * * An interrupt line delivering NMIs cannot be shared and IRQ handling * cannot be threaded. * * Interrupt lines requested for NMI delivering must produce per cpu * interrupts and have auto enabling setting disabled. * * @dev_id must be globally unique. Normally the address of the device data * structure is used as the cookie. Since the handler receives this value * it makes sense to use it. * * If the interrupt line cannot be used to deliver NMIs, function will fail * and return a negative value. */ int request_nmi(unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *name, void *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; /* NMI cannot be shared, used for Polling */ if (irqflags & (IRQF_SHARED | IRQF_COND_SUSPEND | IRQF_IRQPOLL)) return -EINVAL; if (!(irqflags & IRQF_PERCPU)) return -EINVAL; if (!handler) return -EINVAL; desc = irq_to_desc(irq); if (!desc || (irq_settings_can_autoenable(desc) && !(irqflags & IRQF_NO_AUTOEN)) || !irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc)) || !irq_supports_nmi(desc)) return -EINVAL; action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = irqflags | IRQF_NO_THREAD | IRQF_NOBALANCING; action->name = name; action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) goto err_out; retval = __setup_irq(irq, desc, action); if (retval) goto err_irq_setup; scoped_guard(raw_spinlock_irqsave, &desc->lock) { /* Setup NMI state */ desc->istate |= IRQS_NMI; retval = irq_nmi_setup(desc); if (retval) { __cleanup_nmi(irq, desc); return -EINVAL; } return 0; } err_irq_setup: irq_chip_pm_put(&desc->irq_data); err_out: kfree(action); return retval; } void enable_percpu_irq(unsigned int irq, unsigned int type) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { struct irq_desc *desc = scoped_irqdesc; /* * If the trigger type is not specified by the caller, then * use the default for this interrupt. */ type &= IRQ_TYPE_SENSE_MASK; if (type == IRQ_TYPE_NONE) type = irqd_get_trigger_type(&desc->irq_data); if (type != IRQ_TYPE_NONE) { if (__irq_set_trigger(desc, type)) { WARN(1, "failed to set type for IRQ%d\n", irq); return; } } irq_percpu_enable(desc, smp_processor_id()); } } EXPORT_SYMBOL_GPL(enable_percpu_irq); void enable_percpu_nmi(unsigned int irq, unsigned int type) { enable_percpu_irq(irq, type); } /** * irq_percpu_is_enabled - Check whether the per cpu irq is enabled * @irq: Linux irq number to check for * * Must be called from a non migratable context. Returns the enable * state of a per cpu interrupt on the current cpu. */ bool irq_percpu_is_enabled(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) return cpumask_test_cpu(smp_processor_id(), scoped_irqdesc->percpu_enabled); return false; } EXPORT_SYMBOL_GPL(irq_percpu_is_enabled); void disable_percpu_irq(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) irq_percpu_disable(scoped_irqdesc, smp_processor_id()); } EXPORT_SYMBOL_GPL(disable_percpu_irq); void disable_percpu_nmi(unsigned int irq) { disable_percpu_irq(irq); } /* * Internal function to unregister a percpu irqaction. */ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); if (!desc) return NULL; scoped_guard(raw_spinlock_irqsave, &desc->lock) { action = desc->action; if (!action || action->percpu_dev_id != dev_id) { WARN(1, "Trying to free already-free IRQ %d\n", irq); return NULL; } if (!cpumask_empty(desc->percpu_enabled)) { WARN(1, "percpu IRQ %d still enabled on CPU%d!\n", irq, cpumask_first(desc->percpu_enabled)); return NULL; } /* Found it - now remove it from the list of entries: */ desc->action = NULL; desc->istate &= ~IRQS_NMI; } unregister_handler_proc(irq, action); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); return action; } /** * free_percpu_irq - free an interrupt allocated with request_percpu_irq * @irq: Interrupt line to free * @dev_id: Device identity to free * * Remove a percpu interrupt handler. The handler is removed, but the * interrupt line is not disabled. This must be done on each CPU before * calling this function. The function does not return until any executing * interrupts for this IRQ have completed. * * This function must not be called from interrupt context. */ void free_percpu_irq(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !irq_settings_is_per_cpu_devid(desc)) return; chip_bus_lock(desc); kfree(__free_percpu_irq(irq, dev_id)); chip_bus_sync_unlock(desc); } EXPORT_SYMBOL_GPL(free_percpu_irq); void free_percpu_nmi(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !irq_settings_is_per_cpu_devid(desc)) return; if (WARN_ON(!irq_is_nmi(desc))) return; kfree(__free_percpu_irq(irq, dev_id)); } /** * setup_percpu_irq - setup a per-cpu interrupt * @irq: Interrupt line to setup * @act: irqaction for the interrupt * * Used to statically setup per-cpu interrupts in the early boot process. */ int setup_percpu_irq(unsigned int irq, struct irqaction *act) { struct irq_desc *desc = irq_to_desc(irq); int retval; if (!desc || !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) return retval; retval = __setup_irq(irq, desc, act); if (retval) irq_chip_pm_put(&desc->irq_data); return retval; } /** * __request_percpu_irq - allocate a percpu interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * @flags: Interrupt type flags (IRQF_TIMER only) * @devname: An ascii name for the claiming device * @dev_id: A percpu cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt on the * local CPU. If the interrupt is supposed to be enabled on other CPUs, it * has to be done on each CPU using enable_percpu_irq(). * * @dev_id must be globally unique. It is a per-cpu variable, and * the handler gets called with the interrupted CPU's instance of * that variable. */ int __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (!dev_id) return -EINVAL; desc = irq_to_desc(irq); if (!desc || !irq_settings_can_request(desc) || !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; if (flags && flags != IRQF_TIMER) return -EINVAL; action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND; action->name = devname; action->percpu_dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) { kfree(action); return retval; } retval = __setup_irq(irq, desc, action); if (retval) { irq_chip_pm_put(&desc->irq_data); kfree(action); } return retval; } EXPORT_SYMBOL_GPL(__request_percpu_irq); /** * request_percpu_nmi - allocate a percpu interrupt line for NMI delivery * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * @name: An ascii name for the claiming device * @dev_id: A percpu cookie passed back to the handler function * * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs * have to be setup on each CPU by calling prepare_percpu_nmi() before * being enabled on the same CPU by using enable_percpu_nmi(). * * @dev_id must be globally unique. It is a per-cpu variable, and the * handler gets called with the interrupted CPU's instance of that * variable. * * Interrupt lines requested for NMI delivering should have auto enabling * setting disabled. * * If the interrupt line cannot be used to deliver NMIs, function * will fail returning a negative value. */ int request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name, void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (!handler) return -EINVAL; desc = irq_to_desc(irq); if (!desc || !irq_settings_can_request(desc) || !irq_settings_is_per_cpu_devid(desc) || irq_settings_can_autoenable(desc) || !irq_supports_nmi(desc)) return -EINVAL; /* The line cannot already be NMI */ if (irq_is_nmi(desc)) return -EINVAL; action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD | IRQF_NOBALANCING; action->name = name; action->percpu_dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) goto err_out; retval = __setup_irq(irq, desc, action); if (retval) goto err_irq_setup; scoped_guard(raw_spinlock_irqsave, &desc->lock) desc->istate |= IRQS_NMI; return 0; err_irq_setup: irq_chip_pm_put(&desc->irq_data); err_out: kfree(action); return retval; } /** * prepare_percpu_nmi - performs CPU local setup for NMI delivery * @irq: Interrupt line to prepare for NMI delivery * * This call prepares an interrupt line to deliver NMI on the current CPU, * before that interrupt line gets enabled with enable_percpu_nmi(). * * As a CPU local operation, this should be called from non-preemptible * context. * * If the interrupt line cannot be used to deliver NMIs, function will fail * returning a negative value. */ int prepare_percpu_nmi(unsigned int irq) { int ret = -EINVAL; WARN_ON(preemptible()); scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { if (WARN(!irq_is_nmi(scoped_irqdesc), "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n", irq)) return -EINVAL; ret = irq_nmi_setup(scoped_irqdesc); if (ret) pr_err("Failed to setup NMI delivery: irq %u\n", irq); } return ret; } /** * teardown_percpu_nmi - undoes NMI setup of IRQ line * @irq: Interrupt line from which CPU local NMI configuration should be removed * * This call undoes the setup done by prepare_percpu_nmi(). * * IRQ line should not be enabled for the current CPU. * As a CPU local operation, this should be called from non-preemptible * context. */ void teardown_percpu_nmi(unsigned int irq) { WARN_ON(preemptible()); scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { if (WARN_ON(!irq_is_nmi(scoped_irqdesc))) return; irq_nmi_teardown(scoped_irqdesc); } } static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { struct irq_chip *chip; int err = -EINVAL; do { chip = irq_data_get_irq_chip(data); if (WARN_ON_ONCE(!chip)) return -ENODEV; if (chip->irq_get_irqchip_state) break; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY data = data->parent_data; #else data = NULL; #endif } while (data); if (data) err = chip->irq_get_irqchip_state(data, which, state); return err; } /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. * @irq: Interrupt line that is forwarded to a VM * @which: One of IRQCHIP_STATE_* the caller wants to know about * @state: a pointer to a boolean where the state is to be stored * * This call snapshots the internal irqchip state of an interrupt, * returning into @state the bit corresponding to stage @which * * This function should be called with preemption disabled if the interrupt * controller has per-cpu registers. */ int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool *state) { scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc); return __irq_get_irqchip_state(data, which, state); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_get_irqchip_state); /** * irq_set_irqchip_state - set the state of a forwarded interrupt. * @irq: Interrupt line that is forwarded to a VM * @which: State to be restored (one of IRQCHIP_STATE_*) * @val: Value corresponding to @which * * This call sets the internal irqchip state of an interrupt, depending on * the value of @which. * * This function should be called with migration disabled if the interrupt * controller has per-cpu registers. */ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool val) { scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc); struct irq_chip *chip; do { chip = irq_data_get_irq_chip(data); if (WARN_ON_ONCE(!chip)) return -ENODEV; if (chip->irq_set_irqchip_state) break; data = irqd_get_parent_data(data); } while (data); if (data) return chip->irq_set_irqchip_state(data, which, val); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_irqchip_state); /** * irq_has_action - Check whether an interrupt is requested * @irq: The linux irq number * * Returns: A snapshot of the current state */ bool irq_has_action(unsigned int irq) { bool res; rcu_read_lock(); res = irq_desc_has_action(irq_to_desc(irq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(irq_has_action); /** * irq_check_status_bit - Check whether bits in the irq descriptor status are set * @irq: The linux irq number * @bitmask: The bitmask to evaluate * * Returns: True if one of the bits in @bitmask is set */ bool irq_check_status_bit(unsigned int irq, unsigned int bitmask) { struct irq_desc *desc; bool res = false; rcu_read_lock(); desc = irq_to_desc(irq); if (desc) res = !!(desc->status_use_accessors & bitmask); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(irq_check_status_bit); |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/hfsplus/super.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * */ #include <linux/module.h> #include <linux/init.h> #include <linux/pagemap.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/slab.h> #include <linux/vfs.h> #include <linux/nls.h> static struct inode *hfsplus_alloc_inode(struct super_block *sb); static void hfsplus_free_inode(struct inode *inode); #include "hfsplus_fs.h" #include "xattr.h" static int hfsplus_system_read_inode(struct inode *inode) { struct hfsplus_vh *vhdr = HFSPLUS_SB(inode->i_sb)->s_vhdr; switch (inode->i_ino) { case HFSPLUS_EXT_CNID: hfsplus_inode_read_fork(inode, &vhdr->ext_file); inode->i_mapping->a_ops = &hfsplus_btree_aops; break; case HFSPLUS_CAT_CNID: hfsplus_inode_read_fork(inode, &vhdr->cat_file); inode->i_mapping->a_ops = &hfsplus_btree_aops; break; case HFSPLUS_ALLOC_CNID: hfsplus_inode_read_fork(inode, &vhdr->alloc_file); inode->i_mapping->a_ops = &hfsplus_aops; break; case HFSPLUS_START_CNID: hfsplus_inode_read_fork(inode, &vhdr->start_file); break; case HFSPLUS_ATTR_CNID: hfsplus_inode_read_fork(inode, &vhdr->attr_file); inode->i_mapping->a_ops = &hfsplus_btree_aops; break; default: return -EIO; } return 0; } struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino) { struct hfs_find_data fd; struct inode *inode; int err; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; atomic_set(&HFSPLUS_I(inode)->opencnt, 0); HFSPLUS_I(inode)->first_blocks = 0; HFSPLUS_I(inode)->clump_blocks = 0; HFSPLUS_I(inode)->alloc_blocks = 0; HFSPLUS_I(inode)->cached_start = U32_MAX; HFSPLUS_I(inode)->cached_blocks = 0; memset(HFSPLUS_I(inode)->first_extents, 0, sizeof(hfsplus_extent_rec)); memset(HFSPLUS_I(inode)->cached_extents, 0, sizeof(hfsplus_extent_rec)); HFSPLUS_I(inode)->extent_state = 0; mutex_init(&HFSPLUS_I(inode)->extents_lock); HFSPLUS_I(inode)->rsrc_inode = NULL; HFSPLUS_I(inode)->create_date = 0; HFSPLUS_I(inode)->linkid = 0; HFSPLUS_I(inode)->flags = 0; HFSPLUS_I(inode)->fs_blocks = 0; HFSPLUS_I(inode)->userflags = 0; HFSPLUS_I(inode)->subfolders = 0; INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list); spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock); HFSPLUS_I(inode)->phys_size = 0; if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID || inode->i_ino == HFSPLUS_ROOT_CNID) { err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); if (!err) { err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); if (!err) err = hfsplus_cat_read_inode(inode, &fd); hfs_find_exit(&fd); } } else { err = hfsplus_system_read_inode(inode); } if (err) { iget_failed(inode); return ERR_PTR(err); } unlock_new_inode(inode); return inode; } static int hfsplus_system_write_inode(struct inode *inode) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; struct hfsplus_fork_raw *fork; struct hfs_btree *tree = NULL; switch (inode->i_ino) { case HFSPLUS_EXT_CNID: fork = &vhdr->ext_file; tree = sbi->ext_tree; break; case HFSPLUS_CAT_CNID: fork = &vhdr->cat_file; tree = sbi->cat_tree; break; case HFSPLUS_ALLOC_CNID: fork = &vhdr->alloc_file; break; case HFSPLUS_START_CNID: fork = &vhdr->start_file; break; case HFSPLUS_ATTR_CNID: fork = &vhdr->attr_file; tree = sbi->attr_tree; break; default: return -EIO; } if (fork->total_size != cpu_to_be64(inode->i_size)) { set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags); hfsplus_mark_mdb_dirty(inode->i_sb); } hfsplus_inode_write_fork(inode, fork); if (tree) { int err = hfs_btree_write(tree); if (err) { pr_err("b-tree write err: %d, ino %lu\n", err, inode->i_ino); return err; } } return 0; } static int hfsplus_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; hfs_dbg("ino %lu\n", inode->i_ino); err = hfsplus_ext_write_extent(inode); if (err) return err; if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID || inode->i_ino == HFSPLUS_ROOT_CNID) return hfsplus_cat_write_inode(inode); else return hfsplus_system_write_inode(inode); } static void hfsplus_evict_inode(struct inode *inode) { hfs_dbg("ino %lu\n", inode->i_ino); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL; iput(HFSPLUS_I(inode)->rsrc_inode); } } static int hfsplus_sync_fs(struct super_block *sb, int wait) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; int write_backup = 0; int error, error2; if (!wait) return 0; hfs_dbg("starting...\n"); /* * Explicitly write out the special metadata inodes. * * While these special inodes are marked as hashed and written * out peridocically by the flusher threads we redirty them * during writeout of normal inodes, and thus the life lock * prevents us from getting the latest state to disk. */ error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping); error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping); if (!error) error = error2; if (sbi->attr_tree) { error2 = filemap_write_and_wait(sbi->attr_tree->inode->i_mapping); if (!error) error = error2; } error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); if (!error) error = error2; mutex_lock(&sbi->vh_mutex); mutex_lock(&sbi->alloc_mutex); vhdr->free_blocks = cpu_to_be32(sbi->free_blocks); vhdr->next_cnid = cpu_to_be32(sbi->next_cnid); vhdr->folder_count = cpu_to_be32(sbi->folder_count); vhdr->file_count = cpu_to_be32(sbi->file_count); hfs_dbg("free_blocks %u, next_cnid %u, folder_count %u, file_count %u\n", sbi->free_blocks, sbi->next_cnid, sbi->folder_count, sbi->file_count); if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) { memcpy(sbi->s_backup_vhdr, sbi->s_vhdr, sizeof(*sbi->s_vhdr)); write_backup = 1; } error2 = hfsplus_submit_bio(sb, sbi->part_start + HFSPLUS_VOLHEAD_SECTOR, sbi->s_vhdr_buf, NULL, REQ_OP_WRITE); if (!error) error = error2; if (!write_backup) goto out; error2 = hfsplus_submit_bio(sb, sbi->part_start + sbi->sect_count - 2, sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE); if (!error) error2 = error; out: mutex_unlock(&sbi->alloc_mutex); mutex_unlock(&sbi->vh_mutex); if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) blkdev_issue_flush(sb->s_bdev); hfs_dbg("finished: err %d\n", error); return error; } static void delayed_sync_fs(struct work_struct *work) { int err; struct hfsplus_sb_info *sbi; sbi = container_of(work, struct hfsplus_sb_info, sync_work.work); spin_lock(&sbi->work_lock); sbi->work_queued = 0; spin_unlock(&sbi->work_lock); err = hfsplus_sync_fs(sbi->alloc_file->i_sb, 1); if (err) pr_err("delayed sync fs err %d\n", err); } void hfsplus_mark_mdb_dirty(struct super_block *sb) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); unsigned long delay; if (sb_rdonly(sb)) return; spin_lock(&sbi->work_lock); if (!sbi->work_queued) { delay = msecs_to_jiffies(dirty_writeback_interval * 10); queue_delayed_work(system_long_wq, &sbi->sync_work, delay); sbi->work_queued = 1; } spin_unlock(&sbi->work_lock); } static void delayed_free(struct rcu_head *p) { struct hfsplus_sb_info *sbi = container_of(p, struct hfsplus_sb_info, rcu); unload_nls(sbi->nls); kfree(sbi); } static void hfsplus_put_super(struct super_block *sb) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); hfs_dbg("starting...\n"); cancel_delayed_work_sync(&sbi->sync_work); if (!sb_rdonly(sb) && sbi->s_vhdr) { struct hfsplus_vh *vhdr = sbi->s_vhdr; vhdr->modify_date = hfsp_now2mt(); vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT); vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT); hfsplus_sync_fs(sb, 1); } iput(sbi->alloc_file); iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); call_rcu(&sbi->rcu, delayed_free); hfs_dbg("finished\n"); } static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = HFSPLUS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->total_blocks << sbi->fs_shift; buf->f_bfree = sbi->free_blocks << sbi->fs_shift; buf->f_bavail = buf->f_bfree; buf->f_files = 0xFFFFFFFF; buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = HFSPLUS_MAX_STRLEN; return 0; } static int hfsplus_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; sync_filesystem(sb); if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb)) return 0; if (!(fc->sb_flags & SB_RDONLY)) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n"); sb->s_flags |= SB_RDONLY; fc->sb_flags |= SB_RDONLY; } else if (test_bit(HFSPLUS_SB_FORCE, &sbi->flags)) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= SB_RDONLY; fc->sb_flags |= SB_RDONLY; } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) { pr_warn("filesystem is marked journaled, leaving read-only.\n"); sb->s_flags |= SB_RDONLY; fc->sb_flags |= SB_RDONLY; } } return 0; } static const struct super_operations hfsplus_sops = { .alloc_inode = hfsplus_alloc_inode, .free_inode = hfsplus_free_inode, .write_inode = hfsplus_write_inode, .evict_inode = hfsplus_evict_inode, .put_super = hfsplus_put_super, .sync_fs = hfsplus_sync_fs, .statfs = hfsplus_statfs, .show_options = hfsplus_show_options, }; static int hfsplus_fill_super(struct super_block *sb, struct fs_context *fc) { struct hfsplus_vh *vhdr; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); hfsplus_cat_entry entry; struct hfs_find_data fd; struct inode *root, *inode; struct qstr str; struct nls_table *nls; u64 last_fs_block, last_fs_page; int silent = fc->sb_flags & SB_SILENT; int err; mutex_init(&sbi->alloc_mutex); mutex_init(&sbi->vh_mutex); spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); err = -EINVAL; if (!sbi->nls) { /* try utf8 first, as this is the old default behaviour */ sbi->nls = load_nls("utf8"); if (!sbi->nls) sbi->nls = load_nls_default(); } /* temporarily use utf8 to correctly find the hidden dir below */ nls = sbi->nls; sbi->nls = load_nls("utf8"); if (!sbi->nls) { pr_err("unable to load nls for utf8\n"); goto out_unload_nls; } /* Grab the volume header */ if (hfsplus_read_wrapper(sb)) { if (!silent) pr_warn("unable to find HFS+ superblock\n"); goto out_unload_nls; } vhdr = sbi->s_vhdr; /* Copy parts of the volume header into the superblock */ sb->s_magic = HFSPLUS_VOLHEAD_SIG; if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION || be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) { pr_err("wrong filesystem version\n"); goto out_free_vhdr; } sbi->total_blocks = be32_to_cpu(vhdr->total_blocks); sbi->free_blocks = be32_to_cpu(vhdr->free_blocks); sbi->next_cnid = be32_to_cpu(vhdr->next_cnid); sbi->file_count = be32_to_cpu(vhdr->file_count); sbi->folder_count = be32_to_cpu(vhdr->folder_count); sbi->data_clump_blocks = be32_to_cpu(vhdr->data_clump_sz) >> sbi->alloc_blksz_shift; if (!sbi->data_clump_blocks) sbi->data_clump_blocks = 1; sbi->rsrc_clump_blocks = be32_to_cpu(vhdr->rsrc_clump_sz) >> sbi->alloc_blksz_shift; if (!sbi->rsrc_clump_blocks) sbi->rsrc_clump_blocks = 1; err = -EFBIG; last_fs_block = sbi->total_blocks - 1; last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >> PAGE_SHIFT; if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { pr_err("filesystem size too large\n"); goto out_free_vhdr; } /* Set up operations so we can load metadata */ sb->s_op = &hfsplus_sops; sb->s_maxbytes = MAX_LFS_FILESIZE; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { pr_warn("Filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && !sb_rdonly(sb)) { pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } err = -EINVAL; /* Load metadata objects (B*Trees) */ sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID); if (!sbi->ext_tree) { pr_err("failed to load extents file\n"); goto out_free_vhdr; } sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID); if (!sbi->cat_tree) { pr_err("failed to load catalog file\n"); goto out_close_ext_tree; } atomic_set(&sbi->attr_tree_state, HFSPLUS_EMPTY_ATTR_TREE); if (vhdr->attr_file.total_blocks != 0) { sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); if (!sbi->attr_tree) { pr_err("failed to load attributes file\n"); goto out_close_cat_tree; } atomic_set(&sbi->attr_tree_state, HFSPLUS_VALID_ATTR_TREE); } sb->s_xattr = hfsplus_xattr_handlers; inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { pr_err("failed to load allocation file\n"); err = PTR_ERR(inode); goto out_close_attr_tree; } sbi->alloc_file = inode; /* Load the root directory */ root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID); if (IS_ERR(root)) { pr_err("failed to load root directory\n"); err = PTR_ERR(root); goto out_put_alloc_file; } set_default_d_op(sb, &hfsplus_dentry_operations); sb->s_root = d_make_root(root); if (!sb->s_root) { err = -ENOMEM; goto out_put_alloc_file; } str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1; str.name = HFSP_HIDDENDIR_NAME; err = hfs_find_init(sbi->cat_tree, &fd); if (err) goto out_put_root; err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str); if (unlikely(err < 0)) goto out_put_root; if (!hfs_brec_read(&fd, &entry, sizeof(entry))) { hfs_find_exit(&fd); if (entry.type != cpu_to_be16(HFSPLUS_FOLDER)) { err = -EIO; goto out_put_root; } inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id)); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_put_root; } sbi->hidden_dir = inode; } else hfs_find_exit(&fd); if (!sb_rdonly(sb)) { /* * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused * all three are registered with Apple for our use */ vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION); vhdr->modify_date = hfsp_now2mt(); be32_add_cpu(&vhdr->write_count, 1); vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); hfsplus_sync_fs(sb, 1); if (!sbi->hidden_dir) { mutex_lock(&sbi->vh_mutex); sbi->hidden_dir = hfsplus_new_inode(sb, root, S_IFDIR); if (!sbi->hidden_dir) { mutex_unlock(&sbi->vh_mutex); err = -ENOMEM; goto out_put_root; } err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str, sbi->hidden_dir); if (err) { mutex_unlock(&sbi->vh_mutex); goto out_put_hidden_dir; } err = hfsplus_init_security(sbi->hidden_dir, root, &str); if (err == -EOPNOTSUPP) err = 0; /* Operation is not supported. */ else if (err) { /* * Try to delete anyway without * error analysis. */ hfsplus_delete_cat(sbi->hidden_dir->i_ino, root, &str); mutex_unlock(&sbi->vh_mutex); goto out_put_hidden_dir; } mutex_unlock(&sbi->vh_mutex); hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY); } } unload_nls(sbi->nls); sbi->nls = nls; return 0; out_put_hidden_dir: cancel_delayed_work_sync(&sbi->sync_work); iput(sbi->hidden_dir); out_put_root: dput(sb->s_root); sb->s_root = NULL; out_put_alloc_file: iput(sbi->alloc_file); out_close_attr_tree: hfs_btree_close(sbi->attr_tree); out_close_cat_tree: hfs_btree_close(sbi->cat_tree); out_close_ext_tree: hfs_btree_close(sbi->ext_tree); out_free_vhdr: kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); out_unload_nls: unload_nls(sbi->nls); unload_nls(nls); kfree(sbi); return err; } MODULE_AUTHOR("Brad Boyer"); MODULE_DESCRIPTION("Extended Macintosh Filesystem"); MODULE_LICENSE("GPL"); static struct kmem_cache *hfsplus_inode_cachep; static struct inode *hfsplus_alloc_inode(struct super_block *sb) { struct hfsplus_inode_info *i; i = alloc_inode_sb(sb, hfsplus_inode_cachep, GFP_KERNEL); return i ? &i->vfs_inode : NULL; } static void hfsplus_free_inode(struct inode *inode) { kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode)); } #define HFSPLUS_INODE_SIZE sizeof(struct hfsplus_inode_info) static int hfsplus_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, hfsplus_fill_super); } static void hfsplus_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations hfsplus_context_ops = { .parse_param = hfsplus_parse_param, .get_tree = hfsplus_get_tree, .reconfigure = hfsplus_reconfigure, .free = hfsplus_free_fc, }; static int hfsplus_init_fs_context(struct fs_context *fc) { struct hfsplus_sb_info *sbi; sbi = kzalloc(sizeof(struct hfsplus_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; if (fc->purpose != FS_CONTEXT_FOR_RECONFIGURE) hfsplus_fill_defaults(sbi); fc->s_fs_info = sbi; fc->ops = &hfsplus_context_ops; return 0; } static struct file_system_type hfsplus_fs_type = { .owner = THIS_MODULE, .name = "hfsplus", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = hfsplus_init_fs_context, }; MODULE_ALIAS_FS("hfsplus"); static void hfsplus_init_once(void *p) { struct hfsplus_inode_info *i = p; inode_init_once(&i->vfs_inode); } static int __init init_hfsplus_fs(void) { int err; hfsplus_inode_cachep = kmem_cache_create("hfsplus_icache", HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfsplus_init_once); if (!hfsplus_inode_cachep) return -ENOMEM; err = hfsplus_create_attr_tree_cache(); if (err) goto destroy_inode_cache; err = register_filesystem(&hfsplus_fs_type); if (err) goto destroy_attr_tree_cache; return 0; destroy_attr_tree_cache: hfsplus_destroy_attr_tree_cache(); destroy_inode_cache: kmem_cache_destroy(hfsplus_inode_cachep); return err; } static void __exit exit_hfsplus_fs(void) { unregister_filesystem(&hfsplus_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); hfsplus_destroy_attr_tree_cache(); kmem_cache_destroy(hfsplus_inode_cachep); } module_init(init_hfsplus_fs) module_exit(exit_hfsplus_fs) |
| 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 | /* * Linux Security Module interfaces * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2016 Mellanox Techonologies * * 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. * * Due to this file being licensed under the GPL there is controversy over * whether this permits you to write a module that #includes this file * without placing your module under the GPL. Please consult a lawyer for * advice before doing this. * */ #ifndef __LINUX_LSM_HOOKS_H #define __LINUX_LSM_HOOKS_H #include <uapi/linux/lsm.h> #include <linux/security.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/xattr.h> #include <linux/static_call.h> #include <linux/unroll.h> #include <linux/jump_label.h> #include <linux/lsm_count.h> union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" #undef LSM_HOOK void *lsm_func_addr; }; /* * @key: static call key as defined by STATIC_CALL_KEY * @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP * @hl: The security_hook_list as initialized by the owning LSM. * @active: Enabled when the static call has an LSM hook associated. */ struct lsm_static_call { struct static_call_key *key; void *trampoline; struct security_hook_list *hl; /* this needs to be true or false based on what the key defaults to */ struct static_key_false *active; } __randomize_layout; /* * Table of the static calls for each LSM hook. * Once the LSMs are initialized, their callbacks will be copied to these * tables such that the calls are filled backwards (from last to first). * This way, we can jump directly to the first used static call, and execute * all of them after. This essentially makes the entry point * dynamic to adapt the number of static calls to the number of callbacks. */ struct lsm_static_calls_table { #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ struct lsm_static_call NAME[MAX_LSM_COUNT]; #include <linux/lsm_hook_defs.h> #undef LSM_HOOK } __packed __randomize_layout; /** * struct lsm_id - Identify a Linux Security Module. * @lsm: name of the LSM, must be approved by the LSM maintainers * @id: LSM ID number from uapi/linux/lsm.h * * Contains the information that identifies the LSM. */ struct lsm_id { const char *name; u64 id; }; /* * Security module hook list structure. * For use with generic list macros for common operations. * * struct security_hook_list - Contents of a cacheable, mappable object. * @scalls: The beginning of the array of static calls assigned to this hook. * @hook: The callback for the hook. * @lsm: The name of the lsm that owns this hook. */ struct security_hook_list { struct lsm_static_call *scalls; union security_list_options hook; const struct lsm_id *lsmid; } __randomize_layout; /* * Security blob size or offset data. */ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_ib; int lbs_inode; int lbs_sock; int lbs_superblock; int lbs_ipc; int lbs_key; int lbs_msg_msg; int lbs_perf_event; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ int lbs_tun_dev; int lbs_bdev; int lbs_bpf_map; int lbs_bpf_prog; int lbs_bpf_token; }; /* * LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void * LSM hooks (in include/linux/lsm_hook_defs.h). */ #define LSM_RET_VOID ((void) 0) /* * Initializing a security_hook_list structure takes * up a lot of space in a source file. This macro takes * care of the common case and reduces the amount of * text involved. */ #define LSM_HOOK_INIT(NAME, HOOK) \ { \ .scalls = static_calls_table.NAME, \ .hook = { .NAME = HOOK } \ } extern void security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) enum lsm_order { LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ LSM_ORDER_MUTABLE = 0, LSM_ORDER_LAST = 1, /* This is only for integrity. */ }; struct lsm_info { const char *name; /* Required. */ enum lsm_order order; /* Optional: default is LSM_ORDER_MUTABLE */ unsigned long flags; /* Optional: flags describing LSM */ int *enabled; /* Optional: controlled by CONFIG_LSM */ int (*init)(void); /* Required. */ struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */ }; #define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(".lsm_info.init") \ __aligned(sizeof(unsigned long)) #define DEFINE_EARLY_LSM(lsm) \ static struct lsm_info __early_lsm_##lsm \ __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) /* DO NOT tamper with these variables outside of the LSM framework */ extern char *lsm_names; extern struct lsm_static_calls_table static_calls_table __ro_after_init; extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; /** * lsm_get_xattr_slot - Return the next available slot and increment the index * @xattrs: array storing LSM-provided xattrs * @xattr_count: number of already stored xattrs (updated) * * Retrieve the first available slot in the @xattrs array to fill with an xattr, * and increment @xattr_count. * * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. */ static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, int *xattr_count) { if (unlikely(!xattrs)) return NULL; return &xattrs[(*xattr_count)++]; } #endif /* ! __LINUX_LSM_HOOKS_H */ |
| 1 16 2 1 1 15 16 7 7 7 1 1 1 6 6 7 5 5 5 6 6 6 12 12 11 7 8 9 1 8 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct pause_req_info { struct ethnl_req_info base; enum ethtool_mac_stats_src src; }; #define PAUSE_REQINFO(__req_base) \ container_of(__req_base, struct pause_req_info, base) struct pause_reply_data { struct ethnl_reply_data base; struct ethtool_pauseparam pauseparam; struct ethtool_pause_stats pausestat; }; #define PAUSE_REPDATA(__reply_base) \ container_of(__reply_base, struct pause_reply_data, base) const struct nla_policy ethnl_pause_get_policy[] = { [ETHTOOL_A_PAUSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), [ETHTOOL_A_PAUSE_STATS_SRC] = NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; static int pause_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, struct netlink_ext_ack *extack) { enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; struct pause_req_info *req_info = PAUSE_REQINFO(req_base); if (tb[ETHTOOL_A_PAUSE_STATS_SRC]) { if (!(req_base->flags & ETHTOOL_FLAG_STATS)) { NL_SET_ERR_MSG_MOD(extack, "ETHTOOL_FLAG_STATS must be set when requesting a source of stats"); return -EINVAL; } src = nla_get_u32(tb[ETHTOOL_A_PAUSE_STATS_SRC]); } req_info->src = src; return 0; } static int pause_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { const struct pause_req_info *req_info = PAUSE_REQINFO(req_base); struct pause_reply_data *data = PAUSE_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; ethtool_stats_init((u64 *)&data->pausestat, sizeof(data->pausestat) / 8); data->pausestat.src = src; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; } dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); if (req_base->flags & ETHTOOL_FLAG_STATS && dev->ethtool_ops->get_pause_stats) dev->ethtool_ops->get_pause_stats(dev, &data->pausestat); ethnl_ops_complete(dev); return 0; } static int pause_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { int n = nla_total_size(sizeof(u8)) + /* _PAUSE_AUTONEG */ nla_total_size(sizeof(u8)) + /* _PAUSE_RX */ nla_total_size(sizeof(u8)); /* _PAUSE_TX */ if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ nla_total_size(sizeof(u32)) + /* _PAUSE_STATS_SRC */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype, u16 padtype) { if (val == ETHTOOL_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, padtype)) return -EMSGSIZE; return 0; } static int pause_put_stats(struct sk_buff *skb, const struct ethtool_pause_stats *pause_stats) { const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD; struct nlattr *nest; if (nla_put_u32(skb, ETHTOOL_A_PAUSE_STATS_SRC, pause_stats->src)) return -EMSGSIZE; nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS); if (!nest) return -EMSGSIZE; if (ethtool_put_stat(skb, pause_stats->tx_pause_frames, ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) || ethtool_put_stat(skb, pause_stats->rx_pause_frames, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int pause_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pause_reply_data *data = PAUSE_REPDATA(reply_base); const struct ethtool_pauseparam *pauseparam = &data->pauseparam; if (nla_put_u8(skb, ETHTOOL_A_PAUSE_AUTONEG, !!pauseparam->autoneg) || nla_put_u8(skb, ETHTOOL_A_PAUSE_RX, !!pauseparam->rx_pause) || nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause)) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && pause_put_stats(skb, &data->pausestat)) return -EMSGSIZE; return 0; } /* PAUSE_SET */ const struct nla_policy ethnl_pause_set_policy[] = { [ETHTOOL_A_PAUSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_TX] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_STATS_SRC] = { .type = NLA_REJECT }, }; static int ethnl_set_pause_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_pauseparam && ops->set_pauseparam ? 1 : -EOPNOTSUPP; } static int ethnl_set_pause(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; struct ethtool_pauseparam params = {}; struct nlattr **tb = info->attrs; bool mod = false; int ret; dev->ethtool_ops->get_pauseparam(dev, ¶ms); ethnl_update_bool32(¶ms.autoneg, tb[ETHTOOL_A_PAUSE_AUTONEG], &mod); ethnl_update_bool32(¶ms.rx_pause, tb[ETHTOOL_A_PAUSE_RX], &mod); ethnl_update_bool32(¶ms.tx_pause, tb[ETHTOOL_A_PAUSE_TX], &mod); if (!mod) return 0; ret = dev->ethtool_ops->set_pauseparam(dev, ¶ms); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_pause_request_ops = { .request_cmd = ETHTOOL_MSG_PAUSE_GET, .reply_cmd = ETHTOOL_MSG_PAUSE_GET_REPLY, .hdr_attr = ETHTOOL_A_PAUSE_HEADER, .req_info_size = sizeof(struct pause_req_info), .reply_data_size = sizeof(struct pause_reply_data), .parse_request = pause_parse_request, .prepare_data = pause_prepare_data, .reply_size = pause_reply_size, .fill_reply = pause_fill_reply, .set_validate = ethnl_set_pause_validate, .set = ethnl_set_pause, .set_ntf_cmd = ETHTOOL_MSG_PAUSE_NTF, }; |
| 1 33 1 33 1 1 32 33 33 33 21 21 21 21 21 21 21 21 21 21 33 33 33 33 33 33 33 33 33 33 33 48 48 48 48 48 48 48 110 110 110 109 109 109 110 66 110 110 110 110 110 110 | 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 | /* * Mu-Law conversion Plug-In Interface * Copyright (c) 1999 by Jaroslav Kysela <perex@perex.cz> * Uros Bizjak <uros@kss-loka.si> * * Based on reference implementation by Sun Microsystems, Inc. * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library 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 Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #include <linux/time.h> #include <sound/core.h> #include <sound/pcm.h> #include "pcm_plugin.h" #define SIGN_BIT (0x80) /* Sign bit for a u-law byte. */ #define QUANT_MASK (0xf) /* Quantization field mask. */ #define NSEGS (8) /* Number of u-law segments. */ #define SEG_SHIFT (4) /* Left shift for segment number. */ #define SEG_MASK (0x70) /* Segment field mask. */ static inline int val_seg(int val) { int r = 0; val >>= 7; if (val & 0xf0) { val >>= 4; r += 4; } if (val & 0x0c) { val >>= 2; r += 2; } if (val & 0x02) r += 1; return r; } #define BIAS (0x84) /* Bias for linear code. */ /* * linear2ulaw() - Convert a linear PCM value to u-law * * In order to simplify the encoding process, the original linear magnitude * is biased by adding 33 which shifts the encoding range from (0 - 8158) to * (33 - 8191). The result can be seen in the following encoding table: * * Biased Linear Input Code Compressed Code * ------------------------ --------------- * 00000001wxyza 000wxyz * 0000001wxyzab 001wxyz * 000001wxyzabc 010wxyz * 00001wxyzabcd 011wxyz * 0001wxyzabcde 100wxyz * 001wxyzabcdef 101wxyz * 01wxyzabcdefg 110wxyz * 1wxyzabcdefgh 111wxyz * * Each biased linear code has a leading 1 which identifies the segment * number. The value of the segment number is equal to 7 minus the number * of leading 0's. The quantization interval is directly available as the * four bits wxyz. * The trailing bits (a - h) are ignored. * * Ordinarily the complement of the resulting code word is used for * transmission, and so the code word is complemented before it is returned. * * For further information see John C. Bellamy's Digital Telephony, 1982, * John Wiley & Sons, pps 98-111 and 472-476. */ static unsigned char linear2ulaw(int pcm_val) /* 2's complement (16-bit range) */ { int mask; int seg; unsigned char uval; /* Get the sign and the magnitude of the value. */ if (pcm_val < 0) { pcm_val = BIAS - pcm_val; mask = 0x7F; } else { pcm_val += BIAS; mask = 0xFF; } if (pcm_val > 0x7FFF) pcm_val = 0x7FFF; /* Convert the scaled magnitude to segment number. */ seg = val_seg(pcm_val); /* * Combine the sign, segment, quantization bits; * and complement the code word. */ uval = (seg << 4) | ((pcm_val >> (seg + 3)) & 0xF); return uval ^ mask; } /* * ulaw2linear() - Convert a u-law value to 16-bit linear PCM * * First, a biased linear code is derived from the code word. An unbiased * output can then be obtained by subtracting 33 from the biased code. * * Note that this function expects to be passed the complement of the * original code word. This is in keeping with ISDN conventions. */ static int ulaw2linear(unsigned char u_val) { int t; /* Complement to obtain normal u-law value. */ u_val = ~u_val; /* * Extract and bias the quantization bits. Then * shift up by the segment number and subtract out the bias. */ t = ((u_val & QUANT_MASK) << 3) + BIAS; t <<= ((unsigned)u_val & SEG_MASK) >> SEG_SHIFT; return ((u_val & SIGN_BIT) ? (BIAS - t) : (t - BIAS)); } /* * Basic Mu-Law plugin */ typedef void (*mulaw_f)(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames); struct mulaw_priv { mulaw_f func; int cvt_endian; /* need endian conversion? */ unsigned int native_ofs; /* byte offset in native format */ unsigned int copy_ofs; /* byte offset in s16 format */ unsigned int native_bytes; /* byte size of the native format */ unsigned int copy_bytes; /* bytes to copy per conversion */ u16 flip; /* MSB flip for signedness, done after endian conversion */ }; static inline void cvt_s16_to_native(struct mulaw_priv *data, unsigned char *dst, u16 sample) { sample ^= data->flip; if (data->cvt_endian) sample = swab16(sample); if (data->native_bytes > data->copy_bytes) memset(dst, 0, data->native_bytes); memcpy(dst + data->native_ofs, (char *)&sample + data->copy_ofs, data->copy_bytes); } static void mulaw_decode(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { struct mulaw_priv *data = (struct mulaw_priv *)plugin->extra_data; int channel; int nchannels = plugin->src_format.channels; for (channel = 0; channel < nchannels; ++channel) { char *src; char *dst; int src_step, dst_step; snd_pcm_uframes_t frames1; if (!src_channels[channel].enabled) { if (dst_channels[channel].wanted) snd_pcm_area_silence(&dst_channels[channel].area, 0, frames, plugin->dst_format.format); dst_channels[channel].enabled = 0; continue; } dst_channels[channel].enabled = 1; src = src_channels[channel].area.addr + src_channels[channel].area.first / 8; dst = dst_channels[channel].area.addr + dst_channels[channel].area.first / 8; src_step = src_channels[channel].area.step / 8; dst_step = dst_channels[channel].area.step / 8; frames1 = frames; while (frames1-- > 0) { signed short sample = ulaw2linear(*src); cvt_s16_to_native(data, dst, sample); src += src_step; dst += dst_step; } } } static inline signed short cvt_native_to_s16(struct mulaw_priv *data, unsigned char *src) { u16 sample = 0; memcpy((char *)&sample + data->copy_ofs, src + data->native_ofs, data->copy_bytes); if (data->cvt_endian) sample = swab16(sample); sample ^= data->flip; return (signed short)sample; } static void mulaw_encode(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { struct mulaw_priv *data = (struct mulaw_priv *)plugin->extra_data; int channel; int nchannels = plugin->src_format.channels; for (channel = 0; channel < nchannels; ++channel) { char *src; char *dst; int src_step, dst_step; snd_pcm_uframes_t frames1; if (!src_channels[channel].enabled) { if (dst_channels[channel].wanted) snd_pcm_area_silence(&dst_channels[channel].area, 0, frames, plugin->dst_format.format); dst_channels[channel].enabled = 0; continue; } dst_channels[channel].enabled = 1; src = src_channels[channel].area.addr + src_channels[channel].area.first / 8; dst = dst_channels[channel].area.addr + dst_channels[channel].area.first / 8; src_step = src_channels[channel].area.step / 8; dst_step = dst_channels[channel].area.step / 8; frames1 = frames; while (frames1-- > 0) { signed short sample = cvt_native_to_s16(data, src); *dst = linear2ulaw(sample); src += src_step; dst += dst_step; } } } static snd_pcm_sframes_t mulaw_transfer(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { struct mulaw_priv *data; if (snd_BUG_ON(!plugin || !src_channels || !dst_channels)) return -ENXIO; if (frames == 0) return 0; #ifdef CONFIG_SND_DEBUG { unsigned int channel; for (channel = 0; channel < plugin->src_format.channels; channel++) { if (snd_BUG_ON(src_channels[channel].area.first % 8 || src_channels[channel].area.step % 8)) return -ENXIO; if (snd_BUG_ON(dst_channels[channel].area.first % 8 || dst_channels[channel].area.step % 8)) return -ENXIO; } } #endif if (frames > dst_channels[0].frames) frames = dst_channels[0].frames; data = (struct mulaw_priv *)plugin->extra_data; data->func(plugin, src_channels, dst_channels, frames); return frames; } static void init_data(struct mulaw_priv *data, snd_pcm_format_t format) { #ifdef SNDRV_LITTLE_ENDIAN data->cvt_endian = snd_pcm_format_big_endian(format) > 0; #else data->cvt_endian = snd_pcm_format_little_endian(format) > 0; #endif if (!snd_pcm_format_signed(format)) data->flip = 0x8000; data->native_bytes = snd_pcm_format_physical_width(format) / 8; data->copy_bytes = data->native_bytes < 2 ? 1 : 2; if (snd_pcm_format_little_endian(format)) { data->native_ofs = data->native_bytes - data->copy_bytes; data->copy_ofs = 2 - data->copy_bytes; } else { /* S24 in 4bytes need an 1 byte offset */ data->native_ofs = data->native_bytes - snd_pcm_format_width(format) / 8; } } int snd_pcm_plugin_build_mulaw(struct snd_pcm_substream *plug, struct snd_pcm_plugin_format *src_format, struct snd_pcm_plugin_format *dst_format, struct snd_pcm_plugin **r_plugin) { int err; struct mulaw_priv *data; struct snd_pcm_plugin *plugin; struct snd_pcm_plugin_format *format; mulaw_f func; if (snd_BUG_ON(!r_plugin)) return -ENXIO; *r_plugin = NULL; if (snd_BUG_ON(src_format->rate != dst_format->rate)) return -ENXIO; if (snd_BUG_ON(src_format->channels != dst_format->channels)) return -ENXIO; if (dst_format->format == SNDRV_PCM_FORMAT_MU_LAW) { format = src_format; func = mulaw_encode; } else if (src_format->format == SNDRV_PCM_FORMAT_MU_LAW) { format = dst_format; func = mulaw_decode; } else { snd_BUG(); return -EINVAL; } if (!snd_pcm_format_linear(format->format)) return -EINVAL; err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion", src_format, dst_format, sizeof(struct mulaw_priv), &plugin); if (err < 0) return err; data = (struct mulaw_priv *)plugin->extra_data; data->func = func; init_data(data, format->format); plugin->transfer = mulaw_transfer; *r_plugin = plugin; return 0; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Basic Node interface support */ #include <linux/module.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/mempolicy.h> #include <linux/vmstat.h> #include <linux/notifier.h> #include <linux/node.h> #include <linux/hugetlb.h> #include <linux/compaction.h> #include <linux/cpumask.h> #include <linux/topology.h> #include <linux/nodemask.h> #include <linux/cpu.h> #include <linux/device.h> #include <linux/pm_runtime.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/memblock.h> static const struct bus_type node_subsys = { .name = "node", .dev_name = "node", }; static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct node *node_dev = to_node(dev); cpumask_var_t mask; ssize_t n; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return 0; cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask); n = cpumap_print_bitmask_to_buf(buf, mask, off, count); free_cpumask_var(mask); return n; } static const BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES); static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct node *node_dev = to_node(dev); cpumask_var_t mask; ssize_t n; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return 0; cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask); n = cpumap_print_list_to_buf(buf, mask, off, count); free_cpumask_var(mask); return n; } static const BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES); /** * struct node_access_nodes - Access class device to hold user visible * relationships to other nodes. * @dev: Device for this memory access class * @list_node: List element in the node's access list * @access: The access class rank * @coord: Heterogeneous memory performance coordinates */ struct node_access_nodes { struct device dev; struct list_head list_node; unsigned int access; #ifdef CONFIG_HMEM_REPORTING struct access_coordinate coord; #endif }; #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev) static struct attribute *node_init_access_node_attrs[] = { NULL, }; static struct attribute *node_targ_access_node_attrs[] = { NULL, }; static const struct attribute_group initiators = { .name = "initiators", .attrs = node_init_access_node_attrs, }; static const struct attribute_group targets = { .name = "targets", .attrs = node_targ_access_node_attrs, }; static const struct attribute_group *node_access_node_groups[] = { &initiators, &targets, NULL, }; #ifdef CONFIG_MEMORY_HOTPLUG static BLOCKING_NOTIFIER_HEAD(node_chain); int register_node_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&node_chain, nb); } EXPORT_SYMBOL(register_node_notifier); void unregister_node_notifier(struct notifier_block *nb) { blocking_notifier_chain_unregister(&node_chain, nb); } EXPORT_SYMBOL(unregister_node_notifier); int node_notify(unsigned long val, void *v) { return blocking_notifier_call_chain(&node_chain, val, v); } #endif static void node_remove_accesses(struct node *node) { struct node_access_nodes *c, *cnext; list_for_each_entry_safe(c, cnext, &node->access_list, list_node) { list_del(&c->list_node); device_unregister(&c->dev); } } static void node_access_release(struct device *dev) { kfree(to_access_nodes(dev)); } static struct node_access_nodes *node_init_node_access(struct node *node, enum access_coordinate_class access) { struct node_access_nodes *access_node; struct device *dev; list_for_each_entry(access_node, &node->access_list, list_node) if (access_node->access == access) return access_node; access_node = kzalloc(sizeof(*access_node), GFP_KERNEL); if (!access_node) return NULL; access_node->access = access; dev = &access_node->dev; dev->parent = &node->dev; dev->release = node_access_release; dev->groups = node_access_node_groups; if (dev_set_name(dev, "access%u", access)) goto free; if (device_register(dev)) goto free_name; pm_runtime_no_callbacks(dev); list_add_tail(&access_node->list_node, &node->access_list); return access_node; free_name: kfree_const(dev->kobj.name); free: kfree(access_node); return NULL; } #ifdef CONFIG_HMEM_REPORTING #define ACCESS_ATTR(property) \ static ssize_t property##_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sysfs_emit(buf, "%u\n", \ to_access_nodes(dev)->coord.property); \ } \ static DEVICE_ATTR_RO(property) ACCESS_ATTR(read_bandwidth); ACCESS_ATTR(read_latency); ACCESS_ATTR(write_bandwidth); ACCESS_ATTR(write_latency); static struct attribute *access_attrs[] = { &dev_attr_read_bandwidth.attr, &dev_attr_read_latency.attr, &dev_attr_write_bandwidth.attr, &dev_attr_write_latency.attr, NULL, }; /** * node_set_perf_attrs - Set the performance values for given access class * @nid: Node identifier to be set * @coord: Heterogeneous memory performance coordinates * @access: The access class the for the given attributes */ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, enum access_coordinate_class access) { struct node_access_nodes *c; struct node *node; int i; if (WARN_ON_ONCE(!node_online(nid))) return; node = node_devices[nid]; c = node_init_node_access(node, access); if (!c) return; c->coord = *coord; for (i = 0; access_attrs[i] != NULL; i++) { if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i], "initiators")) { pr_info("failed to add performance attribute to node %d\n", nid); break; } } /* When setting CPU access coordinates, update mempolicy */ if (access == ACCESS_COORDINATE_CPU) { if (mempolicy_set_node_perf(nid, coord)) { pr_info("failed to set mempolicy attrs for node %d\n", nid); } } } EXPORT_SYMBOL_GPL(node_set_perf_attrs); /** * node_update_perf_attrs - Update the performance values for given access class * @nid: Node identifier to be updated * @coord: Heterogeneous memory performance coordinates * @access: The access class for the given attributes */ void node_update_perf_attrs(unsigned int nid, struct access_coordinate *coord, enum access_coordinate_class access) { struct node_access_nodes *access_node; struct node *node; int i; if (WARN_ON_ONCE(!node_online(nid))) return; node = node_devices[nid]; list_for_each_entry(access_node, &node->access_list, list_node) { if (access_node->access != access) continue; access_node->coord = *coord; for (i = 0; access_attrs[i]; i++) { sysfs_notify(&access_node->dev.kobj, NULL, access_attrs[i]->name); } break; } /* When setting CPU access coordinates, update mempolicy */ if (access != ACCESS_COORDINATE_CPU) return; if (mempolicy_set_node_perf(nid, coord)) pr_info("failed to set mempolicy attrs for node %d\n", nid); } EXPORT_SYMBOL_GPL(node_update_perf_attrs); /** * struct node_cache_info - Internal tracking for memory node caches * @dev: Device represeting the cache level * @node: List element for tracking in the node * @cache_attrs:Attributes for this cache level */ struct node_cache_info { struct device dev; struct list_head node; struct node_cache_attrs cache_attrs; }; #define to_cache_info(device) container_of(device, struct node_cache_info, dev) #define CACHE_ATTR(name, fmt) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sysfs_emit(buf, fmt "\n", \ to_cache_info(dev)->cache_attrs.name); \ } \ static DEVICE_ATTR_RO(name); CACHE_ATTR(size, "%llu") CACHE_ATTR(line_size, "%u") CACHE_ATTR(indexing, "%u") CACHE_ATTR(write_policy, "%u") CACHE_ATTR(address_mode, "%#x") static struct attribute *cache_attrs[] = { &dev_attr_indexing.attr, &dev_attr_size.attr, &dev_attr_line_size.attr, &dev_attr_write_policy.attr, &dev_attr_address_mode.attr, NULL, }; ATTRIBUTE_GROUPS(cache); static void node_cache_release(struct device *dev) { kfree(dev); } static void node_cacheinfo_release(struct device *dev) { struct node_cache_info *info = to_cache_info(dev); kfree(info); } static void node_init_cache_dev(struct node *node) { struct device *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return; device_initialize(dev); dev->parent = &node->dev; dev->release = node_cache_release; if (dev_set_name(dev, "memory_side_cache")) goto put_device; if (device_add(dev)) goto put_device; pm_runtime_no_callbacks(dev); node->cache_dev = dev; return; put_device: put_device(dev); } /** * node_add_cache() - add cache attribute to a memory node * @nid: Node identifier that has new cache attributes * @cache_attrs: Attributes for the cache being added */ void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs) { struct node_cache_info *info; struct device *dev; struct node *node; if (!node_online(nid) || !node_devices[nid]) return; node = node_devices[nid]; list_for_each_entry(info, &node->cache_attrs, node) { if (info->cache_attrs.level == cache_attrs->level) { dev_warn(&node->dev, "attempt to add duplicate cache level:%d\n", cache_attrs->level); return; } } if (!node->cache_dev) node_init_cache_dev(node); if (!node->cache_dev) return; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return; dev = &info->dev; device_initialize(dev); dev->parent = node->cache_dev; dev->release = node_cacheinfo_release; dev->groups = cache_groups; if (dev_set_name(dev, "index%d", cache_attrs->level)) goto put_device; info->cache_attrs = *cache_attrs; if (device_add(dev)) { dev_warn(&node->dev, "failed to add cache level:%d\n", cache_attrs->level); goto put_device; } pm_runtime_no_callbacks(dev); list_add_tail(&info->node, &node->cache_attrs); return; put_device: put_device(dev); } static void node_remove_caches(struct node *node) { struct node_cache_info *info, *next; if (!node->cache_dev) return; list_for_each_entry_safe(info, next, &node->cache_attrs, node) { list_del(&info->node); device_unregister(&info->dev); } device_unregister(node->cache_dev); } static void node_init_caches(unsigned int nid) { INIT_LIST_HEAD(&node_devices[nid]->cache_attrs); } #else static void node_init_caches(unsigned int nid) { } static void node_remove_caches(struct node *node) { } #endif #define K(x) ((x) << (PAGE_SHIFT - 10)) static ssize_t node_read_meminfo(struct device *dev, struct device_attribute *attr, char *buf) { int len = 0; int nid = dev->id; struct pglist_data *pgdat = NODE_DATA(nid); struct sysinfo i; unsigned long sreclaimable, sunreclaimable; unsigned long swapcached = 0; si_meminfo_node(&i, nid); sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B); sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B); #ifdef CONFIG_SWAP swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE); #endif len = sysfs_emit_at(buf, len, "Node %d MemTotal: %8lu kB\n" "Node %d MemFree: %8lu kB\n" "Node %d MemUsed: %8lu kB\n" "Node %d SwapCached: %8lu kB\n" "Node %d Active: %8lu kB\n" "Node %d Inactive: %8lu kB\n" "Node %d Active(anon): %8lu kB\n" "Node %d Inactive(anon): %8lu kB\n" "Node %d Active(file): %8lu kB\n" "Node %d Inactive(file): %8lu kB\n" "Node %d Unevictable: %8lu kB\n" "Node %d Mlocked: %8lu kB\n", nid, K(i.totalram), nid, K(i.freeram), nid, K(i.totalram - i.freeram), nid, K(swapcached), nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) + node_page_state(pgdat, NR_ACTIVE_FILE)), nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) + node_page_state(pgdat, NR_INACTIVE_FILE)), nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)), nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)), nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)), nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)), nid, K(node_page_state(pgdat, NR_UNEVICTABLE)), nid, K(sum_zone_node_page_state(nid, NR_MLOCK))); #ifdef CONFIG_HIGHMEM len += sysfs_emit_at(buf, len, "Node %d HighTotal: %8lu kB\n" "Node %d HighFree: %8lu kB\n" "Node %d LowTotal: %8lu kB\n" "Node %d LowFree: %8lu kB\n", nid, K(i.totalhigh), nid, K(i.freehigh), nid, K(i.totalram - i.totalhigh), nid, K(i.freeram - i.freehigh)); #endif len += sysfs_emit_at(buf, len, "Node %d Dirty: %8lu kB\n" "Node %d Writeback: %8lu kB\n" "Node %d FilePages: %8lu kB\n" "Node %d Mapped: %8lu kB\n" "Node %d AnonPages: %8lu kB\n" "Node %d Shmem: %8lu kB\n" "Node %d KernelStack: %8lu kB\n" #ifdef CONFIG_SHADOW_CALL_STACK "Node %d ShadowCallStack:%8lu kB\n" #endif "Node %d PageTables: %8lu kB\n" "Node %d SecPageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" "Node %d WritebackTmp: %8lu kB\n" "Node %d KReclaimable: %8lu kB\n" "Node %d Slab: %8lu kB\n" "Node %d SReclaimable: %8lu kB\n" "Node %d SUnreclaim: %8lu kB\n" #ifdef CONFIG_TRANSPARENT_HUGEPAGE "Node %d AnonHugePages: %8lu kB\n" "Node %d ShmemHugePages: %8lu kB\n" "Node %d ShmemPmdMapped: %8lu kB\n" "Node %d FileHugePages: %8lu kB\n" "Node %d FilePmdMapped: %8lu kB\n" #endif #ifdef CONFIG_UNACCEPTED_MEMORY "Node %d Unaccepted: %8lu kB\n" #endif , nid, K(node_page_state(pgdat, NR_FILE_DIRTY)), nid, K(node_page_state(pgdat, NR_WRITEBACK)), nid, K(node_page_state(pgdat, NR_FILE_PAGES)), nid, K(node_page_state(pgdat, NR_FILE_MAPPED)), nid, K(node_page_state(pgdat, NR_ANON_MAPPED)), nid, K(i.sharedram), nid, node_page_state(pgdat, NR_KERNEL_STACK_KB), #ifdef CONFIG_SHADOW_CALL_STACK nid, node_page_state(pgdat, NR_KERNEL_SCS_KB), #endif nid, K(node_page_state(pgdat, NR_PAGETABLE)), nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), nid, 0UL, nid, 0UL, nid, 0UL, nid, K(sreclaimable + node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)), nid, K(sreclaimable + sunreclaimable), nid, K(sreclaimable), nid, K(sunreclaimable) #ifdef CONFIG_TRANSPARENT_HUGEPAGE , nid, K(node_page_state(pgdat, NR_ANON_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), nid, K(node_page_state(pgdat, NR_FILE_THPS)), nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED)) #endif #ifdef CONFIG_UNACCEPTED_MEMORY , nid, K(sum_zone_node_page_state(nid, NR_UNACCEPTED)) #endif ); len += hugetlb_report_node_meminfo(buf, len, nid); return len; } #undef K static DEVICE_ATTR(meminfo, 0444, node_read_meminfo, NULL); static ssize_t node_read_numastat(struct device *dev, struct device_attribute *attr, char *buf) { fold_vm_numa_events(); return sysfs_emit(buf, "numa_hit %lu\n" "numa_miss %lu\n" "numa_foreign %lu\n" "interleave_hit %lu\n" "local_node %lu\n" "other_node %lu\n", sum_zone_numa_event_state(dev->id, NUMA_HIT), sum_zone_numa_event_state(dev->id, NUMA_MISS), sum_zone_numa_event_state(dev->id, NUMA_FOREIGN), sum_zone_numa_event_state(dev->id, NUMA_INTERLEAVE_HIT), sum_zone_numa_event_state(dev->id, NUMA_LOCAL), sum_zone_numa_event_state(dev->id, NUMA_OTHER)); } static DEVICE_ATTR(numastat, 0444, node_read_numastat, NULL); static ssize_t node_read_vmstat(struct device *dev, struct device_attribute *attr, char *buf) { int nid = dev->id; struct pglist_data *pgdat = NODE_DATA(nid); int i; int len = 0; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) len += sysfs_emit_at(buf, len, "%s %lu\n", zone_stat_name(i), sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA fold_vm_numa_events(); for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) len += sysfs_emit_at(buf, len, "%s %lu\n", numa_stat_name(i), sum_zone_numa_event_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { unsigned long pages = node_page_state_pages(pgdat, i); if (vmstat_item_print_in_thp(i)) pages /= HPAGE_PMD_NR; len += sysfs_emit_at(buf, len, "%s %lu\n", node_stat_name(i), pages); } return len; } static DEVICE_ATTR(vmstat, 0444, node_read_vmstat, NULL); static ssize_t node_read_distance(struct device *dev, struct device_attribute *attr, char *buf) { int nid = dev->id; int len = 0; int i; /* * buf is currently PAGE_SIZE in length and each node needs 4 chars * at the most (distance + space or newline). */ BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE); for_each_online_node(i) { len += sysfs_emit_at(buf, len, "%s%d", i ? " " : "", node_distance(nid, i)); } len += sysfs_emit_at(buf, len, "\n"); return len; } static DEVICE_ATTR(distance, 0444, node_read_distance, NULL); static struct attribute *node_dev_attrs[] = { &dev_attr_meminfo.attr, &dev_attr_numastat.attr, &dev_attr_distance.attr, &dev_attr_vmstat.attr, NULL }; static const struct bin_attribute *node_dev_bin_attrs[] = { &bin_attr_cpumap, &bin_attr_cpulist, NULL }; static const struct attribute_group node_dev_group = { .attrs = node_dev_attrs, .bin_attrs = node_dev_bin_attrs, }; static const struct attribute_group *node_dev_groups[] = { &node_dev_group, #ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP &arch_node_dev_group, #endif #ifdef CONFIG_MEMORY_FAILURE &memory_failure_attr_group, #endif NULL }; static void node_device_release(struct device *dev) { kfree(to_node(dev)); } /* * register_node - Setup a sysfs device for a node. * @num - Node number to use when creating the device. * * Initialize and register the node device. */ static int register_node(struct node *node, int num) { int error; node->dev.id = num; node->dev.bus = &node_subsys; node->dev.release = node_device_release; node->dev.groups = node_dev_groups; error = device_register(&node->dev); if (error) { put_device(&node->dev); } else { hugetlb_register_node(node); compaction_register_node(node); reclaim_register_node(node); } return error; } /** * unregister_node - unregister a node device * @node: node going away * * Unregisters a node device @node. All the devices on the node must be * unregistered before calling this function. */ void unregister_node(struct node *node) { hugetlb_unregister_node(node); compaction_unregister_node(node); reclaim_unregister_node(node); node_remove_accesses(node); node_remove_caches(node); device_unregister(&node->dev); } struct node *node_devices[MAX_NUMNODES]; /* * register cpu under node */ int register_cpu_under_node(unsigned int cpu, unsigned int nid) { int ret; struct device *obj; if (!node_online(nid)) return 0; obj = get_cpu_device(cpu); if (!obj) return 0; ret = sysfs_create_link(&node_devices[nid]->dev.kobj, &obj->kobj, kobject_name(&obj->kobj)); if (ret) return ret; return sysfs_create_link(&obj->kobj, &node_devices[nid]->dev.kobj, kobject_name(&node_devices[nid]->dev.kobj)); } /** * register_memory_node_under_compute_node - link memory node to its compute * node for a given access class. * @mem_nid: Memory node number * @cpu_nid: Cpu node number * @access: Access class to register * * Description: * For use with platforms that may have separate memory and compute nodes. * This function will export node relationships linking which memory * initiator nodes can access memory targets at a given ranked access * class. */ int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, enum access_coordinate_class access) { struct node *init_node, *targ_node; struct node_access_nodes *initiator, *target; int ret; if (!node_online(cpu_nid) || !node_online(mem_nid)) return -ENODEV; init_node = node_devices[cpu_nid]; targ_node = node_devices[mem_nid]; initiator = node_init_node_access(init_node, access); target = node_init_node_access(targ_node, access); if (!initiator || !target) return -ENOMEM; ret = sysfs_add_link_to_group(&initiator->dev.kobj, "targets", &targ_node->dev.kobj, dev_name(&targ_node->dev)); if (ret) return ret; ret = sysfs_add_link_to_group(&target->dev.kobj, "initiators", &init_node->dev.kobj, dev_name(&init_node->dev)); if (ret) goto err; return 0; err: sysfs_remove_link_from_group(&initiator->dev.kobj, "targets", dev_name(&targ_node->dev)); return ret; } int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) { struct device *obj; if (!node_online(nid)) return 0; obj = get_cpu_device(cpu); if (!obj) return 0; sysfs_remove_link(&node_devices[nid]->dev.kobj, kobject_name(&obj->kobj)); sysfs_remove_link(&obj->kobj, kobject_name(&node_devices[nid]->dev.kobj)); return 0; } #ifdef CONFIG_MEMORY_HOTPLUG static void do_register_memory_block_under_node(int nid, struct memory_block *mem_blk) { int ret; ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, &mem_blk->dev.kobj, kobject_name(&mem_blk->dev.kobj)); if (ret && ret != -EEXIST) dev_err_ratelimited(&node_devices[nid]->dev, "can't create link to %s in sysfs (%d)\n", kobject_name(&mem_blk->dev.kobj), ret); ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj, &node_devices[nid]->dev.kobj, kobject_name(&node_devices[nid]->dev.kobj)); if (ret && ret != -EEXIST) dev_err_ratelimited(&mem_blk->dev, "can't create link to %s in sysfs (%d)\n", kobject_name(&node_devices[nid]->dev.kobj), ret); } /* * During hotplug we know that all pages in the memory block belong to the same * node. */ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk, void *arg) { int nid = *(int *)arg; do_register_memory_block_under_node(nid, mem_blk); return 0; } /* * Unregister a memory block device under the node it spans. Memory blocks * with multiple nodes cannot be offlined and therefore also never be removed. */ void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { if (mem_blk->nid == NUMA_NO_NODE) return; sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj, kobject_name(&mem_blk->dev.kobj)); sysfs_remove_link(&mem_blk->dev.kobj, kobject_name(&node_devices[mem_blk->nid]->dev.kobj)); } /* register all memory blocks under the corresponding nodes */ static void register_memory_blocks_under_nodes(void) { struct memblock_region *r; for_each_mem_region(r) { const unsigned long start_block_id = phys_to_block_id(r->base); const unsigned long end_block_id = phys_to_block_id(r->base + r->size - 1); const int nid = memblock_get_region_node(r); unsigned long block_id; if (!node_online(nid)) continue; for (block_id = start_block_id; block_id <= end_block_id; block_id++) { struct memory_block *mem; mem = find_memory_block_by_id(block_id); if (!mem) continue; memory_block_add_nid_early(mem, nid); do_register_memory_block_under_node(nid, mem); put_device(&mem->dev); } } } void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn, unsigned long end_pfn) { walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), (void *)&nid, register_mem_block_under_node_hotplug); return; } #endif /* CONFIG_MEMORY_HOTPLUG */ int register_one_node(int nid) { int error; int cpu; struct node *node; node = kzalloc(sizeof(struct node), GFP_KERNEL); if (!node) return -ENOMEM; INIT_LIST_HEAD(&node->access_list); node_devices[nid] = node; error = register_node(node_devices[nid], nid); if (error) { node_devices[nid] = NULL; return error; } /* link cpu under this node */ for_each_present_cpu(cpu) { if (cpu_to_node(cpu) == nid) register_cpu_under_node(cpu, nid); } node_init_caches(nid); return error; } void unregister_one_node(int nid) { if (!node_devices[nid]) return; unregister_node(node_devices[nid]); node_devices[nid] = NULL; } /* * node states attributes */ struct node_attr { struct device_attribute attr; enum node_states state; }; static ssize_t show_node_state(struct device *dev, struct device_attribute *attr, char *buf) { struct node_attr *na = container_of(attr, struct node_attr, attr); return sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&node_states[na->state])); } #define _NODE_ATTR(name, state) \ { __ATTR(name, 0444, show_node_state, NULL), state } static struct node_attr node_state_attr[] = { [N_POSSIBLE] = _NODE_ATTR(possible, N_POSSIBLE), [N_ONLINE] = _NODE_ATTR(online, N_ONLINE), [N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY), #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY), #endif [N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY), [N_CPU] = _NODE_ATTR(has_cpu, N_CPU), [N_GENERIC_INITIATOR] = _NODE_ATTR(has_generic_initiator, N_GENERIC_INITIATOR), }; static struct attribute *node_state_attrs[] = { &node_state_attr[N_POSSIBLE].attr.attr, &node_state_attr[N_ONLINE].attr.attr, &node_state_attr[N_NORMAL_MEMORY].attr.attr, #ifdef CONFIG_HIGHMEM &node_state_attr[N_HIGH_MEMORY].attr.attr, #endif &node_state_attr[N_MEMORY].attr.attr, &node_state_attr[N_CPU].attr.attr, &node_state_attr[N_GENERIC_INITIATOR].attr.attr, NULL }; static const struct attribute_group memory_root_attr_group = { .attrs = node_state_attrs, }; static const struct attribute_group *cpu_root_attr_groups[] = { &memory_root_attr_group, NULL, }; void __init node_dev_init(void) { int ret, i; BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES); BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES); ret = subsys_system_register(&node_subsys, cpu_root_attr_groups); if (ret) panic("%s() failed to register subsystem: %d\n", __func__, ret); /* * Create all node devices, which will properly link the node * to already created cpu devices. */ for_each_online_node(i) { ret = register_one_node(i); if (ret) panic("%s() failed to add node: %d\n", __func__, ret); } register_memory_blocks_under_nodes(); } |
| 262 262 262 19 19 19 18 222 221 222 221 222 1 222 1 221 220 222 10 10 10 10 10 217 12 221 221 220 222 12 222 221 222 222 10 10 10 10 221 110 110 110 110 110 109 110 110 110 110 110 7 7 7 7 7 105 7 110 110 109 110 110 110 7 110 109 110 110 7 7 7 7 110 110 110 110 110 110 110 104 104 104 104 134 135 136 136 77 77 77 77 77 77 77 77 77 22 22 22 21 20 21 21 21 21 21 20 20 2 20 18 18 18 18 12 12 1 1 1 263 264 264 264 130 129 1 263 263 264 264 264 2 263 264 256 262 256 264 263 108 262 133 264 264 264 136 136 134 136 80 81 81 81 81 81 81 81 81 122 122 122 109 110 109 110 110 110 104 103 104 104 104 104 104 104 104 1 103 104 104 104 104 33 103 103 10 10 10 10 10 8 8 8 8 8 129 10 127 9 9 9 9 9 9 9 9 129 129 129 129 129 129 129 129 129 129 129 128 128 128 128 128 116 8 116 116 116 116 116 1 116 116 116 116 116 116 116 116 110 116 2 2 116 128 81 90 90 90 90 110 110 110 110 110 109 110 68 68 110 110 116 116 8 115 115 8 8 8 8 8 2 8 8 8 8 225 225 226 226 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2002 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions work with the state functions in sctp_sm_statefuns.c * to implement the state operations. These functions implement the * steps which require modifying existing data structures. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * C. Robin <chris@hundredacre.ac.uk> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/utils.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/skbuff.h> #include <linux/random.h> /* for get_random_bytes */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static struct sctp_chunk *sctp_make_control(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp); static struct sctp_chunk *sctp_make_data(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp); static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp); static struct sctp_cookie_param *sctp_pack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *init_chunk, int *cookie_len, const __u8 *raw_addrs, int addrs_len); static int sctp_process_param(struct sctp_association *asoc, union sctp_params param, const union sctp_addr *peer_addr, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) { struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg; if (chunk->shkey) { struct sctp_shared_key *shkey = chunk->shkey; struct sctp_association *asoc = chunk->asoc; /* refcnt == 2 and !list_empty mean after this release, it's * not being used anywhere, and it's time to notify userland * that this shkey can be freed if it's been deactivated. */ if (shkey->deactivated && !list_empty(&shkey->key_list) && refcount_read(&shkey->refcnt) == 2) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, shkey->key_id, SCTP_AUTH_FREE_KEY, GFP_KERNEL); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_auth_shkey_release(chunk->shkey); } } static void sctp_control_set_owner_w(struct sctp_chunk *chunk) { struct sctp_association *asoc = chunk->asoc; struct sk_buff *skb = chunk->skb; /* TODO: properly account for control chunks. * To do it right we'll need: * 1) endpoint if association isn't known. * 2) proper memory accounting. * * For now don't do anything for now. */ if (chunk->auth) { chunk->shkey = asoc->shkey; sctp_auth_shkey_hold(chunk->shkey); } skb->sk = asoc ? asoc->base.sk : NULL; skb_shinfo(skb)->destructor_arg = chunk; skb->destructor = sctp_control_release_owner; } /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 2: The ECN capable field is reserved for future use of * Explicit Congestion Notification. */ static const struct sctp_paramhdr ecap_param = { SCTP_PARAM_ECN_CAPABLE, cpu_to_be16(sizeof(struct sctp_paramhdr)), }; static const struct sctp_paramhdr prsctp_param = { SCTP_PARAM_FWD_TSN_SUPPORT, cpu_to_be16(sizeof(struct sctp_paramhdr)), }; /* A helper to initialize an op error inside a provided chunk, as most * cause codes will be embedded inside an abort chunk. */ int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, size_t paylen) { struct sctp_errhdr err; __u16 len; /* Cause code constants are now defined in network order. */ err.cause = cause_code; len = sizeof(err) + paylen; err.length = htons(len); if (skb_tailroom(chunk->skb) < len) return -ENOSPC; chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); return 0; } /* 3.3.2 Initiation (INIT) (1) * * This chunk is used to initiate a SCTP association between two * endpoints. The format of the INIT chunk is shown below: * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 1 | Chunk Flags | Chunk Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Initiate Tag | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Advertised Receiver Window Credit (a_rwnd) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Number of Outbound Streams | Number of Inbound Streams | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Initial TSN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / Optional/Variable-Length Parameters / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * * The INIT chunk contains the following parameters. Unless otherwise * noted, each parameter MUST only be included once in the INIT chunk. * * Fixed Parameters Status * ---------------------------------------------- * Initiate Tag Mandatory * Advertised Receiver Window Credit Mandatory * Number of Outbound Streams Mandatory * Number of Inbound Streams Mandatory * Initial TSN Mandatory * * Variable Parameters Status Type Value * ------------------------------------------------------------- * IPv4 Address (Note 1) Optional 5 * IPv6 Address (Note 1) Optional 6 * Cookie Preservative Optional 9 * Reserved for ECN Capable (Note 2) Optional 32768 (0x8000) * Host Name Address (Note 3) Optional 11 * Supported Address Types (Note 4) Optional 12 */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, const struct sctp_bind_addr *bp, gfp_t gfp, int vparam_len) { struct sctp_supported_ext_param ext_param; struct sctp_adaptation_ind_param aiparam; struct sctp_paramhdr *auth_chunks = NULL; struct sctp_paramhdr *auth_hmacs = NULL; struct sctp_supported_addrs_param sat; struct sctp_endpoint *ep = asoc->ep; struct sctp_chunk *retval = NULL; int num_types, addrs_len = 0; struct sctp_inithdr init; union sctp_params addrs; struct sctp_sock *sp; __u8 extensions[5]; size_t chunksize; __be16 types[2]; int num_ext = 0; /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 1: The INIT chunks can contain multiple addresses that * can be IPv4 and/or IPv6 in any combination. */ /* Convert the provided bind address list to raw format. */ addrs = sctp_bind_addrs_to_raw(bp, &addrs_len, gfp); init.init_tag = htonl(asoc->c.my_vtag); init.a_rwnd = htonl(asoc->rwnd); init.num_outbound_streams = htons(asoc->c.sinit_num_ostreams); init.num_inbound_streams = htons(asoc->c.sinit_max_instreams); init.initial_tsn = htonl(asoc->c.initial_tsn); /* How many address types are needed? */ sp = sctp_sk(asoc->base.sk); num_types = sp->pf->supported_addrs(sp, types); chunksize = sizeof(init) + addrs_len; chunksize += SCTP_PAD4(SCTP_SAT_LEN(num_types)); if (asoc->ep->ecn_enable) chunksize += sizeof(ecap_param); if (asoc->ep->prsctp_enable) chunksize += sizeof(prsctp_param); /* ADDIP: Section 4.2.7: * An implementation supporting this extension [ADDIP] MUST list * the ASCONF,the ASCONF-ACK, and the AUTH chunks in its INIT and * INIT-ACK parameters. */ if (asoc->ep->asconf_enable) { extensions[num_ext] = SCTP_CID_ASCONF; extensions[num_ext+1] = SCTP_CID_ASCONF_ACK; num_ext += 2; } if (asoc->ep->reconf_enable) { extensions[num_ext] = SCTP_CID_RECONF; num_ext += 1; } if (sp->adaptation_ind) chunksize += sizeof(aiparam); if (asoc->ep->intl_enable) { extensions[num_ext] = SCTP_CID_I_DATA; num_ext += 1; } chunksize += vparam_len; /* Account for AUTH related parameters */ if (ep->auth_enable) { /* Add random parameter length*/ chunksize += sizeof(asoc->c.auth_random); /* Add HMACS parameter length if any were defined */ auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; extensions[num_ext] = SCTP_CID_AUTH; num_ext += 1; } /* If we have any extensions to report, account for that */ if (num_ext) chunksize += SCTP_PAD4(sizeof(ext_param) + num_ext); /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 3: An INIT chunk MUST NOT contain more than one Host * Name address parameter. Moreover, the sender of the INIT * MUST NOT combine any other address types with the Host Name * address in the INIT. The receiver of INIT MUST ignore any * other address types if the Host Name address parameter is * present in the received INIT chunk. * * PLEASE DO NOT FIXME [This version does not support Host Name.] */ retval = sctp_make_control(asoc, SCTP_CID_INIT, 0, chunksize, gfp); if (!retval) goto nodata; retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(init), &init); retval->param_hdr.v = sctp_addto_chunk(retval, addrs_len, addrs.v); /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 4: This parameter, when present, specifies all the * address types the sending endpoint can support. The absence * of this parameter indicates that the sending endpoint can * support any address type. */ sat.param_hdr.type = SCTP_PARAM_SUPPORTED_ADDRESS_TYPES; sat.param_hdr.length = htons(SCTP_SAT_LEN(num_types)); sctp_addto_chunk(retval, sizeof(sat), &sat); sctp_addto_chunk(retval, num_types * sizeof(__u16), &types); if (asoc->ep->ecn_enable) sctp_addto_chunk(retval, sizeof(ecap_param), &ecap_param); /* Add the supported extensions parameter. Be nice and add this * fist before addiding the parameters for the extensions themselves */ if (num_ext) { ext_param.param_hdr.type = SCTP_PARAM_SUPPORTED_EXT; ext_param.param_hdr.length = htons(sizeof(ext_param) + num_ext); sctp_addto_chunk(retval, sizeof(ext_param), &ext_param); sctp_addto_param(retval, num_ext, extensions); } if (asoc->ep->prsctp_enable) sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param); if (sp->adaptation_ind) { aiparam.param_hdr.type = SCTP_PARAM_ADAPTATION_LAYER_IND; aiparam.param_hdr.length = htons(sizeof(aiparam)); aiparam.adaptation_ind = htonl(sp->adaptation_ind); sctp_addto_chunk(retval, sizeof(aiparam), &aiparam); } /* Add SCTP-AUTH chunks to the parameter list */ if (ep->auth_enable) { sctp_addto_chunk(retval, sizeof(asoc->c.auth_random), asoc->c.auth_random); if (auth_hmacs) sctp_addto_chunk(retval, ntohs(auth_hmacs->length), auth_hmacs); if (auth_chunks) sctp_addto_chunk(retval, ntohs(auth_chunks->length), auth_chunks); } nodata: kfree(addrs.v); return retval; } struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, gfp_t gfp, int unkparam_len) { struct sctp_supported_ext_param ext_param; struct sctp_adaptation_ind_param aiparam; struct sctp_paramhdr *auth_chunks = NULL; struct sctp_paramhdr *auth_random = NULL; struct sctp_paramhdr *auth_hmacs = NULL; struct sctp_chunk *retval = NULL; struct sctp_cookie_param *cookie; struct sctp_inithdr initack; union sctp_params addrs; struct sctp_sock *sp; __u8 extensions[5]; size_t chunksize; int num_ext = 0; int cookie_len; int addrs_len; /* Note: there may be no addresses to embed. */ addrs = sctp_bind_addrs_to_raw(&asoc->base.bind_addr, &addrs_len, gfp); initack.init_tag = htonl(asoc->c.my_vtag); initack.a_rwnd = htonl(asoc->rwnd); initack.num_outbound_streams = htons(asoc->c.sinit_num_ostreams); initack.num_inbound_streams = htons(asoc->c.sinit_max_instreams); initack.initial_tsn = htonl(asoc->c.initial_tsn); /* FIXME: We really ought to build the cookie right * into the packet instead of allocating more fresh memory. */ cookie = sctp_pack_cookie(asoc->ep, asoc, chunk, &cookie_len, addrs.v, addrs_len); if (!cookie) goto nomem_cookie; /* Calculate the total size of allocation, include the reserved * space for reporting unknown parameters if it is specified. */ sp = sctp_sk(asoc->base.sk); chunksize = sizeof(initack) + addrs_len + cookie_len + unkparam_len; /* Tell peer that we'll do ECN only if peer advertised such cap. */ if (asoc->peer.ecn_capable) chunksize += sizeof(ecap_param); if (asoc->peer.prsctp_capable) chunksize += sizeof(prsctp_param); if (asoc->peer.asconf_capable) { extensions[num_ext] = SCTP_CID_ASCONF; extensions[num_ext+1] = SCTP_CID_ASCONF_ACK; num_ext += 2; } if (asoc->peer.reconf_capable) { extensions[num_ext] = SCTP_CID_RECONF; num_ext += 1; } if (sp->adaptation_ind) chunksize += sizeof(aiparam); if (asoc->peer.intl_capable) { extensions[num_ext] = SCTP_CID_I_DATA; num_ext += 1; } if (asoc->peer.auth_capable) { auth_random = (struct sctp_paramhdr *)asoc->c.auth_random; chunksize += ntohs(auth_random->length); auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; extensions[num_ext] = SCTP_CID_AUTH; num_ext += 1; } if (num_ext) chunksize += SCTP_PAD4(sizeof(ext_param) + num_ext); /* Now allocate and fill out the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_INIT_ACK, 0, chunksize, gfp); if (!retval) goto nomem_chunk; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it received the DATA or control chunk * to which it is replying. * * [INIT ACK back to where the INIT came from.] */ if (chunk->transport) retval->transport = sctp_assoc_lookup_paddr(asoc, &chunk->transport->ipaddr); retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(initack), &initack); retval->param_hdr.v = sctp_addto_chunk(retval, addrs_len, addrs.v); sctp_addto_chunk(retval, cookie_len, cookie); if (asoc->peer.ecn_capable) sctp_addto_chunk(retval, sizeof(ecap_param), &ecap_param); if (num_ext) { ext_param.param_hdr.type = SCTP_PARAM_SUPPORTED_EXT; ext_param.param_hdr.length = htons(sizeof(ext_param) + num_ext); sctp_addto_chunk(retval, sizeof(ext_param), &ext_param); sctp_addto_param(retval, num_ext, extensions); } if (asoc->peer.prsctp_capable) sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param); if (sp->adaptation_ind) { aiparam.param_hdr.type = SCTP_PARAM_ADAPTATION_LAYER_IND; aiparam.param_hdr.length = htons(sizeof(aiparam)); aiparam.adaptation_ind = htonl(sp->adaptation_ind); sctp_addto_chunk(retval, sizeof(aiparam), &aiparam); } if (asoc->peer.auth_capable) { sctp_addto_chunk(retval, ntohs(auth_random->length), auth_random); if (auth_hmacs) sctp_addto_chunk(retval, ntohs(auth_hmacs->length), auth_hmacs); if (auth_chunks) sctp_addto_chunk(retval, ntohs(auth_chunks->length), auth_chunks); } /* We need to remove the const qualifier at this point. */ retval->asoc = (struct sctp_association *) asoc; nomem_chunk: kfree(cookie); nomem_cookie: kfree(addrs.v); return retval; } /* 3.3.11 Cookie Echo (COOKIE ECHO) (10): * * This chunk is used only during the initialization of an association. * It is sent by the initiator of an association to its peer to complete * the initialization process. This chunk MUST precede any DATA chunk * sent within the association, but MAY be bundled with one or more DATA * chunks in the same packet. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 10 |Chunk Flags | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * / Cookie / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Chunk Flags: 8 bit * * Set to zero on transmit and ignored on receipt. * * Length: 16 bits (unsigned integer) * * Set to the size of the chunk in bytes, including the 4 bytes of * the chunk header and the size of the Cookie. * * Cookie: variable size * * This field must contain the exact cookie received in the * State Cookie parameter from the previous INIT ACK. * * An implementation SHOULD make the cookie as small as possible * to insure interoperability. */ struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; int cookie_len; void *cookie; cookie = asoc->peer.cookie; cookie_len = asoc->peer.cookie_len; /* Build a cookie echo chunk. */ retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ECHO, 0, cookie_len, GFP_ATOMIC); if (!retval) goto nodata; retval->subh.cookie_hdr = sctp_addto_chunk(retval, cookie_len, cookie); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [COOKIE ECHO back to where the INIT ACK came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* 3.3.12 Cookie Acknowledgement (COOKIE ACK) (11): * * This chunk is used only during the initialization of an * association. It is used to acknowledge the receipt of a COOKIE * ECHO chunk. This chunk MUST precede any DATA or SACK chunk sent * within the association, but MAY be bundled with one or more DATA * chunks or SACK chunk in the same SCTP packet. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 11 |Chunk Flags | Length = 4 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Chunk Flags: 8 bits * * Set to zero on transmit and ignored on receipt. */ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ACK, 0, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [COOKIE ACK back to where the COOKIE ECHO came from.] */ if (retval && chunk && chunk->transport) retval->transport = sctp_assoc_lookup_paddr(asoc, &chunk->transport->ipaddr); return retval; } /* * Appendix A: Explicit Congestion Notification: * CWR: * * RFC 2481 details a specific bit for a sender to send in the header of * its next outbound TCP segment to indicate to its peer that it has * reduced its congestion window. This is termed the CWR bit. For * SCTP the same indication is made by including the CWR chunk. * This chunk contains one data element, i.e. the TSN number that * was sent in the ECNE chunk. This element represents the lowest * TSN number in the datagram that was originally marked with the * CE bit. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Chunk Type=13 | Flags=00000000| Chunk Length = 8 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Lowest TSN Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Note: The CWR is considered a Control chunk. */ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; struct sctp_cwrhdr cwr; cwr.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_CWR, 0, sizeof(cwr), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecn_cwr_hdr = sctp_addto_chunk(retval, sizeof(cwr), &cwr); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [Report a reduced congestion window back to where the ECNE * came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* Make an ECNE chunk. This is a congestion experienced report. */ struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn) { struct sctp_chunk *retval; struct sctp_ecnehdr ecne; ecne.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_ECNE, 0, sizeof(ecne), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecne_hdr = sctp_addto_chunk(retval, sizeof(ecne), &ecne); nodata: return retval; } /* Make a DATA chunk for the given association from the provided * parameters. However, do not populate the data payload. */ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp) { struct sctp_chunk *retval; struct sctp_datahdr dp; /* We assign the TSN as LATE as possible, not here when * creating the chunk. */ memset(&dp, 0, sizeof(dp)); dp.ppid = sinfo->sinfo_ppid; dp.stream = htons(sinfo->sinfo_stream); /* Set the flags for an unordered send. */ if (sinfo->sinfo_flags & SCTP_UNORDERED) flags |= SCTP_DATA_UNORDERED; retval = sctp_make_data(asoc, flags, sizeof(dp) + len, gfp); if (!retval) return NULL; retval->subh.data_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp); memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo)); return retval; } /* Create a selective ackowledgement (SACK) for the given * association. This reports on which TSN's we've seen to date, * including duplicates and gaps. */ struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; struct sctp_chunk *retval; struct sctp_sackhdr sack; __u32 ctsn; int len; memset(gabs, 0, sizeof(gabs)); ctsn = sctp_tsnmap_get_ctsn(map); pr_debug("%s: sackCTSNAck sent:0x%x\n", __func__, ctsn); /* How much room is needed in the chunk? */ num_gabs = sctp_tsnmap_num_gabs(map, gabs); num_dup_tsns = sctp_tsnmap_num_dups(map); /* Initialize the SACK header. */ sack.cum_tsn_ack = htonl(ctsn); sack.a_rwnd = htonl(asoc->a_rwnd); sack.num_gap_ack_blocks = htons(num_gabs); sack.num_dup_tsns = htons(num_dup_tsns); len = sizeof(sack) + sizeof(struct sctp_gap_ack_block) * num_gabs + sizeof(__u32) * num_dup_tsns; /* Create the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_SACK, 0, len, GFP_ATOMIC); if (!retval) goto nodata; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, etc.) to the same destination transport * address from which it received the DATA or control chunk to * which it is replying. This rule should also be followed if * the endpoint is bundling DATA chunks together with the * reply chunk. * * However, when acknowledging multiple DATA chunks received * in packets from different source addresses in a single * SACK, the SACK chunk may be transmitted to one of the * destination transport addresses from which the DATA or * control chunks being acknowledged were received. * * [BUG: We do not implement the following paragraph. * Perhaps we should remember the last transport we used for a * SACK and avoid that (if possible) if we have seen any * duplicates. --piggy] * * When a receiver of a duplicate DATA chunk sends a SACK to a * multi- homed endpoint it MAY be beneficial to vary the * destination address and not use the source address of the * DATA chunk. The reason being that receiving a duplicate * from a multi-homed endpoint might indicate that the return * path (as specified in the source address of the DATA chunk) * for the SACK is broken. * * [Send to the address from which we last received a DATA chunk.] */ retval->transport = asoc->peer.last_data_from; retval->subh.sack_hdr = sctp_addto_chunk(retval, sizeof(sack), &sack); /* Add the gap ack block information. */ if (num_gabs) sctp_addto_chunk(retval, sizeof(__u32) * num_gabs, gabs); /* Add the duplicate TSN information. */ if (num_dup_tsns) { asoc->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); } /* Once we have a sack generated, check to see what our sack * generation is, if its 0, reset the transports to 0, and reset * the association generation to 1 * * The idea is that zero is never used as a valid generation for the * association so no transport will match after a wrap event like this, * Until the next sack */ if (++asoc->peer.sack_generation == 0) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) trans->sack_generation = 0; asoc->peer.sack_generation = 1; } nodata: return retval; } /* Make a SHUTDOWN chunk. */ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_shutdownhdr shut; struct sctp_chunk *retval; __u32 ctsn; ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, sizeof(shut), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.shutdown_hdr = sctp_addto_chunk(retval, sizeof(shut), &shut); if (chunk) retval->transport = chunk->transport; nodata: return retval; } struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_ACK, 0, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ACK back to where the SHUTDOWN came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } struct sctp_chunk *sctp_make_shutdown_complete( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; __u8 flags = 0; /* Set the T-bit if we have no association (vtag will be * reflected) */ flags |= asoc ? 0 : SCTP_CHUNK_FLAG_T; retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_COMPLETE, flags, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [Report SHUTDOWN COMPLETE back to where the SHUTDOWN ACK * came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } /* Create an ABORT. Note that we set the T bit if we have no * association, except when responding to an INIT (sctpimpguide 2.41). */ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const size_t hint) { struct sctp_chunk *retval; __u8 flags = 0; /* Set the T-bit if we have no association and 'chunk' is not * an INIT (vtag will be reflected). */ if (!asoc) { if (chunk && chunk->chunk_hdr && chunk->chunk_hdr->type == SCTP_CID_INIT) flags = 0; else flags = SCTP_CHUNK_FLAG_T; } retval = sctp_make_control(asoc, SCTP_CID_ABORT, flags, hint, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ABORT back to where the offender came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } /* Helper to create ABORT with a NO_USER_DATA error. */ struct sctp_chunk *sctp_make_abort_no_data( const struct sctp_association *asoc, const struct sctp_chunk *chunk, __u32 tsn) { struct sctp_chunk *retval; __be32 payload; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + sizeof(tsn)); if (!retval) goto no_mem; /* Put the tsn back into network byte order. */ payload = htonl(tsn); sctp_init_cause(retval, SCTP_ERROR_NO_DATA, sizeof(payload)); sctp_addto_chunk(retval, sizeof(payload), (const void *)&payload); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ABORT back to where the offender came from.] */ if (chunk) retval->transport = chunk->transport; no_mem: return retval; } /* Helper to create ABORT with a SCTP_ERROR_USER_ABORT error. */ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, struct msghdr *msg, size_t paylen) { struct sctp_chunk *retval; void *payload = NULL; int err; retval = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr) + paylen); if (!retval) goto err_chunk; if (paylen) { /* Put the msg_iov together into payload. */ payload = kmalloc(paylen, GFP_KERNEL); if (!payload) goto err_payload; err = memcpy_from_msg(payload, msg, paylen); if (err < 0) goto err_copy; } sctp_init_cause(retval, SCTP_ERROR_USER_ABORT, paylen); sctp_addto_chunk(retval, paylen, payload); if (paylen) kfree(payload); return retval; err_copy: kfree(payload); err_payload: sctp_chunk_free(retval); retval = NULL; err_chunk: return retval; } /* Append bytes to the end of a parameter. Will panic if chunk is not big * enough. */ static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data) { int chunklen = ntohs(chunk->chunk_hdr->length); void *target; target = skb_put(chunk->skb, len); if (data) memcpy(target, data, len); else memset(target, 0, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + len); chunk->chunk_end = skb_tail_pointer(chunk->skb); return target; } /* Make an ABORT chunk with a PROTOCOL VIOLATION cause code. */ struct sctp_chunk *sctp_make_abort_violation( const struct sctp_association *asoc, const struct sctp_chunk *chunk, const __u8 *payload, const size_t paylen) { struct sctp_chunk *retval; struct sctp_paramhdr phdr; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + paylen + sizeof(phdr)); if (!retval) goto end; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen + sizeof(phdr)); phdr.type = htons(chunk->chunk_hdr->type); phdr.length = chunk->chunk_hdr->length; sctp_addto_chunk(retval, paylen, payload); sctp_addto_param(retval, sizeof(phdr), &phdr); end: return retval; } struct sctp_chunk *sctp_make_violation_paramlen( const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_paramhdr *param) { static const char error[] = "The following parameter had invalid length:"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr) + sizeof(*param); struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error) + sizeof(*param)); sctp_addto_chunk(retval, sizeof(error), error); sctp_addto_param(retval, sizeof(*param), param); nodata: return retval; } struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { static const char error[] = "Association exceeded its max_retrans count"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error)); sctp_addto_chunk(retval, sizeof(error), error); nodata: return retval; } struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_new_encap_port_hdr nep; struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + sizeof(nep)); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep)); nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port; nep.new_port = chunk->transport->encap_port; sctp_addto_chunk(retval, sizeof(nep), &nep); nodata: return retval; } /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size) { struct sctp_sender_hb_info hbinfo = {}; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, sizeof(hbinfo), GFP_ATOMIC); if (!retval) goto nodata; hbinfo.param_hdr.type = SCTP_PARAM_HEARTBEAT_INFO; hbinfo.param_hdr.length = htons(sizeof(hbinfo)); hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; hbinfo.probe_size = probe_size; /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. */ retval->transport = (struct sctp_transport *) transport; retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), &hbinfo); retval->pmtu_probe = !!probe_size; nodata: return retval; } struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT_ACK, 0, paylen, GFP_ATOMIC); if (!retval) goto nodata; retval->subh.hbs_hdr = sctp_addto_chunk(retval, paylen, payload); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [HBACK back to where the HEARTBEAT came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* RFC4820 3. Padding Chunk (PAD) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0x84 | Flags=0 | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * \ Padding Data / * / \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); if (!retval) return NULL; skb_put_zero(retval->skb, len); retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); retval->chunk_end = skb_tail_pointer(retval->skb); return retval; } /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ static struct sctp_chunk *sctp_make_op_error_space( const struct sctp_association *asoc, const struct sctp_chunk *chunk, size_t size) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_ERROR, 0, sizeof(struct sctp_errhdr) + size, GFP_ATOMIC); if (!retval) goto nodata; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, etc.) to the same destination transport * address from which it received the DATA or control chunk * to which it is replying. * */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* Create an Operation Error chunk of a fixed size, specifically, * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. * This is a helper function to allocate an error chunk for those * invalid parameter codes in which we may not want to report all the * errors, if the incoming chunk is large. If it can't fit in a single * packet, we ignore it. */ static inline struct sctp_chunk *sctp_make_op_error_limited( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { size_t size = SCTP_DEFAULT_MAXSEGMENT; struct sctp_sock *sp = NULL; if (asoc) { size = min_t(size_t, size, asoc->pathmtu); sp = sctp_sk(asoc->base.sk); } size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr)); return sctp_make_op_error_space(asoc, chunk, size); } /* Create an Operation Error chunk. */ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, size_t paylen, size_t reserve_tail) { struct sctp_chunk *retval; retval = sctp_make_op_error_space(asoc, chunk, paylen + reserve_tail); if (!retval) goto nodata; sctp_init_cause(retval, cause_code, paylen + reserve_tail); sctp_addto_chunk(retval, paylen, payload); if (reserve_tail) sctp_addto_param(retval, reserve_tail, NULL); nodata: return retval; } struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc, __u16 key_id) { struct sctp_authhdr auth_hdr; const struct sctp_hmac *hmac_desc; struct sctp_chunk *retval; /* Get the first hmac that the peer told us to use */ hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (unlikely(!hmac_desc)) return NULL; retval = sctp_make_control(asoc, SCTP_CID_AUTH, 0, hmac_desc->hmac_len + sizeof(auth_hdr), GFP_ATOMIC); if (!retval) return NULL; auth_hdr.hmac_id = htons(hmac_desc->hmac_id); auth_hdr.shkey_id = htons(key_id); retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(auth_hdr), &auth_hdr); skb_put_zero(retval->skb, hmac_desc->hmac_len); /* Adjust the chunk header to include the empty MAC */ retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + hmac_desc->hmac_len); retval->chunk_end = skb_tail_pointer(retval->skb); return retval; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Turn an skb into a chunk. * FIXME: Eventually move the structure directly inside the skb->cb[]. * * sctpimpguide-05.txt Section 2.8.2 * M1) Each time a new DATA chunk is transmitted * set the 'TSN.Missing.Report' count for that TSN to 0. The * 'TSN.Missing.Report' count will be used to determine missing chunks * and when to fast retransmit. * */ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, const struct sctp_association *asoc, struct sock *sk, gfp_t gfp) { struct sctp_chunk *retval; retval = kmem_cache_zalloc(sctp_chunk_cachep, gfp); if (!retval) goto nodata; if (!sk) pr_debug("%s: chunkifying skb:%p w/o an sk\n", __func__, skb); INIT_LIST_HEAD(&retval->list); retval->skb = skb; retval->asoc = (struct sctp_association *)asoc; retval->singleton = 1; retval->fast_retransmit = SCTP_CAN_FRTX; /* Polish the bead hole. */ INIT_LIST_HEAD(&retval->transmitted_list); INIT_LIST_HEAD(&retval->frag_list); SCTP_DBG_OBJCNT_INC(chunk); refcount_set(&retval->refcnt, 1); nodata: return retval; } /* Set chunk->source and dest based on the IP header in chunk->skb. */ void sctp_init_addrs(struct sctp_chunk *chunk, union sctp_addr *src, union sctp_addr *dest) { memcpy(&chunk->source, src, sizeof(union sctp_addr)); memcpy(&chunk->dest, dest, sizeof(union sctp_addr)); } /* Extract the source address from a chunk. */ const union sctp_addr *sctp_source(const struct sctp_chunk *chunk) { /* If we have a known transport, use that. */ if (chunk->transport) { return &chunk->transport->ipaddr; } else { /* Otherwise, extract it from the IP header. */ return &chunk->source; } } /* Create a new chunk, setting the type and flags headers from the * arguments, reserving enough space for a 'paylen' byte payload. */ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp) { struct sctp_chunkhdr *chunk_hdr; struct sctp_chunk *retval; struct sk_buff *skb; struct sock *sk; int chunklen; chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen); if (chunklen > SCTP_MAX_CHUNK_LEN) goto nodata; /* No need to allocate LL here, as this is only a chunk. */ skb = alloc_skb(chunklen, gfp); if (!skb) goto nodata; /* Make room for the chunk header. */ chunk_hdr = (struct sctp_chunkhdr *)skb_put(skb, sizeof(*chunk_hdr)); chunk_hdr->type = type; chunk_hdr->flags = flags; chunk_hdr->length = htons(sizeof(*chunk_hdr)); sk = asoc ? asoc->base.sk : NULL; retval = sctp_chunkify(skb, asoc, sk, gfp); if (!retval) { kfree_skb(skb); goto nodata; } retval->chunk_hdr = chunk_hdr; retval->chunk_end = ((__u8 *)chunk_hdr) + sizeof(*chunk_hdr); /* Determine if the chunk needs to be authenticated */ if (sctp_auth_send_cid(type, asoc)) retval->auth = 1; return retval; nodata: return NULL; } static struct sctp_chunk *sctp_make_data(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp) { return _sctp_make_chunk(asoc, SCTP_CID_DATA, flags, paylen, gfp); } struct sctp_chunk *sctp_make_idata(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp) { return _sctp_make_chunk(asoc, SCTP_CID_I_DATA, flags, paylen, gfp); } static struct sctp_chunk *sctp_make_control(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp) { struct sctp_chunk *chunk; chunk = _sctp_make_chunk(asoc, type, flags, paylen, gfp); if (chunk) sctp_control_set_owner_w(chunk); return chunk; } /* Release the memory occupied by a chunk. */ static void sctp_chunk_destroy(struct sctp_chunk *chunk) { BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); consume_skb(chunk->skb); consume_skb(chunk->auth_chunk); SCTP_DBG_OBJCNT_DEC(chunk); kmem_cache_free(sctp_chunk_cachep, chunk); } /* Possibly, free the chunk. */ void sctp_chunk_free(struct sctp_chunk *chunk) { /* Release our reference on the message tracker. */ if (chunk->msg) sctp_datamsg_put(chunk->msg); sctp_chunk_put(chunk); } /* Grab a reference to the chunk. */ void sctp_chunk_hold(struct sctp_chunk *ch) { refcount_inc(&ch->refcnt); } /* Release a reference to the chunk. */ void sctp_chunk_put(struct sctp_chunk *ch) { if (refcount_dec_and_test(&ch->refcnt)) sctp_chunk_destroy(ch); } /* Append bytes to the end of a chunk. Will panic if chunk is not big * enough. */ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) { int chunklen = ntohs(chunk->chunk_hdr->length); int padlen = SCTP_PAD4(chunklen) - chunklen; void *target; skb_put_zero(chunk->skb, padlen); target = skb_put_data(chunk->skb, data, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + padlen + len); chunk->chunk_end = skb_tail_pointer(chunk->skb); return target; } /* Append bytes from user space to the end of a chunk. Will panic if * chunk is not big enough. * Returns a kernel err value. */ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len, struct iov_iter *from) { void *target; /* Make room in chunk for data. */ target = skb_put(chunk->skb, len); /* Copy data (whole iovec) into chunk */ if (!copy_from_iter_full(target, len, from)) return -EFAULT; /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(ntohs(chunk->chunk_hdr->length) + len); chunk->chunk_end = skb_tail_pointer(chunk->skb); return 0; } /* Helper function to assign a TSN if needed. This assumes that both * the data_hdr and association have already been assigned. */ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) { struct sctp_stream *stream; struct sctp_chunk *lchunk; struct sctp_datamsg *msg; __u16 ssn, sid; if (chunk->has_ssn) return; /* All fragments will be on the same stream */ sid = ntohs(chunk->subh.data_hdr->stream); stream = &chunk->asoc->stream; /* Now assign the sequence number to the entire message. * All fragments must have the same stream sequence number. */ msg = chunk->msg; list_for_each_entry(lchunk, &msg->chunks, frag_list) { if (lchunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { ssn = 0; } else { if (lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG) ssn = sctp_ssn_next(stream, out, sid); else ssn = sctp_ssn_peek(stream, out, sid); } lchunk->subh.data_hdr->ssn = htons(ssn); lchunk->has_ssn = 1; } } /* Helper function to assign a TSN if needed. This assumes that both * the data_hdr and association have already been assigned. */ void sctp_chunk_assign_tsn(struct sctp_chunk *chunk) { if (!chunk->has_tsn) { /* This is the last possible instant to * assign a TSN. */ chunk->subh.data_hdr->tsn = htonl(sctp_association_get_next_tsn(chunk->asoc)); chunk->has_tsn = 1; } } /* Create a CLOSED association to use with an incoming packet. */ struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *ep, struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_association *asoc; enum sctp_scope scope; struct sk_buff *skb; /* Create the bare association. */ scope = sctp_scope(sctp_source(chunk)); asoc = sctp_association_new(ep, ep->base.sk, scope, gfp); if (!asoc) goto nodata; asoc->temp = 1; skb = chunk->skb; /* Create an entry for the source address of the packet. */ SCTP_INPUT_CB(skb)->af->from_skb(&asoc->c.peer_addr, skb, 1); nodata: return asoc; } /* Build a cookie representing asoc. * This INCLUDES the param header needed to put the cookie in the INIT ACK. */ static struct sctp_cookie_param *sctp_pack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *init_chunk, int *cookie_len, const __u8 *raw_addrs, int addrs_len) { struct sctp_signed_cookie *cookie; struct sctp_cookie_param *retval; int headersize, bodysize; /* Header size is static data prior to the actual cookie, including * any padding. */ headersize = sizeof(struct sctp_paramhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = sizeof(struct sctp_cookie) + ntohs(init_chunk->chunk_hdr->length) + addrs_len; /* Pad out the cookie to a multiple to make the signature * functions simpler to write. */ if (bodysize % SCTP_COOKIE_MULTIPLE) bodysize += SCTP_COOKIE_MULTIPLE - (bodysize % SCTP_COOKIE_MULTIPLE); *cookie_len = headersize + bodysize; /* Clear this memory since we are sending this data structure * out on the network. */ retval = kzalloc(*cookie_len, GFP_ATOMIC); if (!retval) { *cookie_len = 0; return NULL; } cookie = (struct sctp_signed_cookie *) retval->body; /* Set up the parameter header. */ retval->p.type = SCTP_PARAM_STATE_COOKIE; retval->p.length = htons(*cookie_len); /* Copy the cookie part of the association itself. */ cookie->c = asoc->c; /* Save the raw address list length in the cookie. */ cookie->c.raw_addr_list_len = addrs_len; /* Remember PR-SCTP capability. */ cookie->c.prsctp_capable = asoc->peer.prsctp_capable; /* Save adaptation indication in the cookie. */ cookie->c.adaptation_ind = asoc->peer.adaptation_ind; /* Set an expiration time for the cookie. */ cookie->c.expiration = ktime_add(asoc->cookie_life, ktime_get_real()); /* Copy the peer's init packet. */ memcpy(cookie + 1, init_chunk->chunk_hdr, ntohs(init_chunk->chunk_hdr->length)); /* Copy the raw local address list of the association. */ memcpy((__u8 *)(cookie + 1) + ntohs(init_chunk->chunk_hdr->length), raw_addrs, addrs_len); /* Sign the cookie, if cookie authentication is enabled. */ if (sctp_sk(ep->base.sk)->cookie_auth_enable) { static_assert(sizeof(cookie->mac) == SHA256_DIGEST_SIZE); hmac_sha256(&ep->cookie_auth_key, (const u8 *)&cookie->c, bodysize, cookie->mac); } return retval; } /* Unpack the cookie from COOKIE ECHO chunk, recreating the association. */ struct sctp_association *sctp_unpack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, gfp_t gfp, int *error, struct sctp_chunk **errp) { struct sctp_association *retval = NULL; int headersize, bodysize, fixed_size; struct sctp_signed_cookie *cookie; struct sk_buff *skb = chunk->skb; struct sctp_cookie *bear_cookie; enum sctp_scope scope; unsigned int len; ktime_t kt; /* Header size is static data prior to the actual cookie, including * any padding. */ headersize = sizeof(struct sctp_chunkhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = ntohs(chunk->chunk_hdr->length) - headersize; fixed_size = headersize + sizeof(struct sctp_cookie); /* Verify that the chunk looks like it even has a cookie. * There must be enough room for our cookie and our peer's * INIT chunk. */ len = ntohs(chunk->chunk_hdr->length); if (len < fixed_size + sizeof(struct sctp_chunkhdr)) goto malformed; /* Verify that the cookie has been padded out. */ if (bodysize % SCTP_COOKIE_MULTIPLE) goto malformed; /* Process the cookie. */ cookie = chunk->subh.cookie_hdr; bear_cookie = &cookie->c; /* Verify the cookie's MAC, if cookie authentication is enabled. */ if (sctp_sk(ep->base.sk)->cookie_auth_enable) { u8 mac[SHA256_DIGEST_SIZE]; hmac_sha256(&ep->cookie_auth_key, (const u8 *)bear_cookie, bodysize, mac); static_assert(sizeof(cookie->mac) == sizeof(mac)); if (crypto_memneq(mac, cookie->mac, sizeof(mac))) { *error = -SCTP_IERROR_BAD_SIG; goto fail; } } /* IG Section 2.35.2: * 3) Compare the port numbers and the verification tag contained * within the COOKIE ECHO chunk to the actual port numbers and the * verification tag within the SCTP common header of the received * packet. If these values do not match the packet MUST be silently * discarded, */ if (ntohl(chunk->sctp_hdr->vtag) != bear_cookie->my_vtag) { *error = -SCTP_IERROR_BAD_TAG; goto fail; } if (chunk->sctp_hdr->source != bear_cookie->peer_addr.v4.sin_port || ntohs(chunk->sctp_hdr->dest) != bear_cookie->my_port) { *error = -SCTP_IERROR_BAD_PORTS; goto fail; } /* Check to see if the cookie is stale. If there is already * an association, there is no need to check cookie's expiration * for init collision case of lost COOKIE ACK. * If skb has been timestamped, then use the stamp, otherwise * use current time. This introduces a small possibility that * a cookie may be considered expired, but this would only slow * down the new association establishment instead of every packet. */ if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) kt = skb_get_ktime(skb); else kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); __be32 n = htonl(usecs); /* * Section 3.3.10.3 Stale Cookie Error (3) * * Cause of error * --------------- * Stale Cookie Error: Indicates the receipt of a valid State * Cookie that has expired. */ *errp = sctp_make_op_error(asoc, chunk, SCTP_ERROR_STALE_COOKIE, &n, sizeof(n), 0); if (*errp) *error = -SCTP_IERROR_STALE_COOKIE; else *error = -SCTP_IERROR_NOMEM; goto fail; } /* Make a new base association. */ scope = sctp_scope(sctp_source(chunk)); retval = sctp_association_new(ep, ep->base.sk, scope, gfp); if (!retval) { *error = -SCTP_IERROR_NOMEM; goto fail; } /* Set up our peer's port number. */ retval->peer.port = ntohs(chunk->sctp_hdr->source); /* Populate the association from the cookie. */ memcpy(&retval->c, bear_cookie, sizeof(*bear_cookie)); if (sctp_assoc_set_bind_addr_from_cookie(retval, bear_cookie, GFP_ATOMIC) < 0) { *error = -SCTP_IERROR_NOMEM; goto fail; } /* Also, add the destination address. */ if (list_empty(&retval->base.bind_addr.address_list)) { sctp_add_bind_addr(&retval->base.bind_addr, &chunk->dest, sizeof(chunk->dest), SCTP_ADDR_SRC, GFP_ATOMIC); } retval->next_tsn = retval->c.initial_tsn; retval->ctsn_ack_point = retval->next_tsn - 1; retval->addip_serial = retval->c.initial_tsn; retval->strreset_outseq = retval->c.initial_tsn; retval->adv_peer_ack_point = retval->ctsn_ack_point; retval->peer.prsctp_capable = retval->c.prsctp_capable; retval->peer.adaptation_ind = retval->c.adaptation_ind; /* The INIT stuff will be done by the side effects. */ return retval; fail: if (retval) sctp_association_free(retval); return NULL; malformed: /* Yikes! The packet is either corrupt or deliberately * malformed. */ *error = -SCTP_IERROR_MALFORMED; goto fail; } /******************************************************************** * 3rd Level Abstractions ********************************************************************/ struct __sctp_missing { __be32 num_missing; __be16 type; } __packed; /* * Report a missing mandatory parameter. */ static int sctp_process_missing_param(const struct sctp_association *asoc, enum sctp_param paramtype, struct sctp_chunk *chunk, struct sctp_chunk **errp) { struct __sctp_missing report; __u16 len; len = SCTP_PAD4(sizeof(report)); /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. */ if (!*errp) *errp = sctp_make_op_error_space(asoc, chunk, len); if (*errp) { report.num_missing = htonl(1); report.type = paramtype; sctp_init_cause(*errp, SCTP_ERROR_MISS_PARAM, sizeof(report)); sctp_addto_chunk(*errp, sizeof(report), &report); } /* Stop processing this chunk. */ return 0; } /* Report an Invalid Mandatory Parameter. */ static int sctp_process_inv_mandatory(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_chunk **errp) { /* Invalid Mandatory Parameter Error has no payload. */ if (!*errp) *errp = sctp_make_op_error_space(asoc, chunk, 0); if (*errp) sctp_init_cause(*errp, SCTP_ERROR_INV_PARAM, 0); /* Stop processing this chunk. */ return 0; } static int sctp_process_inv_paramlength(const struct sctp_association *asoc, struct sctp_paramhdr *param, const struct sctp_chunk *chunk, struct sctp_chunk **errp) { /* This is a fatal error. Any accumulated non-fatal errors are * not reported. */ if (*errp) sctp_chunk_free(*errp); /* Create an error chunk and fill it in with our payload. */ *errp = sctp_make_violation_paramlen(asoc, chunk, param); return 0; } /* Do not attempt to handle the HOST_NAME parm. However, do * send back an indicator to the peer. */ static int sctp_process_hn_param(const struct sctp_association *asoc, union sctp_params param, struct sctp_chunk *chunk, struct sctp_chunk **errp) { __u16 len = ntohs(param.p->length); /* Processing of the HOST_NAME parameter will generate an * ABORT. If we've accumulated any non-fatal errors, they * would be unrecognized parameters and we should not include * them in the ABORT. */ if (*errp) sctp_chunk_free(*errp); *errp = sctp_make_op_error(asoc, chunk, SCTP_ERROR_DNS_FAILED, param.v, len, 0); /* Stop processing this chunk. */ return 0; } static int sctp_verify_ext_param(struct net *net, const struct sctp_endpoint *ep, union sctp_params param) { __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int have_asconf = 0; int have_auth = 0; int i; for (i = 0; i < num_ext; i++) { switch (param.ext->chunks[i]) { case SCTP_CID_AUTH: have_auth = 1; break; case SCTP_CID_ASCONF: case SCTP_CID_ASCONF_ACK: have_asconf = 1; break; } } /* ADD-IP Security: The draft requires us to ABORT or ignore the * INIT/INIT-ACK if ADD-IP is listed, but AUTH is not. Do this * only if ADD-IP is turned on and we are not backward-compatible * mode. */ if (net->sctp.addip_noauth) return 1; if (ep->asconf_enable && !have_auth && have_asconf) return 0; return 1; } static void sctp_process_ext_param(struct sctp_association *asoc, union sctp_params param) { __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int i; for (i = 0; i < num_ext; i++) { switch (param.ext->chunks[i]) { case SCTP_CID_RECONF: if (asoc->ep->reconf_enable) asoc->peer.reconf_capable = 1; break; case SCTP_CID_FWD_TSN: if (asoc->ep->prsctp_enable) asoc->peer.prsctp_capable = 1; break; case SCTP_CID_AUTH: /* if the peer reports AUTH, assume that he * supports AUTH. */ if (asoc->ep->auth_enable) asoc->peer.auth_capable = 1; break; case SCTP_CID_ASCONF: case SCTP_CID_ASCONF_ACK: if (asoc->ep->asconf_enable) asoc->peer.asconf_capable = 1; break; case SCTP_CID_I_DATA: if (asoc->ep->intl_enable) asoc->peer.intl_capable = 1; break; default: break; } } } /* RFC 3.2.1 & the Implementers Guide 2.2. * * The Parameter Types are encoded such that the * highest-order two bits specify the action that must be * taken if the processing endpoint does not recognize the * Parameter Type. * * 00 - Stop processing this parameter; do not process any further * parameters within this chunk * * 01 - Stop processing this parameter, do not process any further * parameters within this chunk, and report the unrecognized * parameter in an 'Unrecognized Parameter' ERROR chunk. * * 10 - Skip this parameter and continue processing. * * 11 - Skip this parameter and continue processing but * report the unrecognized parameter in an * 'Unrecognized Parameter' ERROR chunk. * * Return value: * SCTP_IERROR_NO_ERROR - continue with the chunk * SCTP_IERROR_ERROR - stop and report an error. * SCTP_IERROR_NOMEME - out of memory. */ static enum sctp_ierror sctp_process_unk_param( const struct sctp_association *asoc, union sctp_params param, struct sctp_chunk *chunk, struct sctp_chunk **errp) { int retval = SCTP_IERROR_NO_ERROR; switch (param.p->type & SCTP_PARAM_ACTION_MASK) { case SCTP_PARAM_ACTION_DISCARD: retval = SCTP_IERROR_ERROR; break; case SCTP_PARAM_ACTION_SKIP: break; case SCTP_PARAM_ACTION_DISCARD_ERR: retval = SCTP_IERROR_ERROR; fallthrough; case SCTP_PARAM_ACTION_SKIP_ERR: /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. */ if (!*errp) { *errp = sctp_make_op_error_limited(asoc, chunk); if (!*errp) { /* If there is no memory for generating the * ERROR report as specified, an ABORT will be * triggered to the peer and the association * won't be established. */ retval = SCTP_IERROR_NOMEM; break; } } if (!sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, ntohs(param.p->length))) sctp_addto_chunk(*errp, ntohs(param.p->length), param.v); break; default: break; } return retval; } /* Verify variable length parameters * Return values: * SCTP_IERROR_ABORT - trigger an ABORT * SCTP_IERROR_NOMEM - out of memory (abort) * SCTP_IERROR_ERROR - stop processing, trigger an ERROR * SCTP_IERROR_NO_ERROR - continue with the chunk */ static enum sctp_ierror sctp_verify_param(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, enum sctp_cid cid, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk) { struct sctp_hmac_algo_param *hmacs; int retval = SCTP_IERROR_NO_ERROR; __u16 n_elt, id = 0; int i; /* FIXME - This routine is not looking at each parameter per the * chunk type, i.e., unrecognized parameters should be further * identified based on the chunk id. */ switch (param.p->type) { case SCTP_PARAM_IPV4_ADDRESS: case SCTP_PARAM_IPV6_ADDRESS: case SCTP_PARAM_COOKIE_PRESERVATIVE: case SCTP_PARAM_SUPPORTED_ADDRESS_TYPES: case SCTP_PARAM_STATE_COOKIE: case SCTP_PARAM_HEARTBEAT_INFO: case SCTP_PARAM_UNRECOGNIZED_PARAMETERS: case SCTP_PARAM_ECN_CAPABLE: case SCTP_PARAM_ADAPTATION_LAYER_IND: break; case SCTP_PARAM_SUPPORTED_EXT: if (!sctp_verify_ext_param(net, ep, param)) return SCTP_IERROR_ABORT; break; case SCTP_PARAM_SET_PRIMARY: if (!ep->asconf_enable) goto unhandled; if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) + sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; case SCTP_PARAM_HOST_NAME_ADDRESS: /* This param has been Deprecated, send ABORT. */ sctp_process_hn_param(asoc, param, chunk, err_chunk); retval = SCTP_IERROR_ABORT; break; case SCTP_PARAM_FWD_TSN_SUPPORT: if (ep->prsctp_enable) break; goto unhandled; case SCTP_PARAM_RANDOM: if (!ep->auth_enable) goto unhandled; /* SCTP-AUTH: Secion 6.1 * If the random number is not 32 byte long the association * MUST be aborted. The ABORT chunk SHOULD contain the error * cause 'Protocol Violation'. */ if (SCTP_AUTH_RANDOM_LENGTH != ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; case SCTP_PARAM_CHUNKS: if (!ep->auth_enable) goto unhandled; /* SCTP-AUTH: Section 3.2 * The CHUNKS parameter MUST be included once in the INIT or * INIT-ACK chunk if the sender wants to receive authenticated * chunks. Its maximum length is 260 bytes. */ if (260 < ntohs(param.p->length)) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; case SCTP_PARAM_HMAC_ALGO: if (!ep->auth_enable) goto unhandled; hmacs = (struct sctp_hmac_algo_param *)param.p; n_elt = (ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) >> 1; /* SCTP-AUTH: Section 6.1 * The HMAC algorithm based on SHA-1 MUST be supported and * included in the HMAC-ALGO parameter. */ for (i = 0; i < n_elt; i++) { id = ntohs(hmacs->hmac_ids[i]); if (id == SCTP_AUTH_HMAC_ID_SHA1) break; } if (id != SCTP_AUTH_HMAC_ID_SHA1) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; unhandled: default: pr_debug("%s: unrecognized param:%d for chunk:%d\n", __func__, ntohs(param.p->type), cid); retval = sctp_process_unk_param(asoc, param, chunk, err_chunk); break; } return retval; } /* Verify the INIT packet before we process it. */ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, enum sctp_cid cid, struct sctp_init_chunk *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; bool has_cookie = false; int result; /* Check for missing mandatory parameters. Note: Initial TSN is * also mandatory, but is not checked here since the valid range * is 0..2**32-1. RFC4960, section 3.3.3. */ if (peer_init->init_hdr.num_outbound_streams == 0 || peer_init->init_hdr.num_inbound_streams == 0 || peer_init->init_hdr.init_tag == 0 || ntohl(peer_init->init_hdr.a_rwnd) < SCTP_DEFAULT_MINWINDOW) return sctp_process_inv_mandatory(asoc, chunk, errp); sctp_walk_params(param, peer_init) { if (param.p->type == SCTP_PARAM_STATE_COOKIE) has_cookie = true; } /* There is a possibility that a parameter length was bad and * in that case we would have stoped walking the parameters. * The current param.p would point at the bad one. * Current consensus on the mailing list is to generate a PROTOCOL * VIOLATION error. We build the ERROR chunk here and let the normal * error handling code build and send the packet. */ if (param.v != (void *)chunk->chunk_end) return sctp_process_inv_paramlength(asoc, param.p, chunk, errp); /* The only missing mandatory param possible today is * the state cookie for an INIT-ACK chunk. */ if ((SCTP_CID_INIT_ACK == cid) && !has_cookie) return sctp_process_missing_param(asoc, SCTP_PARAM_STATE_COOKIE, chunk, errp); /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init) { result = sctp_verify_param(net, ep, asoc, param, cid, chunk, errp); switch (result) { case SCTP_IERROR_ABORT: case SCTP_IERROR_NOMEM: return 0; case SCTP_IERROR_ERROR: return 1; case SCTP_IERROR_NO_ERROR: default: break; } } /* for (loop through all parameters) */ return 1; } /* Unpack the parameters in an INIT packet into an association. * Returns 0 on failure, else success. * FIXME: This is an association method. */ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, const union sctp_addr *peer_addr, struct sctp_init_chunk *peer_init, gfp_t gfp) { struct sctp_transport *transport; struct list_head *pos, *temp; union sctp_params param; union sctp_addr addr; struct sctp_af *af; int src_match = 0; /* We must include the address that the INIT packet came from. * This is the only address that matters for an INIT packet. * When processing a COOKIE ECHO, we retrieve the from address * of the INIT from the cookie. */ /* This implementation defaults to making the first transport * added as the primary transport. The source address seems to * be a better choice than any of the embedded addresses. */ asoc->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; if (sctp_cmp_addr_exact(sctp_source(chunk), peer_addr)) src_match = 1; /* Process the initialization parameters. */ sctp_walk_params(param, peer_init) { if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { af = sctp_get_af_specific(param_type2af(param.p->type)); if (!af->from_addr_param(&addr, param.addr, chunk->sctp_hdr->source, 0)) continue; if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) src_match = 1; } if (!sctp_process_param(asoc, param, peer_addr, gfp)) goto clean_up; } /* source address of chunk may not match any valid address */ if (!src_match) goto clean_up; /* AUTH: After processing the parameters, make sure that we * have all the required info to potentially do authentications. */ if (asoc->peer.auth_capable && (!asoc->peer.peer_random || !asoc->peer.peer_hmacs)) asoc->peer.auth_capable = 0; /* In a non-backward compatible mode, if the peer claims * support for ADD-IP but not AUTH, the ADD-IP spec states * that we MUST ABORT the association. Section 6. The section * also give us an option to silently ignore the packet, which * is what we'll do here. */ if (!asoc->base.net->sctp.addip_noauth && (asoc->peer.asconf_capable && !asoc->peer.auth_capable)) { asoc->peer.addip_disabled_mask |= (SCTP_PARAM_ADD_IP | SCTP_PARAM_DEL_IP | SCTP_PARAM_SET_PRIMARY); asoc->peer.asconf_capable = 0; goto clean_up; } /* Walk list of transports, removing transports in the UNKNOWN state. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); if (transport->state == SCTP_UNKNOWN) { sctp_assoc_rm_peer(asoc, transport); } } /* The fixed INIT headers are always in network byte * order. */ asoc->peer.i.init_tag = ntohl(peer_init->init_hdr.init_tag); asoc->peer.i.a_rwnd = ntohl(peer_init->init_hdr.a_rwnd); asoc->peer.i.num_outbound_streams = ntohs(peer_init->init_hdr.num_outbound_streams); asoc->peer.i.num_inbound_streams = ntohs(peer_init->init_hdr.num_inbound_streams); asoc->peer.i.initial_tsn = ntohl(peer_init->init_hdr.initial_tsn); asoc->strreset_inseq = asoc->peer.i.initial_tsn; /* Apply the upper bounds for output streams based on peer's * number of inbound streams. */ if (asoc->c.sinit_num_ostreams > ntohs(peer_init->init_hdr.num_inbound_streams)) { asoc->c.sinit_num_ostreams = ntohs(peer_init->init_hdr.num_inbound_streams); } if (asoc->c.sinit_max_instreams > ntohs(peer_init->init_hdr.num_outbound_streams)) { asoc->c.sinit_max_instreams = ntohs(peer_init->init_hdr.num_outbound_streams); } /* Copy Initiation tag from INIT to VT_peer in cookie. */ asoc->c.peer_vtag = asoc->peer.i.init_tag; /* Peer Rwnd : Current calculated value of the peer's rwnd. */ asoc->peer.rwnd = asoc->peer.i.a_rwnd; /* RFC 2960 7.2.1 The initial value of ssthresh MAY be arbitrarily * high (for example, implementations MAY use the size of the receiver * advertised window). */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { transport->ssthresh = asoc->peer.i.a_rwnd; } /* Set up the TSN tracking pieces. */ if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, gfp)) goto clean_up; /* RFC 2960 6.5 Stream Identifier and Stream Sequence Number * * The stream sequence number in all the streams shall start * from 0 when the association is established. Also, when the * stream sequence number reaches the value 65535 the next * stream sequence number shall be set to 0. */ if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, asoc->c.sinit_max_instreams, gfp)) goto clean_up; /* Update frag_point when stream_interleave may get changed. */ sctp_assoc_update_frag_point(asoc); if (!asoc->temp && sctp_assoc_set_id(asoc, gfp)) goto clean_up; /* ADDIP Section 4.1 ASCONF Chunk Procedures * * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do the following: * ... * A2) A serial number should be assigned to the Chunk. The serial * number should be a monotonically increasing number. All serial * numbers are defined to be initialized at the start of the * association to the same value as the Initial TSN. */ asoc->peer.addip_serial = asoc->peer.i.initial_tsn - 1; return 1; clean_up: /* Release the transport structures. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); if (transport->state != SCTP_ACTIVE) sctp_assoc_rm_peer(asoc, transport); } nomem: return 0; } /* Update asoc with the option described in param. * * RFC2960 3.3.2.1 Optional/Variable Length Parameters in INIT * * asoc is the association to update. * param is the variable length parameter to use for update. * cid tells us if this is an INIT, INIT ACK or COOKIE ECHO. * If the current packet is an INIT we want to minimize the amount of * work we do. In particular, we should not build transport * structures for the addresses. */ static int sctp_process_param(struct sctp_association *asoc, union sctp_params param, const union sctp_addr *peer_addr, gfp_t gfp) { struct sctp_endpoint *ep = asoc->ep; union sctp_addr_param *addr_param; struct net *net = asoc->base.net; struct sctp_transport *t; enum sctp_scope scope; union sctp_addr addr; struct sctp_af *af; int retval = 1, i; u32 stale; __u16 sat; /* We maintain all INIT parameters in network byte order all the * time. This allows us to not worry about whether the parameters * came from a fresh INIT, and INIT ACK, or were stored in a cookie. */ switch (param.p->type) { case SCTP_PARAM_IPV6_ADDRESS: if (PF_INET6 != asoc->base.sk->sk_family) break; goto do_addr_param; case SCTP_PARAM_IPV4_ADDRESS: /* v4 addresses are not allowed on v6-only socket */ if (ipv6_only_sock(asoc->base.sk)) break; do_addr_param: af = sctp_get_af_specific(param_type2af(param.p->type)); if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0)) break; scope = sctp_scope(peer_addr); if (sctp_in_scope(net, &addr, scope)) if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED)) return 0; break; case SCTP_PARAM_COOKIE_PRESERVATIVE: if (!net->sctp.cookie_preserve_enable) break; stale = ntohl(param.life->lifespan_increment); /* Suggested Cookie Life span increment's unit is msec, * (1/1000sec). */ asoc->cookie_life = ktime_add_ms(asoc->cookie_life, stale); break; case SCTP_PARAM_SUPPORTED_ADDRESS_TYPES: /* Turn off the default values first so we'll know which * ones are really set by the peer. */ asoc->peer.ipv4_address = 0; asoc->peer.ipv6_address = 0; /* Assume that peer supports the address family * by which it sends a packet. */ if (peer_addr->sa.sa_family == AF_INET6) asoc->peer.ipv6_address = 1; else if (peer_addr->sa.sa_family == AF_INET) asoc->peer.ipv4_address = 1; /* Cycle through address types; avoid divide by 0. */ sat = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); if (sat) sat /= sizeof(__u16); for (i = 0; i < sat; ++i) { switch (param.sat->types[i]) { case SCTP_PARAM_IPV4_ADDRESS: asoc->peer.ipv4_address = 1; break; case SCTP_PARAM_IPV6_ADDRESS: if (PF_INET6 == asoc->base.sk->sk_family) asoc->peer.ipv6_address = 1; break; default: /* Just ignore anything else. */ break; } } break; case SCTP_PARAM_STATE_COOKIE: asoc->peer.cookie_len = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); kfree(asoc->peer.cookie); asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp); if (!asoc->peer.cookie) retval = 0; break; case SCTP_PARAM_HEARTBEAT_INFO: /* Would be odd to receive, but it causes no problems. */ break; case SCTP_PARAM_UNRECOGNIZED_PARAMETERS: /* Rejected during verify stage. */ break; case SCTP_PARAM_ECN_CAPABLE: if (asoc->ep->ecn_enable) { asoc->peer.ecn_capable = 1; break; } /* Fall Through */ goto fall_through; case SCTP_PARAM_ADAPTATION_LAYER_IND: asoc->peer.adaptation_ind = ntohl(param.aind->adaptation_ind); break; case SCTP_PARAM_SET_PRIMARY: if (!ep->asconf_enable) goto fall_through; addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (!af) break; if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) break; if (!af->addr_valid(&addr, NULL, NULL)) break; t = sctp_assoc_lookup_paddr(asoc, &addr); if (!t) break; sctp_assoc_set_primary(asoc, t); break; case SCTP_PARAM_SUPPORTED_EXT: sctp_process_ext_param(asoc, param); break; case SCTP_PARAM_FWD_TSN_SUPPORT: if (asoc->ep->prsctp_enable) { asoc->peer.prsctp_capable = 1; break; } /* Fall Through */ goto fall_through; case SCTP_PARAM_RANDOM: if (!ep->auth_enable) goto fall_through; /* Save peer's random parameter */ kfree(asoc->peer.peer_random); asoc->peer.peer_random = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_random) { retval = 0; break; } break; case SCTP_PARAM_HMAC_ALGO: if (!ep->auth_enable) goto fall_through; /* Save peer's HMAC list */ kfree(asoc->peer.peer_hmacs); asoc->peer.peer_hmacs = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_hmacs) { retval = 0; break; } /* Set the default HMAC the peer requested*/ sctp_auth_asoc_set_default_hmac(asoc, param.hmac_algo); break; case SCTP_PARAM_CHUNKS: if (!ep->auth_enable) goto fall_through; kfree(asoc->peer.peer_chunks); asoc->peer.peer_chunks = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_chunks) retval = 0; break; fall_through: default: /* Any unrecognized parameters should have been caught * and handled by sctp_verify_param() which should be * called prior to this routine. Simply log the error * here. */ pr_debug("%s: ignoring param:%d for association:%p.\n", __func__, ntohs(param.p->type), asoc); break; } return retval; } /* Select a new verification tag. */ __u32 sctp_generate_tag(const struct sctp_endpoint *ep) { /* I believe that this random number generator complies with RFC1750. * A tag of 0 is reserved for special cases (e.g. INIT). */ __u32 x; do { get_random_bytes(&x, sizeof(__u32)); } while (x == 0); return x; } /* Select an initial TSN to send during startup. */ __u32 sctp_generate_tsn(const struct sctp_endpoint *ep) { __u32 retval; get_random_bytes(&retval, sizeof(__u32)); return retval; } /* * ADDIP 3.1.1 Address Configuration Change Chunk (ASCONF) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0xC1 | Chunk Flags | Chunk Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Serial Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Address Parameter | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF Parameter #1 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / .... / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF Parameter #N | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Address Parameter and other parameter will not be wrapped in this function */ static struct sctp_chunk *sctp_make_asconf(struct sctp_association *asoc, union sctp_addr *addr, int vparam_len) { struct sctp_addiphdr asconf; struct sctp_chunk *retval; int length = sizeof(asconf) + vparam_len; union sctp_addr_param addrparam; int addrlen; struct sctp_af *af = sctp_get_af_specific(addr->v4.sin_family); addrlen = af->to_addr_param(addr, &addrparam); if (!addrlen) return NULL; length += addrlen; /* Create the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_ASCONF, 0, length, GFP_ATOMIC); if (!retval) return NULL; asconf.serial = htonl(asoc->addip_serial++); retval->subh.addip_hdr = sctp_addto_chunk(retval, sizeof(asconf), &asconf); retval->param_hdr.v = sctp_addto_chunk(retval, addrlen, &addrparam); return retval; } /* ADDIP * 3.2.1 Add IP Address * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0xC001 | Length = Variable | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF-Request Correlation ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Address Parameter | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * 3.2.2 Delete IP Address * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0xC002 | Length = Variable | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF-Request Correlation ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Address Parameter | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * */ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, union sctp_addr *laddr, struct sockaddr *addrs, int addrcnt, __be16 flags) { union sctp_addr_param addr_param; struct sctp_addip_param param; int paramlen = sizeof(param); struct sctp_chunk *retval; int addr_param_len = 0; union sctp_addr *addr; int totallen = 0, i; int del_pickup = 0; struct sctp_af *af; void *addr_buf; /* Get total length of all the address parameters. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); addr_param_len = af->to_addr_param(addr, &addr_param); totallen += paramlen; totallen += addr_param_len; addr_buf += af->sockaddr_len; if (asoc->asconf_addr_del_pending && !del_pickup) { /* reuse the parameter length from the same scope one */ totallen += paramlen; totallen += addr_param_len; del_pickup = 1; pr_debug("%s: picked same-scope del_pending addr, " "totallen for all addresses is %d\n", __func__, totallen); } } /* Create an asconf chunk with the required length. */ retval = sctp_make_asconf(asoc, laddr, totallen); if (!retval) return NULL; /* Add the address parameters to the asconf chunk. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = flags; param.param_hdr.length = htons(paramlen + addr_param_len); param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); addr_buf += af->sockaddr_len; } if (flags == SCTP_PARAM_ADD_IP && del_pickup) { addr = asoc->asconf_addr_del_pending; af = sctp_get_af_specific(addr->v4.sin_family); addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = SCTP_PARAM_DEL_IP; param.param_hdr.length = htons(paramlen + addr_param_len); param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); } return retval; } /* ADDIP * 3.2.4 Set Primary IP Address * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type =0xC004 | Length = Variable | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF-Request Correlation ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Address Parameter | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Create an ASCONF chunk with Set Primary IP address parameter. */ struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr) { struct sctp_af *af = sctp_get_af_specific(addr->v4.sin_family); union sctp_addr_param addrparam; struct sctp_addip_param param; struct sctp_chunk *retval; int len = sizeof(param); int addrlen; addrlen = af->to_addr_param(addr, &addrparam); if (!addrlen) return NULL; len += addrlen; /* Create the chunk and make asconf header. */ retval = sctp_make_asconf(asoc, addr, len); if (!retval) return NULL; param.param_hdr.type = SCTP_PARAM_SET_PRIMARY; param.param_hdr.length = htons(len); param.crr_id = 0; sctp_addto_chunk(retval, sizeof(param), ¶m); sctp_addto_chunk(retval, addrlen, &addrparam); return retval; } /* ADDIP 3.1.2 Address Configuration Acknowledgement Chunk (ASCONF-ACK) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0x80 | Chunk Flags | Chunk Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Serial Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF Parameter Response#1 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / .... / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ASCONF Parameter Response#N | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Create an ASCONF_ACK chunk with enough space for the parameter responses. */ static struct sctp_chunk *sctp_make_asconf_ack(const struct sctp_association *asoc, __u32 serial, int vparam_len) { struct sctp_addiphdr asconf; struct sctp_chunk *retval; int length = sizeof(asconf) + vparam_len; /* Create the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_ASCONF_ACK, 0, length, GFP_ATOMIC); if (!retval) return NULL; asconf.serial = htonl(serial); retval->subh.addip_hdr = sctp_addto_chunk(retval, sizeof(asconf), &asconf); return retval; } /* Add response parameters to an ASCONF_ACK chunk. */ static void sctp_add_asconf_response(struct sctp_chunk *chunk, __be32 crr_id, __be16 err_code, struct sctp_addip_param *asconf_param) { struct sctp_addip_param ack_param; struct sctp_errhdr err_param; int asconf_param_len = 0; int err_param_len = 0; __be16 response_type; if (SCTP_ERROR_NO_ERROR == err_code) { response_type = SCTP_PARAM_SUCCESS_REPORT; } else { response_type = SCTP_PARAM_ERR_CAUSE; err_param_len = sizeof(err_param); if (asconf_param) asconf_param_len = ntohs(asconf_param->param_hdr.length); } /* Add Success Indication or Error Cause Indication parameter. */ ack_param.param_hdr.type = response_type; ack_param.param_hdr.length = htons(sizeof(ack_param) + err_param_len + asconf_param_len); ack_param.crr_id = crr_id; sctp_addto_chunk(chunk, sizeof(ack_param), &ack_param); if (SCTP_ERROR_NO_ERROR == err_code) return; /* Add Error Cause parameter. */ err_param.cause = err_code; err_param.length = htons(err_param_len + asconf_param_len); sctp_addto_chunk(chunk, err_param_len, &err_param); /* Add the failed TLV copied from ASCONF chunk. */ if (asconf_param) sctp_addto_chunk(chunk, asconf_param_len, asconf_param); } /* Process a asconf parameter. */ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, struct sctp_chunk *asconf, struct sctp_addip_param *asconf_param) { union sctp_addr_param *addr_param; struct sctp_transport *peer; union sctp_addr addr; struct sctp_af *af; addr_param = (void *)asconf_param + sizeof(*asconf_param); if (asconf_param->param_hdr.type != SCTP_PARAM_ADD_IP && asconf_param->param_hdr.type != SCTP_PARAM_DEL_IP && asconf_param->param_hdr.type != SCTP_PARAM_SET_PRIMARY) return SCTP_ERROR_UNKNOWN_PARAM; switch (addr_param->p.type) { case SCTP_PARAM_IPV6_ADDRESS: if (!asoc->peer.ipv6_address) return SCTP_ERROR_DNS_FAILED; break; case SCTP_PARAM_IPV4_ADDRESS: if (!asoc->peer.ipv4_address) return SCTP_ERROR_DNS_FAILED; break; default: return SCTP_ERROR_DNS_FAILED; } af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) return SCTP_ERROR_DNS_FAILED; /* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast * or multicast address. * (note: wildcard is permitted and requires special handling so * make sure we check for that) */ if (!af->is_any(&addr) && !af->addr_valid(&addr, NULL, asconf->skb)) return SCTP_ERROR_DNS_FAILED; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: /* Section 4.2.1: * If the address 0.0.0.0 or ::0 is provided, the source * address of the packet MUST be added. */ if (af->is_any(&addr)) memcpy(&addr, &asconf->source, sizeof(addr)); if (security_sctp_bind_connect(asoc->ep->base.sk, SCTP_PARAM_ADD_IP, (struct sockaddr *)&addr, af->sockaddr_len)) return SCTP_ERROR_REQ_REFUSED; /* ADDIP 4.3 D9) If an endpoint receives an ADD IP address * request and does not have the local resources to add this * new address to the association, it MUST return an Error * Cause TLV set to the new error code 'Operation Refused * Due to Resource Shortage'. */ peer = sctp_assoc_add_peer(asoc, &addr, GFP_ATOMIC, SCTP_UNCONFIRMED); if (!peer) return SCTP_ERROR_RSRC_LOW; /* Start the heartbeat timer. */ sctp_transport_reset_hb_timer(peer); asoc->new_transport = peer; break; case SCTP_PARAM_DEL_IP: /* ADDIP 4.3 D7) If a request is received to delete the * last remaining IP address of a peer endpoint, the receiver * MUST send an Error Cause TLV with the error cause set to the * new error code 'Request to Delete Last Remaining IP Address'. */ if (asoc->peer.transport_count == 1) return SCTP_ERROR_DEL_LAST_IP; /* ADDIP 4.3 D8) If a request is received to delete an IP * address which is also the source address of the IP packet * which contained the ASCONF chunk, the receiver MUST reject * this request. To reject the request the receiver MUST send * an Error Cause TLV set to the new error code 'Request to * Delete Source IP Address' */ if (sctp_cmp_addr_exact(&asconf->source, &addr)) return SCTP_ERROR_DEL_SRC_IP; /* Section 4.2.2 * If the address 0.0.0.0 or ::0 is provided, all * addresses of the peer except the source address of the * packet MUST be deleted. */ if (af->is_any(&addr)) { sctp_assoc_set_primary(asoc, asconf->transport); sctp_assoc_del_nonprimary_peers(asoc, asconf->transport); return SCTP_ERROR_NO_ERROR; } /* If the address is not part of the association, the * ASCONF-ACK with Error Cause Indication Parameter * which including cause of Unresolvable Address should * be sent. */ peer = sctp_assoc_lookup_paddr(asoc, &addr); if (!peer) return SCTP_ERROR_DNS_FAILED; sctp_assoc_rm_peer(asoc, peer); break; case SCTP_PARAM_SET_PRIMARY: /* ADDIP Section 4.2.4 * If the address 0.0.0.0 or ::0 is provided, the receiver * MAY mark the source address of the packet as its * primary. */ if (af->is_any(&addr)) memcpy(&addr, sctp_source(asconf), sizeof(addr)); if (security_sctp_bind_connect(asoc->ep->base.sk, SCTP_PARAM_SET_PRIMARY, (struct sockaddr *)&addr, af->sockaddr_len)) return SCTP_ERROR_REQ_REFUSED; peer = sctp_assoc_lookup_paddr(asoc, &addr); if (!peer) return SCTP_ERROR_DNS_FAILED; sctp_assoc_set_primary(asoc, peer); break; } return SCTP_ERROR_NO_ERROR; } /* Verify the ASCONF packet before we process it. */ bool sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, bool addr_param_needed, struct sctp_paramhdr **errp) { struct sctp_addip_chunk *addip; bool addr_param_seen = false; union sctp_params param; addip = (struct sctp_addip_chunk *)chunk->chunk_hdr; sctp_walk_params(param, addip) { size_t length = ntohs(param.p->length); *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) return false; /* ensure there is only one addr param and it's in the * beginning of addip_hdr params, or we reject it. */ if (param.v != (addip + 1)) return false; addr_param_seen = true; break; case SCTP_PARAM_IPV6_ADDRESS: if (length != sizeof(struct sctp_ipv6addr_param)) return false; if (param.v != (addip + 1)) return false; addr_param_seen = true; break; case SCTP_PARAM_ADD_IP: case SCTP_PARAM_DEL_IP: case SCTP_PARAM_SET_PRIMARY: /* In ASCONF chunks, these need to be first. */ if (addr_param_needed && !addr_param_seen) return false; length = ntohs(param.addip->param_hdr.length); if (length < sizeof(struct sctp_addip_param) + sizeof(**errp)) return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: if (length != sizeof(struct sctp_addip_param)) return false; break; default: /* This is unknown to us, reject! */ return false; } } /* Remaining sanity checks. */ if (addr_param_needed && !addr_param_seen) return false; if (!addr_param_needed && addr_param_seen) return false; if (param.v != chunk->chunk_end) return false; return true; } /* Process an incoming ASCONF chunk with the next expected serial no. and * return an ASCONF_ACK chunk to be sent in response. */ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { union sctp_addr_param *addr_param; struct sctp_addip_chunk *addip; struct sctp_chunk *asconf_ack; bool all_param_pass = true; struct sctp_addiphdr *hdr; int length = 0, chunk_len; union sctp_params param; __be16 err_code; __u32 serial; addip = (struct sctp_addip_chunk *)asconf->chunk_hdr; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); hdr = (struct sctp_addiphdr *)asconf->skb->data; serial = ntohl(hdr->serial); /* Skip the addiphdr and store a pointer to address parameter. */ length = sizeof(*hdr); addr_param = (union sctp_addr_param *)(asconf->skb->data + length); chunk_len -= length; /* Skip the address parameter and store a pointer to the first * asconf parameter. */ length = ntohs(addr_param->p.length); chunk_len -= length; /* create an ASCONF_ACK chunk. * Based on the definitions of parameters, we know that the size of * ASCONF_ACK parameters are less than or equal to the fourfold of ASCONF * parameters. */ asconf_ack = sctp_make_asconf_ack(asoc, serial, chunk_len * 4); if (!asconf_ack) goto done; /* Process the TLVs contained within the ASCONF chunk. */ sctp_walk_params(param, addip) { /* Skip preceding address parameters. */ if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || param.p->type == SCTP_PARAM_IPV6_ADDRESS) continue; err_code = sctp_process_asconf_param(asoc, asconf, param.addip); /* ADDIP 4.1 A7) * If an error response is received for a TLV parameter, * all TLVs with no response before the failed TLV are * considered successful if not reported. All TLVs after * the failed response are considered unsuccessful unless * a specific success indication is present for the parameter. */ if (err_code != SCTP_ERROR_NO_ERROR) all_param_pass = false; if (!all_param_pass) sctp_add_asconf_response(asconf_ack, param.addip->crr_id, err_code, param.addip); /* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add * an IP address sends an 'Out of Resource' in its response, it * MUST also fail any subsequent add or delete requests bundled * in the ASCONF. */ if (err_code == SCTP_ERROR_RSRC_LOW) goto done; } done: asoc->peer.addip_serial++; /* If we are sending a new ASCONF_ACK hold a reference to it in assoc * after freeing the reference to old asconf ack if any. */ if (asconf_ack) { sctp_chunk_hold(asconf_ack); list_add_tail(&asconf_ack->transmitted_list, &asoc->asconf_ack_list); } return asconf_ack; } /* Process a asconf parameter that is successfully acked. */ static void sctp_asconf_param_success(struct sctp_association *asoc, struct sctp_addip_param *asconf_param) { struct sctp_bind_addr *bp = &asoc->base.bind_addr; union sctp_addr_param *addr_param; struct sctp_sockaddr_entry *saddr; struct sctp_transport *transport; union sctp_addr addr; struct sctp_af *af; addr_param = (void *)asconf_param + sizeof(*asconf_param); /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0)) return; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: /* This is always done in BH context with a socket lock * held, so the list can not change. */ local_bh_disable(); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, &addr)) saddr->state = SCTP_ADDR_SRC; } local_bh_enable(); list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { sctp_transport_dst_release(transport); } break; case SCTP_PARAM_DEL_IP: local_bh_disable(); sctp_del_bind_addr(bp, &addr); if (asoc->asconf_addr_del_pending != NULL && sctp_cmp_addr_exact(asoc->asconf_addr_del_pending, &addr)) { kfree(asoc->asconf_addr_del_pending); asoc->asconf_addr_del_pending = NULL; } local_bh_enable(); list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { sctp_transport_dst_release(transport); } break; default: break; } } /* Get the corresponding ASCONF response error code from the ASCONF_ACK chunk * for the given asconf parameter. If there is no response for this parameter, * return the error code based on the third argument 'no_err'. * ADDIP 4.1 * A7) If an error response is received for a TLV parameter, all TLVs with no * response before the failed TLV are considered successful if not reported. * All TLVs after the failed response are considered unsuccessful unless a * specific success indication is present for the parameter. */ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, struct sctp_addip_param *asconf_param, int no_err) { struct sctp_addip_param *asconf_ack_param; struct sctp_errhdr *err_param; int asconf_ack_len; __be16 err_code; int length; if (no_err) err_code = SCTP_ERROR_NO_ERROR; else err_code = SCTP_ERROR_REQ_REFUSED; asconf_ack_len = ntohs(asconf_ack->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. */ length = sizeof(struct sctp_addiphdr); asconf_ack_param = (struct sctp_addip_param *)(asconf_ack->skb->data + length); asconf_ack_len -= length; while (asconf_ack_len > 0) { if (asconf_ack_param->crr_id == asconf_param->crr_id) { switch (asconf_ack_param->param_hdr.type) { case SCTP_PARAM_SUCCESS_REPORT: return SCTP_ERROR_NO_ERROR; case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; asconf_ack_len -= length; if (asconf_ack_len > 0) return err_param->cause; else return SCTP_ERROR_INV_PARAM; break; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); asconf_ack_param = (void *)asconf_ack_param + length; asconf_ack_len -= length; } return err_code; } /* Process an incoming ASCONF_ACK chunk against the cached last ASCONF chunk. */ int sctp_process_asconf_ack(struct sctp_association *asoc, struct sctp_chunk *asconf_ack) { struct sctp_chunk *asconf = asoc->addip_last_asconf; struct sctp_addip_param *asconf_param; __be16 err_code = SCTP_ERROR_NO_ERROR; union sctp_addr_param *addr_param; int asconf_len = asconf->skb->len; int all_param_pass = 0; int length = 0; int no_err = 1; int retval = 0; /* Skip the chunkhdr and addiphdr from the last asconf sent and store * a pointer to address parameter. */ length = sizeof(struct sctp_addip_chunk); addr_param = (union sctp_addr_param *)(asconf->skb->data + length); asconf_len -= length; /* Skip the address parameter in the last asconf sent and store a * pointer to the first asconf parameter. */ length = ntohs(addr_param->p.length); asconf_param = (void *)addr_param + length; asconf_len -= length; /* ADDIP 4.1 * A8) If there is no response(s) to specific TLV parameter(s), and no * failures are indicated, then all request(s) are considered * successful. */ if (asconf_ack->skb->len == sizeof(struct sctp_addiphdr)) all_param_pass = 1; /* Process the TLVs contained in the last sent ASCONF chunk. */ while (asconf_len > 0) { if (all_param_pass) err_code = SCTP_ERROR_NO_ERROR; else { err_code = sctp_get_asconf_response(asconf_ack, asconf_param, no_err); if (no_err && (SCTP_ERROR_NO_ERROR != err_code)) no_err = 0; } switch (err_code) { case SCTP_ERROR_NO_ERROR: sctp_asconf_param_success(asoc, asconf_param); break; case SCTP_ERROR_RSRC_LOW: retval = 1; break; case SCTP_ERROR_UNKNOWN_PARAM: /* Disable sending this type of asconf parameter in * future. */ asoc->peer.addip_disabled_mask |= asconf_param->param_hdr.type; break; case SCTP_ERROR_REQ_REFUSED: case SCTP_ERROR_DEL_LAST_IP: case SCTP_ERROR_DEL_SRC_IP: default: break; } /* Skip the processed asconf parameter and move to the next * one. */ length = ntohs(asconf_param->param_hdr.length); asconf_param = (void *)asconf_param + length; asconf_len -= length; } if (no_err && asoc->src_out_of_asoc_ok) { asoc->src_out_of_asoc_ok = 0; sctp_transport_immediate_rtx(asoc->peer.primary_path); } /* Free the cached last sent asconf chunk. */ list_del_init(&asconf->transmitted_list); sctp_chunk_free(asconf); asoc->addip_last_asconf = NULL; return retval; } /* Make a FWD TSN chunk. */ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_fwdtsn_skip *skiplist) { struct sctp_chunk *retval = NULL; struct sctp_fwdtsn_hdr ftsn_hdr; struct sctp_fwdtsn_skip skip; size_t hint; int i; hint = (nstreams + 1) * sizeof(__u32); retval = sctp_make_control(asoc, SCTP_CID_FWD_TSN, 0, hint, GFP_ATOMIC); if (!retval) return NULL; ftsn_hdr.new_cum_tsn = htonl(new_cum_tsn); retval->subh.fwdtsn_hdr = sctp_addto_chunk(retval, sizeof(ftsn_hdr), &ftsn_hdr); for (i = 0; i < nstreams; i++) { skip.stream = skiplist[i].stream; skip.ssn = skiplist[i].ssn; sctp_addto_chunk(retval, sizeof(skip), &skip); } return retval; } struct sctp_chunk *sctp_make_ifwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_ifwdtsn_skip *skiplist) { struct sctp_chunk *retval = NULL; struct sctp_ifwdtsn_hdr ftsn_hdr; size_t hint; hint = (nstreams + 1) * sizeof(__u32); retval = sctp_make_control(asoc, SCTP_CID_I_FWD_TSN, 0, hint, GFP_ATOMIC); if (!retval) return NULL; ftsn_hdr.new_cum_tsn = htonl(new_cum_tsn); retval->subh.ifwdtsn_hdr = sctp_addto_chunk(retval, sizeof(ftsn_hdr), &ftsn_hdr); sctp_addto_chunk(retval, nstreams * sizeof(skiplist[0]), skiplist); return retval; } /* RE-CONFIG 3.1 (RE-CONFIG chunk) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 130 | Chunk Flags | Chunk Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / Re-configuration Parameter / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / Re-configuration Parameter (optional) / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ static struct sctp_chunk *sctp_make_reconf(const struct sctp_association *asoc, int length) { struct sctp_reconf_chunk *reconf; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_RECONF, 0, length, GFP_ATOMIC); if (!retval) return NULL; reconf = (struct sctp_reconf_chunk *)retval->chunk_hdr; retval->param_hdr.v = (u8 *)(reconf + 1); return retval; } /* RE-CONFIG 4.1 (STREAM OUT RESET) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 13 | Parameter Length = 16 + 2 * N | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Request Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Response Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Sender's Last Assigned TSN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Stream Number 1 (optional) | Stream Number 2 (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * / ...... / * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Stream Number N-1 (optional) | Stream Number N (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * RE-CONFIG 4.2 (STREAM IN RESET) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 14 | Parameter Length = 8 + 2 * N | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Request Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Stream Number 1 (optional) | Stream Number 2 (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * / ...... / * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Stream Number N-1 (optional) | Stream Number N (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_req( const struct sctp_association *asoc, __u16 stream_num, __be16 *stream_list, bool out, bool in) { __u16 stream_len = stream_num * sizeof(__u16); struct sctp_strreset_outreq outreq; struct sctp_strreset_inreq inreq; struct sctp_chunk *retval; __u16 outlen, inlen; outlen = (sizeof(outreq) + stream_len) * out; inlen = (sizeof(inreq) + stream_len) * in; retval = sctp_make_reconf(asoc, SCTP_PAD4(outlen) + SCTP_PAD4(inlen)); if (!retval) return NULL; if (outlen) { outreq.param_hdr.type = SCTP_PARAM_RESET_OUT_REQUEST; outreq.param_hdr.length = htons(outlen); outreq.request_seq = htonl(asoc->strreset_outseq); outreq.response_seq = htonl(asoc->strreset_inseq - 1); outreq.send_reset_at_tsn = htonl(asoc->next_tsn - 1); sctp_addto_chunk(retval, sizeof(outreq), &outreq); if (stream_len) sctp_addto_chunk(retval, stream_len, stream_list); } if (inlen) { inreq.param_hdr.type = SCTP_PARAM_RESET_IN_REQUEST; inreq.param_hdr.length = htons(inlen); inreq.request_seq = htonl(asoc->strreset_outseq + out); sctp_addto_chunk(retval, sizeof(inreq), &inreq); if (stream_len) sctp_addto_chunk(retval, stream_len, stream_list); } return retval; } /* RE-CONFIG 4.3 (SSN/TSN RESET ALL) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 15 | Parameter Length = 8 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Request Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_tsnreq( const struct sctp_association *asoc) { struct sctp_strreset_tsnreq tsnreq; __u16 length = sizeof(tsnreq); struct sctp_chunk *retval; retval = sctp_make_reconf(asoc, length); if (!retval) return NULL; tsnreq.param_hdr.type = SCTP_PARAM_RESET_TSN_REQUEST; tsnreq.param_hdr.length = htons(length); tsnreq.request_seq = htonl(asoc->strreset_outseq); sctp_addto_chunk(retval, sizeof(tsnreq), &tsnreq); return retval; } /* RE-CONFIG 4.5/4.6 (ADD STREAM) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 17 | Parameter Length = 12 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Request Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Number of new streams | Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_addstrm( const struct sctp_association *asoc, __u16 out, __u16 in) { struct sctp_strreset_addstrm addstrm; __u16 size = sizeof(addstrm); struct sctp_chunk *retval; retval = sctp_make_reconf(asoc, (!!out + !!in) * size); if (!retval) return NULL; if (out) { addstrm.param_hdr.type = SCTP_PARAM_RESET_ADD_OUT_STREAMS; addstrm.param_hdr.length = htons(size); addstrm.number_of_streams = htons(out); addstrm.request_seq = htonl(asoc->strreset_outseq); addstrm.reserved = 0; sctp_addto_chunk(retval, size, &addstrm); } if (in) { addstrm.param_hdr.type = SCTP_PARAM_RESET_ADD_IN_STREAMS; addstrm.param_hdr.length = htons(size); addstrm.number_of_streams = htons(in); addstrm.request_seq = htonl(asoc->strreset_outseq + !!out); addstrm.reserved = 0; sctp_addto_chunk(retval, size, &addstrm); } return retval; } /* RE-CONFIG 4.4 (RESP) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 16 | Parameter Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Response Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Result | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_resp(const struct sctp_association *asoc, __u32 result, __u32 sn) { struct sctp_strreset_resp resp; __u16 length = sizeof(resp); struct sctp_chunk *retval; retval = sctp_make_reconf(asoc, length); if (!retval) return NULL; resp.param_hdr.type = SCTP_PARAM_RESET_RESPONSE; resp.param_hdr.length = htons(length); resp.response_seq = htonl(sn); resp.result = htonl(result); sctp_addto_chunk(retval, sizeof(resp), &resp); return retval; } /* RE-CONFIG 4.4 OPTIONAL (TSNRESP) * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Parameter Type = 16 | Parameter Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Re-configuration Response Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Result | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Sender's Next TSN (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Receiver's Next TSN (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_tsnresp(struct sctp_association *asoc, __u32 result, __u32 sn, __u32 sender_tsn, __u32 receiver_tsn) { struct sctp_strreset_resptsn tsnresp; __u16 length = sizeof(tsnresp); struct sctp_chunk *retval; retval = sctp_make_reconf(asoc, length); if (!retval) return NULL; tsnresp.param_hdr.type = SCTP_PARAM_RESET_RESPONSE; tsnresp.param_hdr.length = htons(length); tsnresp.response_seq = htonl(sn); tsnresp.result = htonl(result); tsnresp.senders_next_tsn = htonl(sender_tsn); tsnresp.receivers_next_tsn = htonl(receiver_tsn); sctp_addto_chunk(retval, sizeof(tsnresp), &tsnresp); return retval; } bool sctp_verify_reconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_paramhdr **errp) { struct sctp_reconf_chunk *hdr; union sctp_params param; __be16 last = 0; __u16 cnt = 0; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; sctp_walk_params(param, hdr) { __u16 length = ntohs(param.p->length); *errp = param.p; if (cnt++ > 2) return false; switch (param.p->type) { case SCTP_PARAM_RESET_OUT_REQUEST: if (length < sizeof(struct sctp_strreset_outreq) || (last && last != SCTP_PARAM_RESET_RESPONSE && last != SCTP_PARAM_RESET_IN_REQUEST)) return false; break; case SCTP_PARAM_RESET_IN_REQUEST: if (length < sizeof(struct sctp_strreset_inreq) || (last && last != SCTP_PARAM_RESET_OUT_REQUEST)) return false; break; case SCTP_PARAM_RESET_RESPONSE: if ((length != sizeof(struct sctp_strreset_resp) && length != sizeof(struct sctp_strreset_resptsn)) || (last && last != SCTP_PARAM_RESET_RESPONSE && last != SCTP_PARAM_RESET_OUT_REQUEST)) return false; break; case SCTP_PARAM_RESET_TSN_REQUEST: if (length != sizeof(struct sctp_strreset_tsnreq) || last) return false; break; case SCTP_PARAM_RESET_ADD_IN_STREAMS: if (length != sizeof(struct sctp_strreset_addstrm) || (last && last != SCTP_PARAM_RESET_ADD_OUT_STREAMS)) return false; break; case SCTP_PARAM_RESET_ADD_OUT_STREAMS: if (length != sizeof(struct sctp_strreset_addstrm) || (last && last != SCTP_PARAM_RESET_ADD_IN_STREAMS)) return false; break; default: return false; } last = param.p->type; } return true; } |
| 620 845 411 635 558 627 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Block data types and constants. Directly include this file only to * break include dependency loop. */ #ifndef __LINUX_BLK_TYPES_H #define __LINUX_BLK_TYPES_H #include <linux/types.h> #include <linux/bvec.h> #include <linux/device.h> #include <linux/ktime.h> #include <linux/rw_hint.h> struct bio_set; struct bio; struct bio_integrity_payload; struct page; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif #define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) #define SECTOR_MASK (PAGE_SECTORS - 1) struct block_device { sector_t bd_start_sect; sector_t bd_nr_sectors; struct gendisk * bd_disk; struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; atomic_t __bd_flags; // partition number + flags #define BD_PARTNO 255 // lower 8 bits; assign-once #define BD_READ_ONLY (1u<<8) // read-only policy #define BD_WRITE_HOLDER (1u<<9) #define BD_HAS_SUBMIT_BIO (1u<<10) #define BD_RO_WARNED (1u<<11) #ifdef CONFIG_FAIL_MAKE_REQUEST #define BD_MAKE_IT_FAIL (1u<<12) #endif dev_t bd_dev; struct address_space *bd_mapping; /* page cache */ atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ void * bd_claiming; void * bd_holder; const struct blk_holder_ops *bd_holder_ops; struct mutex bd_holder_lock; int bd_holders; struct kobject *bd_holder_dir; atomic_t bd_fsfreeze_count; /* number of freeze requests */ struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; int bd_writers; #ifdef CONFIG_SECURITY void *bd_security; #endif /* * keep this out-of-line as it's both big and not needed in the fast * path */ struct device bd_device; } __randomize_layout; #define bdev_whole(_bdev) \ ((_bdev)->bd_disk->part0) #define dev_to_bdev(device) \ container_of((device), struct block_device, bd_device) #define bdev_kobj(_bdev) \ (&((_bdev)->bd_device.kobj)) /* * Block error status values. See block/blk-core:blk_errors for the details. */ typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) #define BLK_STS_RESV_CONFLICT ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) #define BLK_STS_IOERR ((__force blk_status_t)10) /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) /* * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set * and the bio would block (cf bio_wouldblock_error()) */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* * BLK_STS_DEV_RESOURCE is returned from the driver to the block layer if * device related resources are unavailable, but the driver can guarantee * that the queue will be rerun in the future once resources become * available again. This is typically the case for device specific * resources that are consumed for IO. If the driver fails allocating these * resources, we know that inflight (or pending) IO will free these * resource upon completion. * * This is different from BLK_STS_RESOURCE in that it explicitly references * a device specific resource. For resources of wider scope, allocation * failure can happen without having pending IO. This means that we can't * rely on request completions freeing these resources, as IO may not be in * flight. Examples of that are kernel memory allocations, DMA mappings, or * any other system wide resources. */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ #define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently active. The same command should be successful if resubmitted * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ #define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ #define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) /* * Invalid size or alignment. */ #define BLK_STS_INVAL ((__force blk_status_t)19) /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with * * Description: * This classifies block error status into non-retryable errors and ones * that may be successful if retried on a failover path. * * Return: * %false - retrying failover path will not help * %true - may succeed if retried */ static inline bool blk_path_error(blk_status_t error) { switch (error) { case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: case BLK_STS_RESV_CONFLICT: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; } /* Anything else could be a path failure, so should be retried */ return true; } typedef __u32 __bitwise blk_opf_t; typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; blk_opf_t bi_opf; /* bottom bits REQ_OP, top bits * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; enum rw_hint bi_write_hint; u8 bi_write_stream; blk_status_t bi_status; atomic_t __bi_remaining; struct bvec_iter bi_iter; union { /* for polled bios: */ blk_qc_t bi_cookie; /* for plugged zoned writes only: */ unsigned int __bi_nr_segments; }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP /* * Represents the association of the css and request_queue for the bio. * If a bio goes direct to device, it will not have a blkg as it will * not have a request_queue associated with it. The reference is put * on release of the bio. */ struct blkcg_gq *bi_blkg; /* Time that this bio was issued. */ u64 issue_time_ns; #ifdef CONFIG_BLK_CGROUP_IOCOST u64 bi_iocost_cost; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *bi_crypt_context; #endif #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif unsigned short bi_vcnt; /* how many bio_vec's */ /* * Everything starting with bi_max_vecs will be preserved by bio_reset() */ unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ struct bio_set *bi_pool; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) #define BIO_MAX_SECTORS (UINT_MAX >> SECTOR_SHIFT) static inline struct bio_vec *bio_inline_vecs(struct bio *bio) { return (struct bio_vec *)(bio + 1); } /* * bio flags */ enum { BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ /* * This bio has completed bps throttling at the single tg granularity, * which is different from BIO_BPS_THROTTLED. When the bio is enqueued * into the sq->queued of the upper tg, or is about to be dispatched, * this flag needs to be cleared. Since blk-throttle and rq_qos are not * on the same hierarchical level, reuse the value. */ BIO_TG_BPS_THROTTLED = BIO_QOS_THROTTLED, BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; typedef __u32 __bitwise blk_mq_req_flags_t; #define REQ_OP_BITS 8 #define REQ_OP_MASK (__force blk_opf_t)((1 << REQ_OP_BITS) - 1) #define REQ_FLAG_BITS 24 /** * enum req_op - Operations common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data * transfer direction: * * - if the least significant bit is set transfers are TO the device * - if the least significant bit is not set transfers are FROM the device * * If a operation does not transfer data the least significant bit has no * meaning. */ enum req_op { /* read sectors from the device */ REQ_OP_READ = (__force blk_opf_t)0, /* write sectors to the device */ REQ_OP_WRITE = (__force blk_opf_t)1, /* flush the volatile write cache */ REQ_OP_FLUSH = (__force blk_opf_t)2, /* discard sectors */ REQ_OP_DISCARD = (__force blk_opf_t)3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = (__force blk_opf_t)7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ REQ_OP_ZONE_OPEN = (__force blk_opf_t)10, /* Close a zone */ REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = (__force blk_opf_t)13, /* reset a zone write pointer */ REQ_OP_ZONE_RESET = (__force blk_opf_t)15, /* reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)17, /* Driver private requests */ REQ_OP_DRV_IN = (__force blk_opf_t)34, REQ_OP_DRV_OUT = (__force blk_opf_t)35, REQ_OP_LAST = (__force blk_opf_t)36, }; /* Keep cmd_flag_name[] in sync with the definitions below */ enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ __REQ_ATOMIC, /* for atomic write operations */ __REQ_P2PDMA, /* contains P2P DMA pages */ /* * Command specific flags, keep last: */ /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_NR_BITS, /* stops here */ }; #define REQ_FAILFAST_DEV \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (__force blk_opf_t)(1ULL << __REQ_SYNC) #define REQ_META (__force blk_opf_t)(1ULL << __REQ_META) #define REQ_PRIO (__force blk_opf_t)(1ULL << __REQ_PRIO) #define REQ_NOMERGE (__force blk_opf_t)(1ULL << __REQ_NOMERGE) #define REQ_IDLE (__force blk_opf_t)(1ULL << __REQ_IDLE) #define REQ_INTEGRITY (__force blk_opf_t)(1ULL << __REQ_INTEGRITY) #define REQ_FUA (__force blk_opf_t)(1ULL << __REQ_FUA) #define REQ_PREFLUSH (__force blk_opf_t)(1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) #define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) #define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) #define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) #define REQ_P2PDMA (__force blk_opf_t)(1ULL << __REQ_P2PDMA) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, STAT_FLUSH, NR_STAT_GROUPS }; static inline enum req_op bio_op(const struct bio *bio) { return bio->bi_opf & REQ_OP_MASK; } static inline bool op_is_write(blk_opf_t op) { return !!(op & (__force blk_opf_t)1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ static inline bool op_is_flush(blk_opf_t op) { return op & (REQ_FUA | REQ_PREFLUSH); } /* * Reads are always treated as synchronous, as are requests with the FUA or * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ static inline bool op_is_sync(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } static inline bool op_is_discard(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } /* * Check if a bio or request operation is a zone management operation, with * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case * due to its different handling in the block layer and device response in * case of command failure. */ static inline bool op_is_zone_mgmt(enum req_op op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: return true; default: return false; } } static inline int op_stat_group(enum req_op op) { if (op_is_discard(op)) return STAT_DISCARD; return op_is_write(op); } struct blk_rq_stat { u64 mean; u64 min; u64 max; u32 nr_samples; u64 batch; }; #endif /* __LINUX_BLK_TYPES_H */ |
| 33 7112 7148 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_H #define _ASM_X86_PAGE_H #include <linux/types.h> #ifdef __KERNEL__ #include <asm/page_types.h> #ifdef CONFIG_X86_64 #include <asm/page_64.h> #else #include <asm/page_32.h> #endif /* CONFIG_X86_64 */ #ifndef __ASSEMBLER__ struct page; #include <linux/range.h> extern struct range pfn_mapped[]; extern int nr_pfn_mapped; static inline void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { clear_page(page); } static inline void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage) { copy_page(to, from); } #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) #endif #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ /* * We need __phys_reloc_hide() here because gcc may assume that there is no * overflow during __pa() calculation and can optimize it unexpectedly. * Newer versions of gcc provide -fno-strict-overflow switch to handle this * case properly. Once all supported versions of gcc understand it, we can * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) */ #define __pa_symbol(x) \ __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) #ifndef __va #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) #endif #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) /* * virt_to_page(kaddr) returns a valid pointer if and only if * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) static __always_inline void *pfn_to_kaddr(unsigned long pfn) { return __va(pfn << PAGE_SHIFT); } static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits) { return __canonical_address(vaddr, vaddr_bits) == vaddr; } #endif /* __ASSEMBLER__ */ #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif /* __KERNEL__ */ #endif /* _ASM_X86_PAGE_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_TIMEOUT_H #define _NF_CONNTRACK_TIMEOUT_H #include <net/net_namespace.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <linux/refcount.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> #define CTNL_TIMEOUT_NAME_MAX 32 struct nf_ct_timeout { __u16 l3num; const struct nf_conntrack_l4proto *l4proto; char data[]; }; struct nf_conn_timeout { struct nf_ct_timeout __rcu *timeout; }; static inline unsigned int * nf_ct_timeout_data(const struct nf_conn_timeout *t) { #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_ct_timeout *timeout; timeout = rcu_dereference(t->timeout); if (timeout == NULL) return NULL; return (unsigned int *)timeout->data; #else return NULL; #endif } static inline struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMEOUT return nf_ct_ext_find(ct, NF_CT_EXT_TIMEOUT); #else return NULL; #endif } static inline struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, struct nf_ct_timeout *timeout, gfp_t gfp) { #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_conn_timeout *timeout_ext; timeout_ext = nf_ct_ext_add(ct, NF_CT_EXT_TIMEOUT, gfp); if (timeout_ext == NULL) return NULL; rcu_assign_pointer(timeout_ext->timeout, timeout); return timeout_ext; #else return NULL; #endif }; static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) { unsigned int *timeouts = NULL; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_conn_timeout *timeout_ext; timeout_ext = nf_ct_timeout_find(ct); if (timeout_ext) timeouts = nf_ct_timeout_data(timeout_ext); #endif return timeouts; } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout); int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name); void nf_ct_destroy_timeout(struct nf_conn *ct); #else static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name) { return -EOPNOTSUPP; } static inline void nf_ct_destroy_timeout(struct nf_conn *ct) { return; } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_ct_timeout_hooks { struct nf_ct_timeout *(*timeout_find_get)(struct net *net, const char *name); void (*timeout_put)(struct nf_ct_timeout *timeout); }; extern const struct nf_ct_timeout_hooks __rcu *nf_ct_timeout_hook; #endif #endif /* _NF_CONNTRACK_TIMEOUT_H */ |
| 262 282 762 2 889 816 1 52 204 33 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PIPE_FS_I_H #define _LINUX_PIPE_FS_I_H #define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ #define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */ #ifdef CONFIG_WATCH_QUEUE #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer * @offset: offset of data inside the @page * @len: length of data inside the @page * @ops: operations associated with this buffer. See @pipe_buf_operations. * @flags: pipe buffer flags. See above. * @private: private data owned by the ops. **/ struct pipe_buffer { struct page *page; unsigned int offset, len; const struct pipe_buf_operations *ops; unsigned int flags; unsigned long private; }; /* * Really only alpha needs 32-bit fields, but * might as well do it for 64-bit architectures * since that's what we've historically done, * and it makes 'head_tail' always be a simple * 'unsigned long'. */ #ifdef CONFIG_64BIT typedef unsigned int pipe_index_t; #else typedef unsigned short pipe_index_t; #endif /* * We have to declare this outside 'struct pipe_inode_info', * but then we can't use 'union pipe_index' for an anonymous * union, so we end up having to duplicate this declaration * below. Annoying. */ union pipe_index { unsigned long head_tail; struct { pipe_index_t head; pipe_index_t tail; }; }; /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @head_tail: unsigned long union of @head and @tail * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; /* This has to match the 'union pipe_index' above */ union { unsigned long head_tail; struct { pipe_index_t head; pipe_index_t tail; }; }; unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; unsigned int r_counter; unsigned int w_counter; bool poll_usage; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif struct page *tmp_page[2]; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; #ifdef CONFIG_WATCH_QUEUE struct watch_queue *watch_queue; #endif }; /* * Note on the nesting of these functions: * * ->confirm() * ->try_steal() * * That is, ->try_steal() must be called on a confirmed buffer. See below for * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); /* * When the contents of this pipe buffer has been completely * consumed by a reader, ->release() is called. */ void (*release)(struct pipe_inode_info *, struct pipe_buffer *); /* * Attempt to take ownership of the pipe buffer and its contents. * ->try_steal() returns %true for success, in which case the contents * of the pipe (the buf->page) is locked and now completely owned by the * caller. The page may then be transferred to a different mapping, the * most often used case is insertion into different file address space * cache. */ bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. */ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_has_watch_queue - Check whether the pipe is a watch_queue, * i.e. it was created with O_NOTIFICATION_PIPE * @pipe: The pipe to check * * Return: true if pipe is a watch queue, false otherwise. */ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) { #ifdef CONFIG_WATCH_QUEUE return pipe->watch_queue != NULL; #else return false; #endif } /** * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { return (pipe_index_t)(head - tail); } /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline bool pipe_empty(unsigned int head, unsigned int tail) { return !pipe_occupancy(head, tail); } /** * pipe_full - Return true if the pipe is full * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer * @limit: The maximum amount of slots available. */ static inline bool pipe_full(unsigned int head, unsigned int tail, unsigned int limit) { return pipe_occupancy(head, tail) >= limit; } /** * pipe_is_full - Return true if the pipe is full * @pipe: the pipe */ static inline bool pipe_is_full(const struct pipe_inode_info *pipe) { return pipe_full(pipe->head, pipe->tail, pipe->max_usage); } /** * pipe_is_empty - Return true if the pipe is empty * @pipe: the pipe */ static inline bool pipe_is_empty(const struct pipe_inode_info *pipe) { return pipe_empty(pipe->head, pipe->tail); } /** * pipe_buf_usage - Return how many pipe buffers are in use * @pipe: the pipe */ static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe) { return pipe_occupancy(pipe->head, pipe->tail); } /** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest */ static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, unsigned int slot) { return &pipe->bufs[slot & (pipe->ring_size - 1)]; } /** * pipe_head_buf - Return the pipe buffer at the head of the pipe ring * @pipe: The pipe to access */ static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) { return pipe_buf(pipe, pipe->head); } /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Return: %true if the reference was successfully obtained. */ static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return buf->ops->get(pipe, buf); } /** * pipe_buf_release - put a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to */ static inline void pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { const struct pipe_buf_operations *ops = buf->ops; buf->ops = NULL; ops->release(pipe, buf); } /** * pipe_buf_confirm - verify contents of the pipe buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to confirm */ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->confirm) return 0; return buf->ops->confirm(pipe, buf); } /** * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->try_steal) return false; return buf->ops->try_steal(pipe, buf); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE /* Pipe lock and unlock operations */ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); long pipe_fcntl(struct file *, unsigned int, unsigned int arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned int size); #endif |
| 268 200 35 269 200 200 200 200 199 | 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 | // 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 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * * This file is part of the SCTP kernel implementation * * These are the state tables for the SCTP state machine. * * 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> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state); static const struct sctp_sm_table_entry bug = { .fn = sctp_sf_bug, .name = "sctp_sf_bug" }; #define DO_LOOKUP(_max, _type, _table) \ ({ \ const struct sctp_sm_table_entry *rtn; \ \ if ((event_subtype._type > (_max))) { \ pr_warn("table %p possible attack: event %d exceeds max %d\n", \ _table, event_subtype._type, _max); \ rtn = &bug; \ } else \ rtn = &_table[event_subtype._type][(int)state]; \ \ rtn; \ }) const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype) { switch (event_type) { case SCTP_EVENT_T_CHUNK: return sctp_chunk_event_lookup(net, event_subtype.chunk, state); case SCTP_EVENT_T_TIMEOUT: return DO_LOOKUP(SCTP_EVENT_TIMEOUT_MAX, timeout, timeout_event_table); case SCTP_EVENT_T_OTHER: return DO_LOOKUP(SCTP_EVENT_OTHER_MAX, other, other_event_table); case SCTP_EVENT_T_PRIMITIVE: return DO_LOOKUP(SCTP_EVENT_PRIMITIVE_MAX, primitive, primitive_event_table); default: /* Yikes! We got an illegal event type. */ return &bug; } } #define TYPE_SCTP_FUNC(func) {.fn = func, .name = #func} #define TYPE_SCTP_DATA { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_fast_4_4), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_DATA */ #define TYPE_SCTP_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1B_init), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_reshutack), \ } /* TYPE_SCTP_INIT */ #define TYPE_SCTP_INIT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_3_initack), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1C_ack), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_INIT_ACK */ #define TYPE_SCTP_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SACK */ #define TYPE_SCTP_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ /* This should not happen, but we are nice. */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ } /* TYPE_SCTP_HEARTBEAT */ #define TYPE_SCTP_HEARTBEAT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_HEARTBEAT_ACK */ #define TYPE_SCTP_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_pdiscard), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_abort), \ } /* TYPE_SCTP_ABORT */ #define TYPE_SCTP_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shut_ctsn), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SHUTDOWN */ #define TYPE_SCTP_SHUTDOWN_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ } /* TYPE_SCTP_SHUTDOWN_ACK */ #define TYPE_SCTP_ERROR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_err), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ERROR */ #define TYPE_SCTP_COOKIE_ECHO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1D_ce), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ } /* TYPE_SCTP_COOKIE_ECHO */ #define TYPE_SCTP_COOKIE_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1E_ca), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_COOKIE_ACK */ #define TYPE_SCTP_ECN_ECNE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_ECNE */ #define TYPE_SCTP_ECN_CWR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_CWR */ #define TYPE_SCTP_SHUTDOWN_COMPLETE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_4_C), \ } /* TYPE_SCTP_SHUTDOWN_COMPLETE */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. * * For base protocol (RFC 2960). */ static const struct sctp_sm_table_entry chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_DATA, TYPE_SCTP_INIT, TYPE_SCTP_INIT_ACK, TYPE_SCTP_SACK, TYPE_SCTP_HEARTBEAT, TYPE_SCTP_HEARTBEAT_ACK, TYPE_SCTP_ABORT, TYPE_SCTP_SHUTDOWN, TYPE_SCTP_SHUTDOWN_ACK, TYPE_SCTP_ERROR, TYPE_SCTP_COOKIE_ECHO, TYPE_SCTP_COOKIE_ACK, TYPE_SCTP_ECN_ECNE, TYPE_SCTP_ECN_CWR, TYPE_SCTP_SHUTDOWN_COMPLETE, }; /* state_fn_t chunk_event_table[][] */ #define TYPE_SCTP_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF */ #define TYPE_SCTP_ASCONF_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF_ACK */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_ASCONF, TYPE_SCTP_ASCONF_ACK, }; /*state_fn_t addip_chunk_event_table[][] */ #define TYPE_SCTP_FWD_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn_fast), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_FWD_TSN */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FWD_TSN, }; /*state_fn_t prsctp_chunk_event_table[][] */ #define TYPE_SCTP_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_RECONF */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry reconf_chunk_event_table[SCTP_NUM_RECONF_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_RECONF, }; /*state_fn_t reconf_chunk_event_table[][] */ #define TYPE_SCTP_AUTH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ } /* TYPE_SCTP_AUTH */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ static const struct sctp_sm_table_entry pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), }; /* chunk pad */ static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), }; /* chunk unknown */ #define TYPE_SCTP_PRIMITIVE_ASSOCIATE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asoc), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ } /* TYPE_SCTP_PRIMITIVE_ASSOCIATE */ #define TYPE_SCTP_PRIMITIVE_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_shutdown), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_shutdown),\ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_prm_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ } /* TYPE_SCTP_PRIMITIVE_SHUTDOWN */ #define TYPE_SCTP_PRIMITIVE_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_prm_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_prm_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_prm_abort), \ } /* TYPE_SCTP_PRIMITIVE_ABORT */ #define TYPE_SCTP_PRIMITIVE_SEND { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_SEND */ #define TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ } /* TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT */ #define TYPE_SCTP_PRIMITIVE_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_ASCONF */ #define TYPE_SCTP_PRIMITIVE_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_RECONF */ /* The primary index for this table is the primitive type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_PRIMITIVE_ASSOCIATE, TYPE_SCTP_PRIMITIVE_SHUTDOWN, TYPE_SCTP_PRIMITIVE_ABORT, TYPE_SCTP_PRIMITIVE_SEND, TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT, TYPE_SCTP_PRIMITIVE_ASCONF, TYPE_SCTP_PRIMITIVE_RECONF, }; #define TYPE_SCTP_OTHER_NO_PENDING_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_no_pending_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_start_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } #define TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_icmp_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_OTHER_NO_PENDING_TSN, TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH, }; #define TYPE_SCTP_EVENT_TIMEOUT_NONE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_t1_cookie_timer_expire), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_t1_init_timer_expire), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T3_RTX { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T4_RTO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_t4_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_autoclose_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_probe), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE, TYPE_SCTP_EVENT_TIMEOUT_T1_INIT, TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN, TYPE_SCTP_EVENT_TIMEOUT_T3_RTX, TYPE_SCTP_EVENT_TIMEOUT_T4_RTO, TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state) { if (state > SCTP_STATE_MAX) return &bug; if (cid == SCTP_CID_I_DATA) cid = SCTP_CID_DATA; if (cid <= SCTP_CID_BASE_MAX) return &chunk_event_table[cid][state]; switch ((u16)cid) { case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: return &prsctp_chunk_event_table[0][state]; case SCTP_CID_ASCONF: return &addip_chunk_event_table[0][state]; case SCTP_CID_ASCONF_ACK: return &addip_chunk_event_table[1][state]; case SCTP_CID_RECONF: return &reconf_chunk_event_table[0][state]; case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; case SCTP_CID_PAD: return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; } |
| 572 572 572 571 572 571 570 552 571 548 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | // SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * * Copyright 2012 Linaro Ltd. * Anton Vorontsov <anton.vorontsov@linaro.org> * * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. */ #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> /* * The window size (vmpressure_win) is the number of scanned pages before * we try to analyze scanned/reclaimed ratio. So the window is used as a * rate-limit tunable for the "low" level notification, and also for * averaging the ratio for medium/critical levels. Using small window * sizes can cause lot of false positives, but too big window size will * delay the notifications. * * As the vmscan reclaimer logic works with chunks which are multiple of * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. * * TODO: Make the window size depend on machine size, as we do for vmstat * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). */ static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; /* * These thresholds are used when we account memory pressure through * scanned/reclaimed ratio. The current values were chosen empirically. In * essence, they are percents: the higher the value, the more number * unsuccessful reclaims there were. */ static const unsigned int vmpressure_level_med = 60; static const unsigned int vmpressure_level_critical = 95; /* * When there are too little pages left to scan, vmpressure() may miss the * critical pressure as number of pages will be less than "window size". * However, in that case the vmscan priority will raise fast as the * reclaimer will try to scan LRUs more deeply. * * The vmscan logic considers these special priorities: * * prio == DEF_PRIORITY (12): reclaimer starts with that value * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed * prio == 0 : close to OOM, kernel scans every page in an lru * * Any value in this range is acceptable for this tunable (i.e. from 12 to * 0). Current value for the vmpressure_level_critical_prio is chosen * empirically, but the number, in essence, means that we consider * critical level when scanning depth is ~10% of the lru size (vmscan * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one * eights). */ static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); static struct vmpressure *work_to_vmpressure(struct work_struct *work) { return container_of(work, struct vmpressure, work); } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr); memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return memcg_to_vmpressure(memcg); } enum vmpressure_levels { VMPRESSURE_LOW = 0, VMPRESSURE_MEDIUM, VMPRESSURE_CRITICAL, VMPRESSURE_NUM_LEVELS, }; enum vmpressure_modes { VMPRESSURE_NO_PASSTHROUGH = 0, VMPRESSURE_HIERARCHY, VMPRESSURE_LOCAL, VMPRESSURE_NUM_MODES, }; static const char * const vmpressure_str_levels[] = { [VMPRESSURE_LOW] = "low", [VMPRESSURE_MEDIUM] = "medium", [VMPRESSURE_CRITICAL] = "critical", }; static const char * const vmpressure_str_modes[] = { [VMPRESSURE_NO_PASSTHROUGH] = "default", [VMPRESSURE_HIERARCHY] = "hierarchy", [VMPRESSURE_LOCAL] = "local", }; static enum vmpressure_levels vmpressure_level(unsigned long pressure) { if (pressure >= vmpressure_level_critical) return VMPRESSURE_CRITICAL; else if (pressure >= vmpressure_level_med) return VMPRESSURE_MEDIUM; return VMPRESSURE_LOW; } static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; unsigned long pressure = 0; /* * reclaimed can be greater than scanned for things such as reclaimed * slab pages. shrink_node() just adds reclaimed pages without a * related increment to scanned pages. */ if (reclaimed >= scanned) goto out; /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages * scanned. This makes it possible to set desired reaction time * and serves as a ratelimit. */ pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); return vmpressure_level(pressure); } struct vmpressure_event { struct eventfd_ctx *efd; enum vmpressure_levels level; enum vmpressure_modes mode; struct list_head node; }; static bool vmpressure_event(struct vmpressure *vmpr, const enum vmpressure_levels level, bool ancestor, bool signalled) { struct vmpressure_event *ev; bool ret = false; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ancestor && ev->mode == VMPRESSURE_LOCAL) continue; if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) continue; if (level < ev->level) continue; eventfd_signal(ev->efd); ret = true; } mutex_unlock(&vmpr->events_lock); return ret; } static void vmpressure_work_fn(struct work_struct *work) { struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; enum vmpressure_levels level; bool ancestor = false; bool signalled = false; spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old * work context cleared the counters. In that case we will run * just after the old work returns, but then scanned might be zero * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } reclaimed = vmpr->tree_reclaimed; vmpr->tree_scanned = 0; vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); do { if (vmpressure_event(vmpr, level, ancestor, signalled)) signalled = true; ancestor = true; } while ((vmpr = vmpressure_parent(vmpr))); } /** * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * * This function should be called from the vmscan reclaim path to account * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * * If @tree is set, vmpressure is in traditional userspace reporting * mode: @memcg is considered the pressure root and userspace is * notified of the entire subtree's reclaim efficiency. * * If @tree is not set, reclaim efficiency is recorded for @memcg, and * only in-kernel users are notified. * * This function does not return any value. */ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr; if (mem_cgroup_disabled()) return; /* * The in-kernel users only care about the reclaim efficiency * for this @memcg rather than the whole subtree, and there * isn't and won't be any in-kernel user in a legacy cgroup. */ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) return; vmpr = memcg_to_vmpressure(memcg); /* * Here we only want to account pressure that userland is able to * help us with. For example, suppose that DMA zone is under * pressure; if we notify userland about that kind of pressure, * then it will be mostly a waste as it will trigger unnecessary * freeing of memory by userland (since userland is more likely to * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That * is why we include only movable, highmem and FS/IO pages. * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so * we account it too. */ if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) return; /* * If we got here with no pages scanned, then that is an indicator * that reclaimer was unable to find any shrinkable LRUs at the * current scanning depth. But it does not mean that we should * report the critical pressure, yet. If the scanning priority * (scanning depth) goes too high (deep), we will be notified * through vmpressure_prio(). But so far, keep calm. */ if (!scanned) return; if (tree) { spin_lock(&vmpr->sr_lock); scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) return; schedule_work(&vmpr->work); } else { enum vmpressure_levels level; /* For now, no users for root-level efficiency */ if (!memcg || mem_cgroup_is_root(memcg)) return; spin_lock(&vmpr->sr_lock); scanned = vmpr->scanned += scanned; reclaimed = vmpr->reclaimed += reclaimed; if (scanned < vmpressure_win) { spin_unlock(&vmpr->sr_lock); return; } vmpr->scanned = vmpr->reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); if (level > VMPRESSURE_LOW) { /* * Let the socket buffer allocator know that * we are having trouble reclaiming LRU pages. * * For hysteresis keep the pressure state * asserted for a second in which subsequent * pressure events can occur. */ mem_cgroup_set_socket_pressure(memcg); } } } /** * vmpressure_prio() - Account memory pressure through reclaimer priority level * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @prio: reclaimer's priority * * This function should be called from the reclaim path every time when * the vmscan's reclaiming priority (scanning depth) changes. * * This function does not return any value. */ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) { /* * We only use prio for accounting critical level. For more info * see comment for vmpressure_level_critical_prio variable above. */ if (prio > vmpressure_level_critical_prio) return; /* * OK, the prio is below the threshold, updating vmpressure * information before shrinker dives into long shrinking of long * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 * to the vmpressure() basically means that we signal 'critical' * level. */ vmpressure(gfp, memcg, true, vmpressure_win, 0); } #define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the * @eventfd. The @args parameter is a comma-delimited string that denotes a * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. * "hierarchy" or "local"). * * To be used as memcg event method. * * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL); if (!spec) return -ENOMEM; /* Find required level */ token = strsep(&spec, ","); ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); if (ret < 0) goto out; level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); if (ret < 0) goto out; mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { ret = -ENOMEM; goto out; } ev->efd = eventfd; ev->level = level; ev->mode = mode; mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); ret = 0; out: kfree(spec_orig); return ret; } /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure * @memcg: memcg handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * * This function does internal manipulations to detach the @eventfd from * the vmpressure notifications, and then frees internal resources * associated with the @eventfd (but the @eventfd itself is not freed). * * To be used as memcg event method. */ void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ev->efd != eventfd) continue; list_del(&ev->node); kfree(ev); break; } mutex_unlock(&vmpr->events_lock); } /** * vmpressure_init() - Initialize vmpressure control structure * @vmpr: Structure to be initialized * * This function should be called on every allocated vmpressure structure * before any usage. */ void vmpressure_init(struct vmpressure *vmpr) { spin_lock_init(&vmpr->sr_lock); mutex_init(&vmpr->events_lock); INIT_LIST_HEAD(&vmpr->events); INIT_WORK(&vmpr->work, vmpressure_work_fn); } /** * vmpressure_cleanup() - shuts down vmpressure control structure * @vmpr: Structure to be cleaned up * * This function should be called before the structure in which it is * embedded is cleaned up. */ void vmpressure_cleanup(struct vmpressure *vmpr) { /* * Make sure there is no pending work before eventfd infrastructure * goes away. */ flush_work(&vmpr->work); } |
| 104 104 1068 24 24 48 39 105 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sched #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCHED_H #include <linux/kthread.h> #include <linux/sched/numa_balancing.h> #include <linux/tracepoint.h> #include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: */ TRACE_EVENT(sched_kthread_stop, TP_PROTO(struct task_struct *t), TP_ARGS(t), TP_STRUCT__entry( __string( comm, t->comm ) __field( pid_t, pid ) ), TP_fast_assign( __assign_str(comm); __entry->pid = t->pid; ), TP_printk("comm=%s pid=%d", __get_str(comm), __entry->pid) ); /* * Tracepoint for the return value of the kthread stopping: */ TRACE_EVENT(sched_kthread_stop_ret, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( int, ret ) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); /** * sched_kthread_work_queue_work - called when a work gets queued * @worker: pointer to the kthread_worker * @work: pointer to struct kthread_work * * This event occurs when a work is queued immediately or once a * delayed work is actually queued (ie: once the delay has been * reached). */ TRACE_EVENT(sched_kthread_work_queue_work, TP_PROTO(struct kthread_worker *worker, struct kthread_work *work), TP_ARGS(worker, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __field( void *, worker) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __entry->worker = worker; ), TP_printk("work struct=%p function=%ps worker=%p", __entry->work, __entry->function, __entry->worker) ); /** * sched_kthread_work_execute_start - called immediately before the work callback * @work: pointer to struct kthread_work * * Allows to track kthread work execution. */ TRACE_EVENT(sched_kthread_work_execute_start, TP_PROTO(struct kthread_work *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * sched_kthread_work_execute_end - called immediately after the work callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(sched_kthread_work_execute_end, TP_PROTO(struct kthread_work *work, kthread_work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /* * Tracepoint for waking up a task: */ DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct task_struct *p), TP_ARGS(__perf_task(p)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, target_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->target_cpu = task_cpu(p); ), TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d", __entry->comm, __entry->pid, __entry->prio, __entry->target_cpu) ); /* * Tracepoint called when waking a task; this tracepoint is guaranteed to be * called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waking up a new task: */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p), TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS static inline long __trace_sched_switch_state(bool preempt, unsigned int prev_state, struct task_struct *p) { unsigned int state; BUG_ON(p != current); /* * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ if (preempt) return TASK_REPORT_MAX; /* * task_state_index() uses fls() and returns a value from 0-8 range. * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using * it for left shift operation to get the correct task->state * mapping. */ state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } #endif /* CREATE_TRACE_POINTS */ /* * Tracepoint for task switches, performed by the scheduler: */ TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, struct task_struct *prev, struct task_struct *next, unsigned int prev_state), TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) __field( pid_t, prev_pid ) __field( int, prev_prio ) __field( long, prev_state ) __array( char, next_comm, TASK_COMM_LEN ) __field( pid_t, next_pid ) __field( int, next_prio ) ), TP_fast_assign( memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { TASK_INTERRUPTIBLE, "S" }, { TASK_UNINTERRUPTIBLE, "D" }, { __TASK_STOPPED, "T" }, { __TASK_TRACED, "t" }, { EXIT_DEAD, "X" }, { EXIT_ZOMBIE, "Z" }, { TASK_PARKED, "P" }, { TASK_DEAD, "I" }) : "R", __entry->prev_state & TASK_REPORT_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); /* * Tracepoint for a task being migrated: */ TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu), TP_ARGS(p, dest_cpu), TP_STRUCT__entry( __string( comm, p->comm ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) ), TP_fast_assign( __assign_str(comm); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d", __get_str(comm), __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu) ); DECLARE_EVENT_CLASS(sched_process_template, TP_PROTO(struct task_struct *p), TP_ARGS(p), TP_STRUCT__entry( __string( comm, p->comm ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __get_str(comm), __entry->pid, __entry->prio) ); /* * Tracepoint for freeing a task: */ DEFINE_EVENT(sched_process_template, sched_process_free, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a task exiting. * Note, it's a superset of sched_process_template and should be kept * compatible as much as possible. sched_process_exits has an extra * `group_dead` argument, so sched_process_template can't be used, * unfortunately, just like sched_migrate_task above. */ TRACE_EVENT(sched_process_exit, TP_PROTO(struct task_struct *p, bool group_dead), TP_ARGS(p, group_dead), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( bool, group_dead ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->group_dead = group_dead; ), TP_printk("comm=%s pid=%d prio=%d group_dead=%s", __entry->comm, __entry->pid, __entry->prio, __entry->group_dead ? "true" : "false" ) ); /* * Tracepoint for waiting on task to unschedule: */ DEFINE_EVENT(sched_process_template, sched_wait_task, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a waiting task: */ TRACE_EVENT(sched_process_wait, TP_PROTO(struct pid *pid), TP_ARGS(pid), TP_STRUCT__entry( __string( comm, current->comm ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = pid_nr(pid); __entry->prio = current->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __get_str(comm), __entry->pid, __entry->prio) ); /* * Tracepoint for kernel_clone: */ TRACE_EVENT(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child), TP_ARGS(parent, child), TP_STRUCT__entry( __string( parent_comm, parent->comm ) __field( pid_t, parent_pid ) __string( child_comm, child->comm ) __field( pid_t, child_pid ) ), TP_fast_assign( __assign_str(parent_comm); __entry->parent_pid = parent->pid; __assign_str(child_comm); __entry->child_pid = child->pid; ), TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d", __get_str(parent_comm), __entry->parent_pid, __get_str(child_comm), __entry->child_pid) ); /* * Tracepoint for exec: */ TRACE_EVENT(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm), TP_ARGS(p, old_pid, bprm), TP_STRUCT__entry( __string( filename, bprm->filename ) __field( pid_t, pid ) __field( pid_t, old_pid ) ), TP_fast_assign( __assign_str(filename); __entry->pid = p->pid; __entry->old_pid = old_pid; ), TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), __entry->pid, __entry->old_pid) ); /** * sched_prepare_exec - called before setting up new exec * @task: pointer to the current task * @bprm: pointer to linux_binprm used for new exec * * Called before flushing the old exec, where @task is still unchanged, but at * the point of no return during switching to the new exec. At the point it is * called the exec will either succeed, or on failure terminate the task. Also * see the "sched_process_exec" tracepoint, which is called right after @task * has successfully switched to the new exec. */ TRACE_EVENT(sched_prepare_exec, TP_PROTO(struct task_struct *task, struct linux_binprm *bprm), TP_ARGS(task, bprm), TP_STRUCT__entry( __string( interp, bprm->interp ) __string( filename, bprm->filename ) __field( pid_t, pid ) __string( comm, task->comm ) ), TP_fast_assign( __assign_str(interp); __assign_str(filename); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("interp=%s filename=%s pid=%d comm=%s", __get_str(interp), __get_str(filename), __entry->pid, __get_str(comm)) ); #ifdef CONFIG_SCHEDSTATS #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS #else #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT_NOP #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS_NOP #endif /* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ DECLARE_EVENT_CLASS_SCHEDSTAT(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(__perf_task(tsk), __perf_count(delay)), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( u64, delay ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->delay = delay; ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", __get_str(comm), __entry->pid, (unsigned long long)__entry->delay) ); /* * Tracepoint for accounting wait time (time the task is runnable * but not actually running due to scheduler contention). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_wait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting sleep time (time the task is not runnable, * including iowait, see below). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_sleep, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting iowait time (time the task is not runnable * due to waiting on IO to complete). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_iowait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting blocked time (time the task is in uninterruptible). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ DECLARE_EVENT_CLASS(sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, __perf_count(runtime)), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( u64, runtime ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->runtime = runtime; ), TP_printk("comm=%s pid=%d runtime=%Lu [ns]", __get_str(comm), __entry->pid, (unsigned long long)__entry->runtime) ); DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, runtime)); /* * Tracepoint for showing priority inheritance modifying a tasks * priority. */ TRACE_EVENT(sched_pi_setprio, TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task), TP_ARGS(tsk, pi_task), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) __field( int, oldprio ) __field( int, newprio ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; __entry->oldprio = tsk->prio; __entry->newprio = pi_task ? min(tsk->normal_prio, pi_task->prio) : tsk->normal_prio; /* XXX SCHED_DEADLINE bits missing */ ), TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", __get_str(comm), __entry->pid, __entry->oldprio, __entry->newprio) ); #ifdef CONFIG_DETECT_HUNG_TASK TRACE_EVENT(sched_process_hang, TP_PROTO(struct task_struct *tsk), TP_ARGS(tsk), TP_STRUCT__entry( __string( comm, tsk->comm ) __field( pid_t, pid ) ), TP_fast_assign( __assign_str(comm); __entry->pid = tsk->pid; ), TP_printk("comm=%s pid=%d", __get_str(comm), __entry->pid) ); #endif /* CONFIG_DETECT_HUNG_TASK */ #ifdef CONFIG_NUMA_BALANCING /* * Tracks migration of tasks from one runqueue to another. Can be used to * detect if automatic NUMA balancing is bouncing between nodes. */ TRACE_EVENT(sched_move_numa, TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), TP_ARGS(tsk, src_cpu, dst_cpu), TP_STRUCT__entry( __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_cpu = dst_cpu; __entry->dst_nid = cpu_to_node(dst_cpu); ), TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", __entry->pid, __entry->tgid, __entry->ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_cpu, __entry->dst_nid) ); DECLARE_EVENT_CLASS(sched_numa_pair_template, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), TP_STRUCT__entry( __field( pid_t, src_pid ) __field( pid_t, src_tgid ) __field( pid_t, src_ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( pid_t, dst_pid ) __field( pid_t, dst_tgid ) __field( pid_t, dst_ngid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->src_pid = task_pid_nr(src_tsk); __entry->src_tgid = task_tgid_nr(src_tsk); __entry->src_ngid = task_numa_group_id(src_tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0; __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0; __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0; __entry->dst_cpu = dst_cpu; __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1; ), TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", __entry->src_pid, __entry->src_tgid, __entry->src_ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, __entry->dst_cpu, __entry->dst_nid) ); DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); #define NUMAB_SKIP_REASON \ EM( NUMAB_SKIP_UNSUITABLE, "unsuitable" ) \ EM( NUMAB_SKIP_SHARED_RO, "shared_ro" ) \ EM( NUMAB_SKIP_INACCESSIBLE, "inaccessible" ) \ EM( NUMAB_SKIP_SCAN_DELAY, "scan_delay" ) \ EM( NUMAB_SKIP_PID_INACTIVE, "pid_inactive" ) \ EM( NUMAB_SKIP_IGNORE_PID, "ignore_pid_inactive" ) \ EMe(NUMAB_SKIP_SEQ_COMPLETED, "seq_completed" ) /* Redefine for export. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); NUMAB_SKIP_REASON /* Redefine for symbolic printing. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } TRACE_EVENT(sched_skip_vma_numa, TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma, enum numa_vmaskip_reason reason), TP_ARGS(mm, vma, reason), TP_STRUCT__entry( __field(unsigned long, numa_scan_offset) __field(unsigned long, vm_start) __field(unsigned long, vm_end) __field(enum numa_vmaskip_reason, reason) ), TP_fast_assign( __entry->numa_scan_offset = mm->numa_scan_offset; __entry->vm_start = vma->vm_start; __entry->vm_end = vma->vm_end; __entry->reason = reason; ), TP_printk("numa_scan_offset=%lX vm_start=%lX vm_end=%lX reason=%s", __entry->numa_scan_offset, __entry->vm_start, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); TRACE_EVENT(sched_skip_cpuset_numa, TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr), TP_ARGS(tsk, mem_allowed_ptr), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __array( unsigned long, mem_allowed, BITS_TO_LONGS(MAX_NUMNODES)) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); BUILD_BUG_ON(sizeof(nodemask_t) != \ BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long)); memcpy(__entry->mem_allowed, mem_allowed_ptr->bits, sizeof(__entry->mem_allowed)); ), TP_printk("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl", __entry->comm, __entry->pid, __entry->tgid, __entry->ngid, MAX_NUMNODES, __entry->mem_allowed) ); #endif /* CONFIG_NUMA_BALANCING */ /* * Tracepoint for waking a polling cpu without an IPI. */ TRACE_EVENT(sched_wake_idle_without_ipi, TP_PROTO(int cpu), TP_ARGS(cpu), TP_STRUCT__entry( __field( int, cpu ) ), TP_fast_assign( __entry->cpu = cpu; ), TP_printk("cpu=%d", __entry->cpu) ); /* * Following tracepoints are not exported in tracefs and provide hooking * mechanisms only for testing and debugging purposes. */ DECLARE_TRACE(pelt_cfs, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(pelt_rt, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_dl, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_hw, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_irq, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_se, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_cpu_capacity, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(sched_overutilized, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); DECLARE_TRACE(sched_util_est_cfs, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(sched_util_est_se, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_update_nr_running, TP_PROTO(struct rq *rq, int change), TP_ARGS(rq, change)); DECLARE_TRACE(sched_compute_energy, TP_PROTO(struct task_struct *p, int dst_cpu, unsigned long energy, unsigned long max_util, unsigned long busy_time), TP_ARGS(p, dst_cpu, energy, max_util, busy_time)); DECLARE_TRACE(sched_entry, TP_PROTO(bool preempt), TP_ARGS(preempt)); DECLARE_TRACE(sched_exit, TP_PROTO(bool is_switch), TP_ARGS(is_switch)); DECLARE_TRACE_CONDITION(sched_set_state, TP_PROTO(struct task_struct *tsk, int state), TP_ARGS(tsk, state), TP_CONDITION(!!(tsk->__state) != !!state)); DECLARE_TRACE(sched_set_need_resched, TP_PROTO(struct task_struct *tsk, int cpu, int tif), TP_ARGS(tsk, cpu, tif)); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 226 226 226 226 226 226 225 225 146 225 225 10 224 10 225 2 2 2 225 226 226 196 96 55 196 193 195 194 18 195 191 193 195 195 194 39 194 195 223 222 223 222 223 223 222 222 223 127 223 112 223 222 106 27 80 223 223 92 223 223 2 223 223 222 222 223 223 222 235 140 1 1 1 1 1 1 1 1 268 263 195 81 153 154 166 166 199 199 199 199 199 199 198 74 198 74 199 199 199 153 4 190 10 10 10 10 10 10 10 10 1 1 1 1 1 1 1 1 1 1 1 1 231 231 226 226 225 1 226 223 221 224 78 78 78 78 78 78 45 45 29 45 12 2 10 42 45 1 45 45 10 10 10 7 74 74 74 74 74 74 1 18 74 225 225 225 225 225 146 225 104 110 111 111 1 110 1 111 111 193 191 191 193 193 | 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 | // 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 Intel Corp. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * This module provides the abstraction for an SCTP association. * * 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> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ryan Layer <rmlayer@us.ibm.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/in.h> #include <net/ipv6.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* Forward declarations for internal functions. */ static void sctp_select_active_and_retran_path(struct sctp_association *asoc); static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc); /* 1st Level Abstractions. */ /* Initialize a new association from provided memory. */ static struct sctp_association *sctp_association_init( struct sctp_association *asoc, const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_sock *sp; struct sctp_paramhdr *p; int i; /* Retrieve the SCTP per socket area. */ sp = sctp_sk((struct sock *)sk); /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; asoc->base.sk = (struct sock *)sk; asoc->base.net = sock_net(sk); sctp_endpoint_hold(asoc->ep); sock_hold(asoc->base.sk); /* Initialize the common base substructure. */ asoc->base.type = SCTP_EP_TYPE_ASSOCIATION; /* Initialize the object handling fields. */ refcount_set(&asoc->base.refcnt, 1); /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); asoc->state = SCTP_STATE_CLOSED; asoc->cookie_life = ms_to_ktime(sp->assocparams.sasoc_cookie_life); asoc->user_frag = sp->user_frag; /* Set the association max_retrans and RTO values from the * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; asoc->pf_retrans = sp->pf_retrans; asoc->ps_retrans = sp->ps_retrans; asoc->pf_expose = sp->pf_expose; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min); /* Initialize the association's heartbeat interval based on the * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; asoc->flowlabel = sp->flowlabel; asoc->dscp = sp->dscp; /* Set association default SACK delay */ asoc->sackdelay = msecs_to_jiffies(sp->sackdelay); asoc->sackfreq = sp->sackfreq; /* Set the association default flags controlling * Heartbeat, SACK delay, and Path MTU Discovery. */ asoc->param_flags = sp->param_flags; /* Initialize the maximum number of new data packets that can be sent * in a burst. */ asoc->max_burst = sp->max_burst; asoc->subscribe = sp->subscribe; /* initialize association timers */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = asoc->rto_initial; /* sctpimpguide Section 2.12.2 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the * recommended value of 5 times 'RTO.Max'. */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = (unsigned long)sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) timer_setup(&asoc->timers[i], sctp_timer_events[i], 0); /* Pull default initialization values from the sock options. * Note: This assumes that the values have already been * validated in the sock. */ asoc->c.sinit_max_instreams = sp->initmsg.sinit_max_instreams; asoc->c.sinit_num_ostreams = sp->initmsg.sinit_num_ostreams; asoc->max_init_attempts = sp->initmsg.sinit_max_attempts; asoc->max_init_timeo = msecs_to_jiffies(sp->initmsg.sinit_max_init_timeo); /* Set the local window size for receive. * This is also the rcvbuf space per association. * RFC 6 - A SCTP receiver MUST be able to receive a minimum of * 1500 bytes in one SCTP packet. */ if ((sk->sk_rcvbuf/2) < SCTP_DEFAULT_MINWINDOW) asoc->rwnd = SCTP_DEFAULT_MINWINDOW; else asoc->rwnd = sk->sk_rcvbuf/2; asoc->a_rwnd = asoc->rwnd; /* Use my own max window until I learn something better. */ asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW; /* Initialize the receive memory counter */ atomic_set(&asoc->rmem_alloc, 0); init_waitqueue_head(&asoc->wait); asoc->c.my_vtag = sctp_generate_tag(ep); asoc->c.my_port = ep->base.bind_addr.port; asoc->c.initial_tsn = sctp_generate_tsn(ep); asoc->next_tsn = asoc->c.initial_tsn; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; asoc->highest_sacked = asoc->ctsn_ack_point; asoc->last_cwr_tsn = asoc->ctsn_ack_point; /* ADDIP Section 4.1 Asconf Chunk Procedures * * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do the following: * ... * A2) a serial number should be assigned to the chunk. The serial * number SHOULD be a monotonically increasing number. The serial * numbers SHOULD be initialized at the start of the * association to the same value as the initial TSN. */ asoc->addip_serial = asoc->c.initial_tsn; asoc->strreset_outseq = asoc->c.initial_tsn; INIT_LIST_HEAD(&asoc->addip_chunk_list); INIT_LIST_HEAD(&asoc->asconf_ack_list); /* Make an empty list of remote transport addresses. */ INIT_LIST_HEAD(&asoc->peer.transport_addr_list); /* RFC 2960 5.1 Normal Establishment of an Association * * After the reception of the first data chunk in an * association the endpoint must immediately respond with a * sack to acknowledge the data chunk. Subsequent * acknowledgements should be done as described in Section * 6.2. * * [We implement this by telling a new association that it * already received one packet.] */ asoc->peer.sack_needed = 1; asoc->peer.sack_generation = 1; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); sctp_inq_set_th_handler(&asoc->base.inqueue, sctp_assoc_bh_rcv); /* Create an output queue. */ sctp_outq_init(asoc, &asoc->outqueue); sctp_ulpq_init(&asoc->ulpq, asoc); if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) goto stream_free; /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; sctp_assoc_update_frag_point(asoc); /* Assume that peer would support both address types unless we are * told otherwise. */ asoc->peer.ipv4_address = 1; if (asoc->base.sk->sk_family == PF_INET6) asoc->peer.ipv6_address = 1; INIT_LIST_HEAD(&asoc->asocs); asoc->default_stream = sp->default_stream; asoc->default_ppid = sp->default_ppid; asoc->default_flags = sp->default_flags; asoc->default_context = sp->default_context; asoc->default_timetolive = sp->default_timetolive; asoc->default_rcv_context = sp->default_rcv_context; /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp)) goto stream_free; asoc->active_key_id = ep->active_key_id; asoc->strreset_enable = ep->strreset_enable; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) memcpy(asoc->c.auth_hmacs, ep->auth_hmacs_list, ntohs(ep->auth_hmacs_list->param_hdr.length)); if (ep->auth_chunk_list) memcpy(asoc->c.auth_chunks, ep->auth_chunk_list, ntohs(ep->auth_chunk_list->param_hdr.length)); /* Get the AUTH random number for this association */ p = (struct sctp_paramhdr *)asoc->c.auth_random; p->type = SCTP_PARAM_RANDOM; p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH); get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH); return asoc; stream_free: sctp_stream_free(&asoc->stream); sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); return NULL; } /* Allocate and initialize a new association */ struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_association *asoc; asoc = kzalloc(sizeof(*asoc), gfp); if (!asoc) goto fail; if (!sctp_association_init(asoc, ep, sk, scope, gfp)) goto fail_init; SCTP_DBG_OBJCNT_INC(assoc); pr_debug("Created asoc %p\n", asoc); return asoc; fail_init: kfree(asoc); fail: return NULL; } /* Free this association if possible. There may still be users, so * the actual deallocation may be delayed. */ void sctp_association_free(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; struct sctp_transport *transport; struct list_head *pos, *temp; int i; /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening * socket. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) sk_acceptq_removed(sk); } /* Mark as dead, so other users can know this structure is * going away. */ asoc->base.dead = true; /* Dispose of any data lying around in the outqueue. */ sctp_outq_free(&asoc->outqueue); /* Dispose of any pending messages for the upper layer. */ sctp_ulpq_free(&asoc->ulpq); /* Dispose of any pending chunks on the inqueue. */ sctp_inq_free(&asoc->base.inqueue); sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); /* Clean up the bound address list. */ sctp_bind_addr_free(&asoc->base.bind_addr); /* Do we need to go through all of our timers and * delete them? To be safe we will try to delete all, but we * should be able to go through and make a guess based * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { if (timer_delete(&asoc->timers[i])) sctp_association_put(asoc); } /* Free peer's cached cookie. */ kfree(asoc->peer.cookie); kfree(asoc->peer.peer_random); kfree(asoc->peer.peer_chunks); kfree(asoc->peer.peer_hmacs); /* Release the transport structures. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); list_del_rcu(pos); sctp_unhash_transport(transport); sctp_transport_free(transport); } asoc->peer.transport_count = 0; sctp_asconf_queue_teardown(asoc); /* Free pending address space being deleted */ kfree(asoc->asconf_addr_del_pending); /* AUTH - Free the endpoint shared keys */ sctp_auth_destroy_keys(&asoc->endpoint_shared_keys); /* AUTH - Free the association shared key */ sctp_auth_key_put(asoc->asoc_shared_key); sctp_association_put(asoc); } /* Cleanup and free up an association. */ static void sctp_association_destroy(struct sctp_association *asoc) { if (unlikely(!asoc->base.dead)) { WARN(1, "Attempt to destroy undead association %p!\n", asoc); return; } sctp_endpoint_put(asoc->ep); sock_put(asoc->base.sk); if (asoc->assoc_id != 0) { spin_lock_bh(&sctp_assocs_id_lock); idr_remove(&sctp_assocs_id, asoc->assoc_id); spin_unlock_bh(&sctp_assocs_id_lock); } WARN_ON(atomic_read(&asoc->rmem_alloc)); kfree_rcu(asoc, rcu); SCTP_DBG_OBJCNT_DEC(assoc); } /* Change the primary destination address for the peer. */ void sctp_assoc_set_primary(struct sctp_association *asoc, struct sctp_transport *transport) { int changeover = 0; /* it's a changeover only if we already have a primary path * that we are changing */ if (asoc->peer.primary_path != NULL && asoc->peer.primary_path != transport) changeover = 1 ; asoc->peer.primary_path = transport; sctp_ulpevent_notify_peer_addr_change(transport, SCTP_ADDR_MADE_PRIM, 0); /* Set a default msg_name for events. */ memcpy(&asoc->peer.primary_addr, &transport->ipaddr, sizeof(union sctp_addr)); /* If the primary path is changing, assume that the * user wants to use this new path. */ if ((transport->state == SCTP_ACTIVE) || (transport->state == SCTP_UNKNOWN)) asoc->peer.active_path = transport; /* * SFR-CACC algorithm: * Upon the receipt of a request to change the primary * destination address, on the data structure for the new * primary destination, the sender MUST do the following: * * 1) If CHANGEOVER_ACTIVE is set, then there was a switch * to this destination address earlier. The sender MUST set * CYCLING_CHANGEOVER to indicate that this switch is a * double switch to the same destination address. * * Really, only bother is we have data queued or outstanding on * the association. */ if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen) return; if (transport->cacc.changeover_active) transport->cacc.cycling_changeover = changeover; /* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that * a changeover has occurred. */ transport->cacc.changeover_active = changeover; /* 3) The sender MUST store the next TSN to be sent in * next_tsn_at_change. */ transport->cacc.next_tsn_at_change = asoc->next_tsn; } /* Remove a transport from an association. */ void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer) { struct sctp_transport *transport; struct list_head *pos; struct sctp_chunk *ch; pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, &peer->ipaddr.sa); /* If we are to remove the current retran_path, update it * to the next peer before removing this peer from the list. */ if (asoc->peer.retran_path == peer) sctp_assoc_update_retran_path(asoc); /* Remove this peer from the list. */ list_del_rcu(&peer->transports); /* Remove this peer from the transport hashtable */ sctp_unhash_transport(peer); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; transport = list_entry(pos, struct sctp_transport, transports); /* Update any entries that match the peer to be deleted. */ if (asoc->peer.primary_path == peer) sctp_assoc_set_primary(asoc, transport); if (asoc->peer.active_path == peer) asoc->peer.active_path = transport; if (asoc->peer.retran_path == peer) asoc->peer.retran_path = transport; if (asoc->peer.last_data_from == peer) asoc->peer.last_data_from = transport; if (asoc->strreset_chunk && asoc->strreset_chunk->transport == peer) { asoc->strreset_chunk->transport = transport; sctp_transport_reset_reconf_timer(transport); } /* If we remove the transport an INIT was last sent to, set it to * NULL. Combined with the update of the retran path above, this * will cause the next INIT to be sent to the next available * transport, maintaining the cycle. */ if (asoc->init_last_sent_to == peer) asoc->init_last_sent_to = NULL; /* If we remove the transport an SHUTDOWN was last sent to, set it * to NULL. Combined with the update of the retran path above, this * will cause the next SHUTDOWN to be sent to the next available * transport, maintaining the cycle. */ if (asoc->shutdown_last_sent_to == peer) asoc->shutdown_last_sent_to = NULL; /* If we remove the transport an ASCONF was last sent to, set it to * NULL. */ if (asoc->addip_last_asconf && asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; /* If we have something on the transmitted list, we have to * save it off. The best place is the active path. */ if (!list_empty(&peer->transmitted)) { struct sctp_transport *active = asoc->peer.active_path; /* Reset the transport of each chunk on this list */ list_for_each_entry(ch, &peer->transmitted, transmitted_list) { ch->transport = NULL; ch->rtt_in_progress = 0; } list_splice_tail_init(&peer->transmitted, &active->transmitted); /* Start a T3 timer here in case it wasn't running so * that these migrated packets have a chance to get * retransmitted. */ if (!timer_pending(&active->T3_rtx_timer)) if (!mod_timer(&active->T3_rtx_timer, jiffies + active->rto)) sctp_transport_hold(active); } list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) if (ch->transport == peer) ch->transport = NULL; asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); sctp_transport_free(peer); } /* Add a transport address to an association. */ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, const union sctp_addr *addr, const gfp_t gfp, const int peer_state) { struct sctp_transport *peer; struct sctp_sock *sp; unsigned short port; sp = sctp_sk(asoc->base.sk); /* AF_INET and AF_INET6 share common port field. */ port = ntohs(addr->v4.sin_port); pr_debug("%s: association:%p addr:%pISpc state:%d\n", __func__, asoc, &addr->sa, peer_state); /* Set the port if it has not been set yet. */ if (0 == asoc->peer.port) asoc->peer.port = port; /* Check to see if this is a duplicate. */ peer = sctp_assoc_lookup_paddr(asoc, addr); if (peer) { /* An UNKNOWN state is only set on transports added by * user in sctp_connectx() call. Such transports should be * considered CONFIRMED per RFC 4960, Section 5.4. */ if (peer->state == SCTP_UNKNOWN) { peer->state = SCTP_ACTIVE; } return peer; } peer = sctp_transport_new(asoc->base.net, addr, gfp); if (!peer) return NULL; sctp_transport_set_owner(peer, asoc); /* Initialize the peer's heartbeat interval based on the * association configured value. */ peer->hbinterval = asoc->hbinterval; peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; /* And the partial failure retrans threshold */ peer->pf_retrans = asoc->pf_retrans; /* And the primary path switchover retrans threshold */ peer->ps_retrans = asoc->ps_retrans; /* Initialize the peer's SACK delay timeout based on the * association configured value. */ peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; if (addr->sa.sa_family == AF_INET6) { __be32 info = addr->v6.sin6_flowinfo; if (info) { peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK); peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } else { peer->flowlabel = asoc->flowlabel; } } peer->dscp = asoc->dscp; /* Enable/disable heartbeat, SACK delay, and path MTU discovery * based on association setting. */ peer->param_flags = asoc->param_flags; /* Initialize the pmtu of the transport. */ sctp_transport_route(peer, NULL, sp); /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. * If not and the current association PMTU is higher than the new * peer's PMTU, reset the association PMTU to the new peer's PMTU. */ sctp_assoc_set_pmtu(asoc, asoc->pathmtu ? min_t(int, peer->pathmtu, asoc->pathmtu) : peer->pathmtu); peer->pmtu_pending = 0; /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. */ sctp_packet_init(&peer->packet, peer, asoc->base.bind_addr.port, asoc->peer.port); /* 7.2.1 Slow-Start * * o The initial cwnd before DATA transmission or after a sufficiently * long idle period MUST be set to * min(4*MTU, max(2*MTU, 4380 bytes)) * * o The initial value of ssthresh MAY be arbitrarily high * (for example, implementations MAY use the size of the * receiver advertised window). */ peer->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); /* At this point, we may not have the receiver's advertised window, * so initialize ssthresh to the default value and it will be set * later when we process the INIT. */ peer->ssthresh = SCTP_DEFAULT_MAXWINDOW; peer->partial_bytes_acked = 0; peer->flight_size = 0; peer->burst_limited = 0; /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; sctp_max_rto(asoc, peer); /* Set the peer's active state. */ peer->state = peer_state; /* Add this peer into the transport hashtable */ if (sctp_hash_transport(peer)) { sctp_transport_free(peer); return NULL; } sctp_transport_pl_reset(peer); /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_ADDED, 0); /* If we do not yet have a primary path, set one. */ if (!asoc->peer.primary_path) { sctp_assoc_set_primary(asoc, peer); asoc->peer.retran_path = peer; } if (asoc->peer.active_path == asoc->peer.retran_path && peer->state != SCTP_UNCONFIRMED) { asoc->peer.retran_path = peer; } return peer; } /* Lookup a transport by address. */ struct sctp_transport *sctp_assoc_lookup_paddr( const struct sctp_association *asoc, const union sctp_addr *address) { struct sctp_transport *t; /* Cycle through all transports searching for a peer address. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (sctp_cmp_addr_exact(address, &t->ipaddr)) return t; } return NULL; } /* Remove all transports except a give one */ void sctp_assoc_del_nonprimary_peers(struct sctp_association *asoc, struct sctp_transport *primary) { struct sctp_transport *temp; struct sctp_transport *t; list_for_each_entry_safe(t, temp, &asoc->peer.transport_addr_list, transports) { /* if the current transport is not the primary one, delete it */ if (t != primary) sctp_assoc_rm_peer(asoc, t); } } /* Engage in transport control operations. * Mark the transport up or down and send a notification to the user. * Select and update the new active and retran paths. */ void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_transport *transport, enum sctp_transport_cmd command, sctp_sn_error_t error) { int spc_state = SCTP_ADDR_AVAILABLE; bool ulp_notify = true; /* Record the transition on the transport. */ switch (command) { case SCTP_TRANSPORT_UP: /* If we are moving from UNCONFIRMED state due * to heartbeat success, report the SCTP_ADDR_CONFIRMED * state to the user, otherwise report SCTP_ADDR_AVAILABLE. */ if (transport->state == SCTP_PF && asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else if (transport->state == SCTP_UNCONFIRMED && error == SCTP_HEARTBEAT_SUCCESS) spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: /* If the transport was never confirmed, do not transition it * to inactive state. Also, release the cached route since * there may be a better route next time. */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); ulp_notify = false; } break; case SCTP_TRANSPORT_PF: transport->state = SCTP_PF; if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else spc_state = SCTP_ADDR_POTENTIALLY_FAILED; break; default: return; } /* Generate and send a SCTP_PEER_ADDR_CHANGE notification * to the user. */ if (ulp_notify) sctp_ulpevent_notify_peer_addr_change(transport, spc_state, error); /* Select new active and retran paths. */ sctp_select_active_and_retran_path(asoc); } /* Hold a reference to an association. */ void sctp_association_hold(struct sctp_association *asoc) { refcount_inc(&asoc->base.refcnt); } /* Release a reference to an association and cleanup * if there are no more references. */ void sctp_association_put(struct sctp_association *asoc) { if (refcount_dec_and_test(&asoc->base.refcnt)) sctp_association_destroy(asoc); } /* Allocate the next TSN, Transmission Sequence Number, for the given * association. */ __u32 sctp_association_get_next_tsn(struct sctp_association *asoc) { /* From Section 1.6 Serial Number Arithmetic: * Transmission Sequence Numbers wrap around when they reach * 2**32 - 1. That is, the next TSN a DATA chunk MUST use * after transmitting TSN = 2*32 - 1 is TSN = 0. */ __u32 retval = asoc->next_tsn; asoc->next_tsn++; asoc->unack_data++; return retval; } /* Compare two addresses to see if they match. Wildcard addresses * only match themselves. */ int sctp_cmp_addr_exact(const union sctp_addr *ss1, const union sctp_addr *ss2) { struct sctp_af *af; af = sctp_get_af_specific(ss1->sa.sa_family); if (unlikely(!af)) return 0; return af->cmp_addr(ss1, ss2); } /* Return an ecne chunk to get prepended to a packet. * Note: We are sly and return a shared, prealloced chunk. FIXME: * No we don't, but we could/should. */ struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc) { if (!asoc->need_ecne) return NULL; /* Send ECNE if needed. * Not being able to allocate a chunk here is not deadly. */ return sctp_make_ecne(asoc, asoc->last_ecne_tsn); } /* * Find which transport this TSN was sent on. */ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc, __u32 tsn) { struct sctp_transport *active; struct sctp_transport *match; struct sctp_transport *transport; struct sctp_chunk *chunk; __be32 key = htonl(tsn); match = NULL; /* * FIXME: In general, find a more efficient data structure for * searching. */ /* * The general strategy is to search each transport's transmitted * list. Return which transport this TSN lives on. * * Let's be hopeful and check the active_path first. * Another optimization would be to know if there is only one * outbound path and not have to look for the TSN at all. * */ active = asoc->peer.active_path; list_for_each_entry(chunk, &active->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = active; goto out; } } /* If not found, go search all the other transports. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { if (transport == active) continue; list_for_each_entry(chunk, &transport->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = transport; goto out; } } } out: return match; } /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { struct sctp_association *asoc = container_of(work, struct sctp_association, base.inqueue.immediate); struct net *net = asoc->base.net; union sctp_subtype subtype; struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; int first_time = 1; /* is this the first time through the loop */ int error = 0; int state; /* The association should be held so we should be safe. */ ep = asoc->ep; inqueue = &asoc->base.inqueue; sctp_association_hold(asoc); while (NULL != (chunk = sctp_inq_pop(inqueue))) { state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); /* If the first chunk in the packet is AUTH, do special * processing specified in Section 6.3 of SCTP-AUTH spec */ if (first_time && subtype.chunk == SCTP_CID_AUTH) { struct sctp_chunkhdr *next_hdr; next_hdr = sctp_inq_peek(inqueue); if (!next_hdr) goto normal; /* If the next chunk is COOKIE-ECHO, skip the AUTH * chunk while saving a pointer to it so we can do * Authentication later (during cookie-echo * processing). */ if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { chunk->auth_chunk = skb_clone(chunk->skb, GFP_ATOMIC); chunk->auth = 1; continue; } } normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has * been sent to the peer during the association setup. It * MUST silently discard these chunks if they are not placed * after an AUTH chunk in the packet. */ if (sctp_auth_recv_cid(subtype.chunk, asoc) && !chunk->auth) continue; /* Remember where the last DATA chunk came from so we * know where to send the SACK. */ if (sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; else { SCTP_INC_STATS(net, SCTP_MIB_INCTRLCHUNKS); asoc->stats.ictrlchunks++; if (chunk->chunk_hdr->type == SCTP_CID_SACK) asoc->stats.isacks++; } if (chunk->transport) chunk->transport->last_time_heard = ktime_get(); /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state, ep, asoc, chunk, GFP_ATOMIC); /* Check to see if the association is freed in response to * the incoming chunk. If so, get out of the while loop. */ if (asoc->base.dead) break; /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; if (first_time) first_time = 0; } sctp_association_put(asoc); } /* This routine moves an association from its old sk to a new sk. */ void sctp_assoc_migrate(struct sctp_association *assoc, struct sock *newsk) { struct sctp_sock *newsp = sctp_sk(newsk); struct sock *oldsk = assoc->base.sk; /* Delete the association from the old endpoint's list of * associations. */ list_del_init(&assoc->asocs); /* Decrement the backlog value for a TCP-style socket. */ if (sctp_style(oldsk, TCP)) sk_acceptq_removed(oldsk); /* Release references to the old endpoint and the sock. */ sctp_endpoint_put(assoc->ep); sock_put(assoc->base.sk); /* Get a reference to the new endpoint. */ assoc->ep = newsp->ep; sctp_endpoint_hold(assoc->ep); /* Get a reference to the new sock. */ assoc->base.sk = newsk; sock_hold(assoc->base.sk); /* Add the association to the new endpoint's list of associations. */ sctp_endpoint_add_asoc(newsp->ep, assoc); } /* Update an association (possibly from unexpected COOKIE-ECHO processing). */ int sctp_assoc_update(struct sctp_association *asoc, struct sctp_association *new) { struct sctp_transport *trans; struct list_head *pos, *temp; /* Copy in new parameters of peer. */ asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC)) return -ENOMEM; /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { trans = list_entry(pos, struct sctp_transport, transports); if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) { sctp_assoc_rm_peer(asoc, trans); continue; } if (asoc->state >= SCTP_STATE_ESTABLISHED) sctp_transport_reset(trans); } /* If the case is A (association restart), use * initial_tsn as next_tsn. If the case is B, use * current next_tsn in case data sent to peer * has been discarded and needs retransmission. */ if (asoc->state >= SCTP_STATE_ESTABLISHED) { asoc->next_tsn = new->next_tsn; asoc->ctsn_ack_point = new->ctsn_ack_point; asoc->adv_peer_ack_point = new->adv_peer_ack_point; /* Reinitialize SSN for both local streams * and peer's streams. */ sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will * cause problems. */ sctp_ulpq_flush(&asoc->ulpq); /* reset the overall association error count so * that the restarted association doesn't get torn * down on the next retransmission timer. */ asoc->overall_error_count = 0; } else { /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; if (sctp_state(asoc, COOKIE_WAIT)) sctp_stream_update(&asoc->stream, &new->stream); /* get a new assoc id if we don't have one yet. */ if (sctp_assoc_set_id(asoc, GFP_ATOMIC)) return -ENOMEM; } /* SCTP-AUTH: Save the peer parameters from the new associations * and also move the association shared keys over */ kfree(asoc->peer.peer_random); asoc->peer.peer_random = new->peer.peer_random; new->peer.peer_random = NULL; kfree(asoc->peer.peer_chunks); asoc->peer.peer_chunks = new->peer.peer_chunks; new->peer.peer_chunks = NULL; kfree(asoc->peer.peer_hmacs); asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; return sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } /* Update the retran path for sending a retransmitted packet. * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: * * When there is outbound data to send and the primary path * becomes inactive (e.g., due to failures), or where the * SCTP user explicitly requests to send data to an * inactive destination transport address, before reporting * an error to its ULP, the SCTP endpoint should try to send * the data to an alternate active destination transport * address if one exists. * * When retransmitting data that timed out, if the endpoint * is multihomed, it should consider each source-destination * address pair in its retransmission selection policy. * When retransmitting timed-out data, the endpoint should * attempt to pick the most divergent source-destination * pair from the original source-destination pair to which * the packet was transmitted. * * Note: Rules for picking the most divergent source-destination * pair are an implementation decision and are not specified * within this document. * * Our basic strategy is to round-robin transports in priorities * according to sctp_trans_score() e.g., if no such * transport with state SCTP_ACTIVE exists, round-robin through * SCTP_UNKNOWN, etc. You get the picture. */ static u8 sctp_trans_score(const struct sctp_transport *trans) { switch (trans->state) { case SCTP_ACTIVE: return 3; /* best case */ case SCTP_UNKNOWN: return 2; case SCTP_PF: return 1; default: /* case SCTP_INACTIVE */ return 0; /* worst case */ } } static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1, struct sctp_transport *trans2) { if (trans1->error_count > trans2->error_count) { return trans2; } else if (trans1->error_count == trans2->error_count && ktime_after(trans2->last_time_heard, trans1->last_time_heard)) { return trans2; } else { return trans1; } } static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, struct sctp_transport *best) { u8 score_curr, score_best; if (best == NULL || curr == best) return curr; score_curr = sctp_trans_score(curr); score_best = sctp_trans_score(best); /* First, try a score-based selection if both transport states * differ. If we're in a tie, lets try to make a more clever * decision here based on error counts and last time heard. */ if (score_curr > score_best) return curr; else if (score_curr == score_best) return sctp_trans_elect_tie(best, curr); else return best; } void sctp_assoc_update_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans = asoc->peer.retran_path; struct sctp_transport *trans_next = NULL; /* We're done as we only have the one and only path. */ if (asoc->peer.transport_count == 1) return; /* If active_path and retran_path are the same and active, * then this is the only active path. Use it. */ if (asoc->peer.active_path == asoc->peer.retran_path && asoc->peer.active_path->state == SCTP_ACTIVE) return; /* Iterate from retran_path's successor back to retran_path. */ for (trans = list_next_entry(trans, transports); 1; trans = list_next_entry(trans, transports)) { /* Manually skip the head element. */ if (&trans->transports == &asoc->peer.transport_addr_list) continue; if (trans->state == SCTP_UNCONFIRMED) continue; trans_next = sctp_trans_elect_best(trans, trans_next); /* Active is good enough for immediate return. */ if (trans_next->state == SCTP_ACTIVE) break; /* We've reached the end, time to update path. */ if (trans == asoc->peer.retran_path) break; } asoc->peer.retran_path = trans_next; pr_debug("%s: association:%p updated new path to addr:%pISpc\n", __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } static void sctp_select_active_and_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL; struct sctp_transport *trans_pf = NULL; /* Look for the two most recently used active transports. */ list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { /* Skip uninteresting transports. */ if (trans->state == SCTP_INACTIVE || trans->state == SCTP_UNCONFIRMED) continue; /* Keep track of the best PF transport from our * list in case we don't find an active one. */ if (trans->state == SCTP_PF) { trans_pf = sctp_trans_elect_best(trans, trans_pf); continue; } /* For active transports, pick the most recent ones. */ if (trans_pri == NULL || ktime_after(trans->last_time_heard, trans_pri->last_time_heard)) { trans_sec = trans_pri; trans_pri = trans; } else if (trans_sec == NULL || ktime_after(trans->last_time_heard, trans_sec->last_time_heard)) { trans_sec = trans; } } /* RFC 2960 6.4 Multi-Homed SCTP Endpoints * * By default, an endpoint should always transmit to the primary * path, unless the SCTP user explicitly specifies the * destination transport address (and possibly source transport * address) to use. [If the primary is active but not most recent, * bump the most recently used transport.] */ if ((asoc->peer.primary_path->state == SCTP_ACTIVE || asoc->peer.primary_path->state == SCTP_UNKNOWN) && asoc->peer.primary_path != trans_pri) { trans_sec = trans_pri; trans_pri = asoc->peer.primary_path; } /* We did not find anything useful for a possible retransmission * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) trans_sec = trans_pri; /* If we failed to find a usable transport, just camp on the * active or pick a PF iff it's the better choice. */ if (trans_pri == NULL) { trans_pri = sctp_trans_elect_best(asoc->peer.active_path, trans_pf); trans_sec = trans_pri; } /* Set the active and retran transports. */ asoc->peer.active_path = trans_pri; asoc->peer.retran_path = trans_sec; } struct sctp_transport * sctp_assoc_choose_alter_transport(struct sctp_association *asoc, struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ if (last_sent_to == NULL) { return asoc->peer.active_path; } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); return asoc->peer.retran_path; } } void sctp_assoc_update_frag_point(struct sctp_association *asoc) { int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu, sctp_datachk_len(&asoc->stream)); if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN - sctp_datachk_len(&asoc->stream)); asoc->frag_point = SCTP_TRUNC4(frag); } void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu) { if (asoc->pathmtu != pmtu) { asoc->pathmtu = pmtu; sctp_assoc_update_frag_point(asoc); } pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, asoc->pathmtu, asoc->frag_point); } /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) { struct sctp_transport *t; __u32 pmtu = 0; if (!asoc) return; /* Get the lowest pmtu of all the transports. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { sctp_transport_update_pmtu(t, atomic_read(&t->mtu_info)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) pmtu = t->pathmtu; } sctp_assoc_set_pmtu(asoc, pmtu); } /* Should we send a SACK to update our peer? */ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) { struct net *net = asoc->base.net; switch (asoc->state) { case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: case SCTP_STATE_SHUTDOWN_SENT: if ((asoc->rwnd > asoc->a_rwnd) && ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, (asoc->base.sk->sk_rcvbuf >> net->sctp.rwnd_upd_shift), asoc->pathmtu))) return true; break; default: break; } return false; } /* Increase asoc's rwnd by len and send any window update SACK if needed. */ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { struct sctp_chunk *sack; struct timer_list *timer; if (asoc->rwnd_over) { if (asoc->rwnd_over >= len) { asoc->rwnd_over -= len; } else { asoc->rwnd += (len - asoc->rwnd_over); asoc->rwnd_over = 0; } } else { asoc->rwnd += len; } /* If we had window pressure, start recovering it * once our rwnd had reached the accumulated pressure * threshold. The idea is to recover slowly, but up * to the initial advertised window. */ if (asoc->rwnd_press) { int change = min(asoc->pathmtu, asoc->rwnd_press); asoc->rwnd += change; asoc->rwnd_press -= change; } pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->a_rwnd); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ if (sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " "a_rwnd:%u\n", __func__, asoc, asoc->rwnd, asoc->a_rwnd); sack = sctp_make_sack(asoc); if (!sack) return; asoc->peer.sack_needed = 0; sctp_outq_tail(&asoc->outqueue, sack, GFP_ATOMIC); /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; if (timer_delete(timer)) sctp_association_put(asoc); } } /* Decrease asoc's rwnd by len. */ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) { int rx_count; int over = 0; if (unlikely(!asoc->rwnd || asoc->rwnd_over)) pr_debug("%s: association:%p has asoc->rwnd:%u, " "asoc->rwnd_over:%u!\n", __func__, asoc, asoc->rwnd, asoc->rwnd_over); if (asoc->ep->rcvbuf_policy) rx_count = atomic_read(&asoc->rmem_alloc); else rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) over = 1; if (asoc->rwnd >= len) { asoc->rwnd -= len; if (over) { asoc->rwnd_press += asoc->rwnd; asoc->rwnd = 0; } } else { asoc->rwnd_over += len - asoc->rwnd; asoc->rwnd = 0; } pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->rwnd_press); } /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. */ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; if (!inet_v6_ipv6only(sk)) flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) flags |= SCTP_ADDR6_PEERSUPP; return sctp_bind_addr_copy(asoc->base.net, &asoc->base.bind_addr, &asoc->ep->base.bind_addr, scope, gfp, flags); } /* Build the association's bind address list from the cookie. */ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, struct sctp_cookie *cookie, gfp_t gfp) { struct sctp_init_chunk *peer_init = (struct sctp_init_chunk *)(cookie + 1); int var_size2 = ntohs(peer_init->chunk_hdr.length); int var_size3 = cookie->raw_addr_list_len; __u8 *raw = (__u8 *)peer_init + var_size2; return sctp_raw_to_bind_addrs(&asoc->base.bind_addr, raw, var_size3, asoc->ep->base.bind_addr.port, gfp); } /* Lookup laddr in the bind address list of an association. */ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, const union sctp_addr *laddr) { int found = 0; if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) && sctp_bind_addr_match(&asoc->base.bind_addr, laddr, sctp_sk(asoc->base.sk))) found = 1; return found; } /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { bool preload = gfpflags_allow_blocking(gfp); int ret; /* If the id is already assigned, keep it. */ if (asoc->assoc_id) return 0; if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. */ ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); if (ret < 0) return ret; asoc->assoc_id = (sctp_assoc_t)ret; return 0; } /* Free the ASCONF queue */ static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc) { struct sctp_chunk *asconf; struct sctp_chunk *tmp; list_for_each_entry_safe(asconf, tmp, &asoc->addip_chunk_list, list) { list_del_init(&asconf->list); sctp_chunk_free(asconf); } } /* Free asconf_ack cache */ static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Clean up the ASCONF_ACK queue */ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; /* We can remove all the entries from the queue up to * the "Peer-Sequence-Number". */ list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { if (ack->subh.addip_hdr->serial == htonl(asoc->peer.addip_serial)) break; list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Find the ASCONF_ACK whose serial number matches ASCONF */ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( const struct sctp_association *asoc, __be32 serial) { struct sctp_chunk *ack; /* Walk through the list of cached ASCONF-ACKs and find the * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { if (sctp_chunk_pending(ack)) continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; } } return NULL; } void sctp_asconf_queue_teardown(struct sctp_association *asoc) { /* Free any cached ASCONF_ACK chunk. */ sctp_assoc_free_asconf_acks(asoc); /* Free the ASCONF queue. */ sctp_assoc_free_asconf_queue(asoc); /* Free any cached ASCONF chunk. */ if (asoc->addip_last_asconf) sctp_chunk_free(asoc->addip_last_asconf); } |
| 184 161 23 185 121 121 121 121 81 23 3 20 49 48 48 1 48 49 49 11 11 92 92 10 84 92 92 7 76 2 1 2 14 2 2 4 4 4 4 4 4 3 4 1 51 3 1 79 79 79 2 16 1 1 4 4 4 2 4 2 2 2 2 2 2 1 1 1 1 20 20 19 20 7 19 16 1 1 1 19 4 19 20 1 14 16 10 2 10 10 10 10 9 8 8 1 3 3 3 1 1 1 3 3 1 3 3 3 22 21 21 21 4 4 4 3 19 7 6 7 6 5 3 15 15 12 15 15 4 15 15 19 17 17 16 16 15 15 15 4 4 2 21 9 9 9 74 4 3 3 1 14 14 13 10 14 14 14 14 14 202 159 145 145 204 70 11 4 204 13 11 10 5 10 10 10 10 10 10 9 9 9 9 9 1 9 8 7 1 6 4 5 3 5 1 5 5 5 6 7 13 160 160 159 3 160 2 1 29 160 159 160 89 84 82 2 1 159 160 157 107 29 29 12 29 107 2 107 107 107 107 32 107 107 107 71 71 74 1 74 158 21 8 6 21 21 22 1 21 21 211 3 204 203 210 205 116 201 202 203 15 15 205 200 204 165 204 190 22 203 1 1 200 186 205 9 205 202 15 186 67 33 7 202 199 200 3 199 199 3 2 199 199 196 20 8 3 183 4 179 178 19 35 209 209 211 212 81 80 80 80 76 80 1 1 80 9 80 80 80 80 3 9 80 80 11 4 12 11 11 1 10 7 9 6 8 7 7 7 6 8 8 1 8 8 2 6 6 6 8 1 1 12 2 1 2 13 12 13 42 41 40 39 39 39 39 38 39 39 39 42 33 31 32 1 30 30 29 16 29 27 26 26 2 27 27 13 1 12 12 13 27 1 1 1 1 1 1 1 1 27 30 32 3 1 1 1 3 4 2 2 2 1 1 2 2 4 11 2 1 1 3 1 1 7 2 2 1 1 1 7 6 6 6 6 6 6 2 3 10 9 9 8 9 9 92 91 11 4 11 11 11 10 7 10 16 17 15 15 15 2 1 1 3 2 2 1 1 1 2 1 1 1 1 1 4 2 2 2 2 3 2 2 3 2 2 7 6 5 5 1 4 4 4 2 1 1 24 22 22 3 2 2 1 1 1 3 2 2 2 2 10 90 3 2 2 20 19 18 17 1 1 1 1 1 1 1 1 2 1 1 2 1 2 1 1 13 20 990 994 992 159 41 2 57 7 7 7 7 1 1 1 7 34 994 1 992 47 9 4 4 5 1 1 5 33 1 21 21 21 2 2 2 14 15 15 14 15 9 9 9 9 8 7 7 6 5 4 3 2 2 6 5 3 5 5 5 5 5 5 5 3 5 13 3 2 2 2 2 2 3 3 3 3 3 3 3 3 1 3 515 514 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) proto = __vlan_get_protocol_offset(skb, proto, skb_mac_offset(skb), NULL); return proto; } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); hrtimer_cancel(&pkc->retire_blk_timer); } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->interval_ktime = ms_to_ktime(req_u->req3.tp_retire_blk_tov); else p1->interval_ktime = ms_to_ktime(prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size)); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); hrtimer_setup(&p1->retire_blk_timer, prb_retire_rx_blk_timer_expired, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); hrtimer_start(&p1->retire_blk_timer, p1->interval_ktime, HRTIMER_MODE_REL_SOFT); prb_open_block(p1, pbd); } /* * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. */ static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *t) { struct packet_sock *po = timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (!frozen) { if (BLOCK_NUM_PKTS(pbd)) { /* Not an empty block. Need retire the block. */ prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); prb_dispatch_next_block(pkc, po); } } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (!prb_curr_blk_in_use(pbd)) { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); } } hrtimer_forward_now(&pkc->retire_blk_timer, pkc->interval_ktime); spin_unlock(&po->sk.sk_receive_queue.lock); return HRTIMER_RESTART; } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * prb_open_block is called by tpacket_rcv or timer callback. * * Reasons why NOT update hrtimer in prb_open_block: * 1) It will increase complexity to distinguish the two caller scenario. * 2) hrtimer_cancel and hrtimer_start need to be called if you want to update * TMO of an already enqueued hrtimer, leading to complex shutdown logic. * * One side effect of NOT update hrtimer when called by tpacket_rcv is that * a newly opened block triggered by tpacket_rcv may be retired earlier than * expected. On the other hand, if timeout is updated in prb_open_block, the * frequent reception of network packets that leads to prb_open_block being * called may cause hrtimer to be removed and enqueued repeatedly. */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (po->num && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __dev_remove_pack(&po->prot_hook); __fanout_link(sk, po); } err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, &sockc); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); sk_drops_inc(sk); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { /* Note: packet_read_pending() might be slow if we * have to call it as it's per_cpu variable, but in * fast-path we don't have to call it, only when ph * is NULL, we need to check the pending_refcnt. */ if (need_wait && packet_read_pending(&po->tx_ring)) { timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } /* check for additional frames */ continue; } else break; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (1); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, &sockc); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; po = pkt_sk(sk); err = packet_alloc_pending(po); if (err) goto out_sk_free; sock_init_data(sock, sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out_sk_free: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp, struct list_head *list) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { list_add(&ml->remove_list, list); *mlp = ml->next; } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; INIT_LIST_HEAD(&i->remove_list); i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct packet_mclist *ml, *tmp; LIST_HEAD(mclist); struct sock *sk; rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist, &mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); /* packet_dev_mc might grab instance locks so can't run under rcu */ list_for_each_entry_safe(ml, tmp, &mclist, remove_list) { packet_dev_mc(dev, ml, -1); kfree(ml); } return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; WRITE_ONCE(po->num, 0); if (was_running) __unregister_prot_hook(sk, false); spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); WRITE_ONCE(po->num, num); if (was_running) register_prot_hook(sk); spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sk_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 87 99 99 99 99 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner * * This file contains the IRQ-resend code * * If the interrupt is waiting to be processed, we try to re-run it. * We can't directly run it from here since the caller might be in an * interrupt-protected region. Not all irq controller chips can * retrigger interrupts at the hardware level, so in those cases * we allow the resending of IRQs via a tasklet. */ #include <linux/irq.h> #include <linux/module.h> #include <linux/random.h> #include <linux/interrupt.h> #include "internals.h" #ifdef CONFIG_HARDIRQS_SW_RESEND /* hlist_head to handle software resend of interrupts: */ static HLIST_HEAD(irq_resend_list); static DEFINE_RAW_SPINLOCK(irq_resend_lock); /* * Run software resends of IRQ's */ static void resend_irqs(struct tasklet_struct *unused) { guard(raw_spinlock_irq)(&irq_resend_lock); while (!hlist_empty(&irq_resend_list)) { struct irq_desc *desc; desc = hlist_entry(irq_resend_list.first, struct irq_desc, resend_node); hlist_del_init(&desc->resend_node); raw_spin_unlock(&irq_resend_lock); desc->handle_irq(desc); raw_spin_lock(&irq_resend_lock); } } /* Tasklet to handle resend: */ static DECLARE_TASKLET(resend_tasklet, resend_irqs); static int irq_sw_resend(struct irq_desc *desc) { /* * Validate whether this interrupt can be safely injected from * non interrupt context */ if (irqd_is_handle_enforce_irqctx(&desc->irq_data)) return -EINVAL; /* * If the interrupt is running in the thread context of the parent * irq we need to be careful, because we cannot trigger it * directly. */ if (irq_settings_is_nested_thread(desc)) { /* * If the parent_irq is valid, we retrigger the parent, * otherwise we do nothing. */ if (!desc->parent_irq) return -EINVAL; desc = irq_to_desc(desc->parent_irq); if (!desc) return -EINVAL; } /* Add to resend_list and activate the softirq: */ scoped_guard(raw_spinlock, &irq_resend_lock) { if (hlist_unhashed(&desc->resend_node)) hlist_add_head(&desc->resend_node, &irq_resend_list); } tasklet_schedule(&resend_tasklet); return 0; } void clear_irq_resend(struct irq_desc *desc) { guard(raw_spinlock)(&irq_resend_lock); hlist_del_init(&desc->resend_node); } void irq_resend_init(struct irq_desc *desc) { INIT_HLIST_NODE(&desc->resend_node); } #else void clear_irq_resend(struct irq_desc *desc) {} void irq_resend_init(struct irq_desc *desc) {} static int irq_sw_resend(struct irq_desc *desc) { return -EINVAL; } #endif static int try_retrigger(struct irq_desc *desc) { if (desc->irq_data.chip->irq_retrigger) return desc->irq_data.chip->irq_retrigger(&desc->irq_data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY return irq_chip_retrigger_hierarchy(&desc->irq_data); #else return 0; #endif } /* * IRQ resend * * Is called with interrupts disabled and desc->lock held. */ int check_irq_resend(struct irq_desc *desc, bool inject) { int err = 0; /* * We do not resend level type interrupts. Level type interrupts * are resent by hardware when they are still active. Clear the * pending bit so suspend/resume does not get confused. */ if (irq_settings_is_level(desc)) { desc->istate &= ~IRQS_PENDING; return -EINVAL; } if (desc->istate & IRQS_REPLAY) return -EBUSY; if (!(desc->istate & IRQS_PENDING) && !inject) return 0; desc->istate &= ~IRQS_PENDING; if (!try_retrigger(desc)) err = irq_sw_resend(desc); /* If the retrigger was successful, mark it with the REPLAY bit */ if (!err) desc->istate |= IRQS_REPLAY; return err; } #ifdef CONFIG_GENERIC_IRQ_INJECTION /** * irq_inject_interrupt - Inject an interrupt for testing/error injection * @irq: The interrupt number * * This function must only be used for debug and testing purposes! * * Especially on x86 this can cause a premature completion of an interrupt * affinity change causing the interrupt line to become stale. Very * unlikely, but possible. * * The injection can fail for various reasons: * - Interrupt is not activated * - Interrupt is NMI type or currently replaying * - Interrupt is level type * - Interrupt does not support hardware retrigger and software resend is * either not enabled or not possible for the interrupt. */ int irq_inject_interrupt(unsigned int irq) { int err = -EINVAL; /* Try the state injection hardware interface first */ if (!irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, true)) return 0; /* That failed, try via the resend mechanism */ scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; /* * Only try to inject when the interrupt is: * - not NMI type * - activated */ if (!irq_is_nmi(desc) && irqd_is_activated(&desc->irq_data)) err = check_irq_resend(desc, true); } return err; } EXPORT_SYMBOL_GPL(irq_inject_interrupt); #endif |
| 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 | // SPDX-License-Identifier: GPL-2.0 /* * f2fs debugging statistics * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2012 Linux Foundation * Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org> */ #include <linux/fs.h> #include <linux/backing-dev.h> #include <linux/f2fs_fs.h> #include <linux/blkdev.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "gc.h" static LIST_HEAD(f2fs_stat_list); static DEFINE_SPINLOCK(f2fs_stat_lock); #ifdef CONFIG_DEBUG_FS static struct dentry *f2fs_debugfs_root; #endif /* * This function calculates BDF of every segments */ void f2fs_update_sit_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); unsigned long long blks_per_sec, hblks_per_sec, total_vblocks; unsigned long long bimodal, dist; unsigned int segno, vblocks; int ndirty = 0; bimodal = 0; total_vblocks = 0; blks_per_sec = CAP_BLKS_PER_SEC(sbi); hblks_per_sec = blks_per_sec / 2; for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) { vblocks = get_valid_blocks(sbi, segno, true); dist = abs(vblocks - hblks_per_sec); bimodal += dist * dist; if (vblocks > 0 && vblocks < blks_per_sec) { total_vblocks += vblocks; ndirty++; } } dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100); si->bimodal = div64_u64(bimodal, dist); if (si->dirty_count) si->avg_vblocks = div_u64(total_vblocks, ndirty); else si->avg_vblocks = 0; } #ifdef CONFIG_DEBUG_FS static void update_multidevice_stats(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); struct f2fs_dev_stats *dev_stats = si->dev_stats; int i, j; if (!f2fs_is_multi_device(sbi)) return; memset(dev_stats, 0, sizeof(struct f2fs_dev_stats) * sbi->s_ndevs); for (i = 0; i < sbi->s_ndevs; i++) { unsigned int start_segno, end_segno; block_t start_blk, end_blk; if (i == 0) { start_blk = MAIN_BLKADDR(sbi); end_blk = FDEV(i).end_blk + 1 - SEG0_BLKADDR(sbi); } else { start_blk = FDEV(i).start_blk; end_blk = FDEV(i).end_blk + 1; } start_segno = GET_SEGNO(sbi, start_blk); end_segno = GET_SEGNO(sbi, end_blk); for (j = start_segno; j < end_segno; j++) { unsigned int seg_blks, sec_blks; seg_blks = get_seg_entry(sbi, j)->valid_blocks; /* update segment stats */ if (is_curseg(sbi, j)) dev_stats[i].devstats[0][DEVSTAT_INUSE]++; else if (seg_blks == BLKS_PER_SEG(sbi)) dev_stats[i].devstats[0][DEVSTAT_FULL]++; else if (seg_blks != 0) dev_stats[i].devstats[0][DEVSTAT_DIRTY]++; else if (!test_bit(j, FREE_I(sbi)->free_segmap)) dev_stats[i].devstats[0][DEVSTAT_FREE]++; else dev_stats[i].devstats[0][DEVSTAT_PREFREE]++; if (!__is_large_section(sbi) || (j % SEGS_PER_SEC(sbi)) != 0) continue; sec_blks = get_sec_entry(sbi, j)->valid_blocks; /* update section stats */ if (is_cursec(sbi, GET_SEC_FROM_SEG(sbi, j))) dev_stats[i].devstats[1][DEVSTAT_INUSE]++; else if (sec_blks == BLKS_PER_SEC(sbi)) dev_stats[i].devstats[1][DEVSTAT_FULL]++; else if (sec_blks != 0) dev_stats[i].devstats[1][DEVSTAT_DIRTY]++; else if (!test_bit(GET_SEC_FROM_SEG(sbi, j), FREE_I(sbi)->free_secmap)) dev_stats[i].devstats[1][DEVSTAT_FREE]++; else dev_stats[i].devstats[1][DEVSTAT_PREFREE]++; } } } static void update_general_status(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); int i; /* these will be changed if online resize is done */ si->main_area_segs = le32_to_cpu(raw_super->segment_count_main); si->main_area_sections = le32_to_cpu(raw_super->section_count); si->main_area_zones = si->main_area_sections / le32_to_cpu(raw_super->secs_per_zone); /* general extent cache stats */ for (i = 0; i < NR_EXTENT_CACHES; i++) { struct extent_tree_info *eti = &sbi->extent_tree[i]; si->hit_cached[i] = atomic64_read(&sbi->read_hit_cached[i]); si->hit_rbtree[i] = atomic64_read(&sbi->read_hit_rbtree[i]); si->total_ext[i] = atomic64_read(&sbi->total_hit_ext[i]); si->hit_total[i] = si->hit_cached[i] + si->hit_rbtree[i]; si->ext_tree[i] = atomic_read(&eti->total_ext_tree); si->zombie_tree[i] = atomic_read(&eti->total_zombie_tree); si->ext_node[i] = atomic_read(&eti->total_ext_node); } /* read extent_cache only */ si->hit_largest = atomic64_read(&sbi->read_hit_largest); si->hit_total[EX_READ] += si->hit_largest; /* block age extent_cache only */ si->allocated_data_blocks = atomic64_read(&sbi->allocated_data_blocks); /* validation check of the segment numbers */ si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA); si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA); si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA); si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE]; si->ndirty_files = sbi->ndirty_inode[FILE_INODE]; si->ndonate_files = sbi->donate_files; si->nquota_files = sbi->nquota_files; si->ndirty_all = sbi->ndirty_inode[DIRTY_META]; si->aw_cnt = atomic_read(&sbi->atomic_files); si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt); si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ); si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE); si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA); si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA); si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA); si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE); si->nr_rd_meta = get_pages(sbi, F2FS_RD_META); if (SM_I(sbi)->fcc_info) { si->nr_flushed = atomic_read(&SM_I(sbi)->fcc_info->issued_flush); si->nr_flushing = atomic_read(&SM_I(sbi)->fcc_info->queued_flush); si->flush_list_empty = llist_empty(&SM_I(sbi)->fcc_info->issue_list); } if (SM_I(sbi)->dcc_info) { si->nr_discarded = atomic_read(&SM_I(sbi)->dcc_info->issued_discard); si->nr_discarding = atomic_read(&SM_I(sbi)->dcc_info->queued_discard); si->nr_discard_cmd = atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt); si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks; } si->nr_issued_ckpt = atomic_read(&sbi->cprc_info.issued_ckpt); si->nr_total_ckpt = atomic_read(&sbi->cprc_info.total_ckpt); si->nr_queued_ckpt = atomic_read(&sbi->cprc_info.queued_ckpt); spin_lock(&sbi->cprc_info.stat_lock); si->cur_ckpt_time = sbi->cprc_info.cur_time; si->peak_ckpt_time = sbi->cprc_info.peak_time; spin_unlock(&sbi->cprc_info.stat_lock); si->total_count = BLKS_TO_SEGS(sbi, (int)sbi->user_block_count); si->rsvd_segs = reserved_segments(sbi); si->overp_segs = overprovision_segments(sbi); si->valid_count = valid_user_blocks(sbi); si->discard_blks = discard_blocks(sbi); si->valid_node_count = valid_node_count(sbi); si->valid_inode_count = valid_inode_count(sbi); si->inline_xattr = atomic_read(&sbi->inline_xattr); si->inline_inode = atomic_read(&sbi->inline_inode); si->inline_dir = atomic_read(&sbi->inline_dir); si->compr_inode = atomic_read(&sbi->compr_inode); si->swapfile_inode = atomic_read(&sbi->swapfile_inode); si->compr_blocks = atomic64_read(&sbi->compr_blocks); si->append = sbi->im[APPEND_INO].ino_num; si->update = sbi->im[UPDATE_INO].ino_num; si->orphans = sbi->im[ORPHAN_INO].ino_num; si->utilization = utilization(sbi); si->free_segs = free_segments(sbi); si->free_secs = free_sections(sbi); si->prefree_count = prefree_segments(sbi); si->dirty_count = dirty_segments(sbi); if (sbi->node_inode) si->node_pages = NODE_MAPPING(sbi)->nrpages; if (sbi->meta_inode) si->meta_pages = META_MAPPING(sbi)->nrpages; #ifdef CONFIG_F2FS_FS_COMPRESSION if (sbi->compress_inode) { si->compress_pages = COMPRESS_MAPPING(sbi)->nrpages; si->compress_page_hit = atomic_read(&sbi->compress_page_hit); } #endif si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT]; si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT]; si->sits = MAIN_SEGS(sbi); si->dirty_sits = SIT_I(sbi)->dirty_sentries; si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID]; si->avail_nids = NM_I(sbi)->available_nids; si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID]; si->io_skip_bggc = sbi->io_skip_bggc; si->other_skip_bggc = sbi->other_skip_bggc; si->util_free = (int)(BLKS_TO_SEGS(sbi, free_user_blocks(sbi))) * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) / 2; si->util_valid = (int)(BLKS_TO_SEGS(sbi, written_block_count(sbi))) * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) / 2; si->util_invalid = 50 - si->util_free - si->util_valid; for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { struct curseg_info *curseg = CURSEG_I(sbi, i); si->curseg[i] = curseg->segno; si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno); si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]); } for (i = META_CP; i < META_MAX; i++) si->meta_count[i] = atomic_read(&sbi->meta_count[i]); for (i = 0; i < NO_CHECK_TYPE; i++) { si->dirty_seg[i] = 0; si->full_seg[i] = 0; si->valid_blks[i] = 0; } for (i = 0; i < MAIN_SEGS(sbi); i++) { int blks = get_seg_entry(sbi, i)->valid_blocks; int type = get_seg_entry(sbi, i)->type; if (!blks) continue; if (blks == BLKS_PER_SEG(sbi)) si->full_seg[type]++; else si->dirty_seg[type]++; si->valid_blks[type] += blks; } update_multidevice_stats(sbi); for (i = 0; i < MAX_CALL_TYPE; i++) si->cp_call_count[i] = atomic_read(&sbi->cp_call_count[i]); for (i = 0; i < 2; i++) { si->segment_count[i] = sbi->segment_count[i]; si->block_count[i] = sbi->block_count[i]; } si->inplace_count = atomic_read(&sbi->inplace_count); } /* * This function calculates memory footprint. */ static void update_mem_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); int i; if (si->base_mem) goto get_cache; /* build stat */ si->base_mem = sizeof(struct f2fs_stat_info); /* build superblock */ si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize; si->base_mem += 2 * sizeof(struct f2fs_inode_info); si->base_mem += sizeof(*sbi->ckpt); /* build sm */ si->base_mem += sizeof(struct f2fs_sm_info); /* build sit */ si->base_mem += sizeof(struct sit_info); si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (__is_large_section(sbi)) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); si->base_mem += __bitmap_size(sbi, SIT_BITMAP); /* build free segmap */ si->base_mem += sizeof(struct free_segmap_info); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi)); /* build curseg */ si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE; si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE; /* build dirty segmap */ si->base_mem += sizeof(struct dirty_seglist_info); si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi)); /* build nm */ si->base_mem += sizeof(struct f2fs_nm_info); si->base_mem += __bitmap_size(sbi, NAT_BITMAP); si->base_mem += F2FS_BLK_TO_BYTES(NM_I(sbi)->nat_bits_blocks); si->base_mem += NM_I(sbi)->nat_blocks * f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK); si->base_mem += NM_I(sbi)->nat_blocks / 8; si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short); get_cache: si->cache_mem = 0; /* build gc */ if (sbi->gc_thread) si->cache_mem += sizeof(struct f2fs_gc_kthread); /* build merge flush thread */ if (SM_I(sbi)->fcc_info) si->cache_mem += sizeof(struct flush_cmd_control); if (SM_I(sbi)->dcc_info) { si->cache_mem += sizeof(struct discard_cmd_control); si->cache_mem += sizeof(struct discard_cmd) * atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt); } /* free nids */ si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] + NM_I(sbi)->nid_cnt[PREALLOC_NID]) * sizeof(struct free_nid); si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] * sizeof(struct nat_entry); si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] * sizeof(struct nat_entry_set); for (i = 0; i < MAX_INO_ENTRY; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); for (i = 0; i < NR_EXTENT_CACHES; i++) { struct extent_tree_info *eti = &sbi->extent_tree[i]; si->ext_mem[i] = atomic_read(&eti->total_ext_tree) * sizeof(struct extent_tree); si->ext_mem[i] += atomic_read(&eti->total_ext_node) * sizeof(struct extent_node); si->cache_mem += si->ext_mem[i]; } si->page_mem = 0; if (sbi->node_inode) { unsigned long npages = NODE_MAPPING(sbi)->nrpages; si->page_mem += (unsigned long long)npages << PAGE_SHIFT; } if (sbi->meta_inode) { unsigned long npages = META_MAPPING(sbi)->nrpages; si->page_mem += (unsigned long long)npages << PAGE_SHIFT; } #ifdef CONFIG_F2FS_FS_COMPRESSION if (sbi->compress_inode) { unsigned long npages = COMPRESS_MAPPING(sbi)->nrpages; si->page_mem += (unsigned long long)npages << PAGE_SHIFT; } #endif } static const char *s_flag[MAX_SBI_FLAG] = { [SBI_IS_DIRTY] = "fs_dirty", [SBI_IS_CLOSE] = "closing", [SBI_NEED_FSCK] = "need_fsck", [SBI_POR_DOING] = "recovering", [SBI_NEED_SB_WRITE] = "sb_dirty", [SBI_NEED_CP] = "need_cp", [SBI_IS_SHUTDOWN] = "shutdown", [SBI_IS_RECOVERED] = "recovered", [SBI_CP_DISABLED] = "cp_disabled", [SBI_CP_DISABLED_QUICK] = "cp_disabled_quick", [SBI_QUOTA_NEED_FLUSH] = "quota_need_flush", [SBI_QUOTA_SKIP_FLUSH] = "quota_skip_flush", [SBI_QUOTA_NEED_REPAIR] = "quota_need_repair", [SBI_IS_RESIZEFS] = "resizefs", [SBI_IS_FREEZING] = "freezefs", [SBI_IS_WRITABLE] = "writable", }; static const char *ipu_mode_names[F2FS_IPU_MAX] = { [F2FS_IPU_FORCE] = "FORCE", [F2FS_IPU_SSR] = "SSR", [F2FS_IPU_UTIL] = "UTIL", [F2FS_IPU_SSR_UTIL] = "SSR_UTIL", [F2FS_IPU_FSYNC] = "FSYNC", [F2FS_IPU_ASYNC] = "ASYNC", [F2FS_IPU_NOCACHE] = "NOCACHE", [F2FS_IPU_HONOR_OPU_WRITE] = "HONOR_OPU_WRITE", }; static int stat_show(struct seq_file *s, void *v) { struct f2fs_stat_info *si; int i = 0, j = 0; spin_lock(&f2fs_stat_lock); list_for_each_entry(si, &f2fs_stat_list, stat_list) { struct f2fs_sb_info *sbi = si->sbi; update_general_status(sbi); seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n", sbi->sb->s_bdev, i++, f2fs_readonly(sbi->sb) ? "RO" : "RW", is_set_ckpt_flags(sbi, CP_DISABLED_FLAG) ? "Disabled" : (f2fs_cp_error(sbi) ? "Error" : "Good")); if (sbi->s_flag) { seq_puts(s, "[SBI:"); for_each_set_bit(j, &sbi->s_flag, MAX_SBI_FLAG) seq_printf(s, " %s", s_flag[j]); seq_puts(s, "]\n"); } seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", si->ssa_area_segs, si->main_area_segs); seq_printf(s, "(OverProv:%d Resv:%d)]\n\n", si->overp_segs, si->rsvd_segs); seq_printf(s, "Current Time Sec: %llu / Mounted Time Sec: %llu\n\n", ktime_get_boottime_seconds(), SIT_I(sbi)->mounted_time); seq_puts(s, "Policy:\n"); seq_puts(s, " - IPU: ["); if (IS_F2FS_IPU_DISABLE(sbi)) { seq_puts(s, " DISABLE"); } else { unsigned long policy = SM_I(sbi)->ipu_policy; for_each_set_bit(j, &policy, F2FS_IPU_MAX) seq_printf(s, " %s", ipu_mode_names[j]); } seq_puts(s, " ]\n\n"); if (test_opt(sbi, DISCARD)) seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n", si->utilization, si->valid_count, si->discard_blks); else seq_printf(s, "Utilization: %u%% (%u valid blocks)\n", si->utilization, si->valid_count); seq_printf(s, " - Node: %u (Inode: %u, ", si->valid_node_count, si->valid_inode_count); seq_printf(s, "Other: %u)\n - Data: %u\n", si->valid_node_count - si->valid_inode_count, si->valid_count - si->valid_node_count); seq_printf(s, " - Inline_xattr Inode: %u\n", si->inline_xattr); seq_printf(s, " - Inline_data Inode: %u\n", si->inline_inode); seq_printf(s, " - Inline_dentry Inode: %u\n", si->inline_dir); seq_printf(s, " - Compressed Inode: %u, Blocks: %llu\n", si->compr_inode, si->compr_blocks); seq_printf(s, " - Swapfile Inode: %u\n", si->swapfile_inode); seq_printf(s, " - Donate Inode: %u\n", si->ndonate_files); seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n", si->orphans, si->append, si->update); seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", si->main_area_segs, si->main_area_sections, si->main_area_zones); seq_printf(s, " TYPE %8s %8s %8s %10s %10s %10s\n", "segno", "secno", "zoneno", "dirty_seg", "full_seg", "valid_blk"); seq_printf(s, " - COLD data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_COLD_DATA], si->cursec[CURSEG_COLD_DATA], si->curzone[CURSEG_COLD_DATA], si->dirty_seg[CURSEG_COLD_DATA], si->full_seg[CURSEG_COLD_DATA], si->valid_blks[CURSEG_COLD_DATA]); seq_printf(s, " - WARM data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_WARM_DATA], si->cursec[CURSEG_WARM_DATA], si->curzone[CURSEG_WARM_DATA], si->dirty_seg[CURSEG_WARM_DATA], si->full_seg[CURSEG_WARM_DATA], si->valid_blks[CURSEG_WARM_DATA]); seq_printf(s, " - HOT data: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_HOT_DATA], si->cursec[CURSEG_HOT_DATA], si->curzone[CURSEG_HOT_DATA], si->dirty_seg[CURSEG_HOT_DATA], si->full_seg[CURSEG_HOT_DATA], si->valid_blks[CURSEG_HOT_DATA]); seq_printf(s, " - Dir dnode: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_HOT_NODE], si->cursec[CURSEG_HOT_NODE], si->curzone[CURSEG_HOT_NODE], si->dirty_seg[CURSEG_HOT_NODE], si->full_seg[CURSEG_HOT_NODE], si->valid_blks[CURSEG_HOT_NODE]); seq_printf(s, " - File dnode: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_WARM_NODE], si->cursec[CURSEG_WARM_NODE], si->curzone[CURSEG_WARM_NODE], si->dirty_seg[CURSEG_WARM_NODE], si->full_seg[CURSEG_WARM_NODE], si->valid_blks[CURSEG_WARM_NODE]); seq_printf(s, " - Indir nodes: %8d %8d %8d %10u %10u %10u\n", si->curseg[CURSEG_COLD_NODE], si->cursec[CURSEG_COLD_NODE], si->curzone[CURSEG_COLD_NODE], si->dirty_seg[CURSEG_COLD_NODE], si->full_seg[CURSEG_COLD_NODE], si->valid_blks[CURSEG_COLD_NODE]); seq_printf(s, " - Pinned file: %8d %8d %8d\n", si->curseg[CURSEG_COLD_DATA_PINNED], si->cursec[CURSEG_COLD_DATA_PINNED], si->curzone[CURSEG_COLD_DATA_PINNED]); seq_printf(s, " - ATGC data: %8d %8d %8d\n", si->curseg[CURSEG_ALL_DATA_ATGC], si->cursec[CURSEG_ALL_DATA_ATGC], si->curzone[CURSEG_ALL_DATA_ATGC]); seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n", si->main_area_segs - si->dirty_count - si->prefree_count - si->free_segs, si->dirty_count); seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n", si->prefree_count, si->free_segs, si->free_secs); if (f2fs_is_multi_device(sbi)) { seq_puts(s, "Multidevice stats:\n"); seq_printf(s, " [seg: %8s %8s %8s %8s %8s]", "inuse", "dirty", "full", "free", "prefree"); if (__is_large_section(sbi)) seq_printf(s, " [sec: %8s %8s %8s %8s %8s]\n", "inuse", "dirty", "full", "free", "prefree"); else seq_puts(s, "\n"); for (i = 0; i < sbi->s_ndevs; i++) { seq_printf(s, " #%-2d %8u %8u %8u %8u %8u", i, si->dev_stats[i].devstats[0][DEVSTAT_INUSE], si->dev_stats[i].devstats[0][DEVSTAT_DIRTY], si->dev_stats[i].devstats[0][DEVSTAT_FULL], si->dev_stats[i].devstats[0][DEVSTAT_FREE], si->dev_stats[i].devstats[0][DEVSTAT_PREFREE]); if (!__is_large_section(sbi)) { seq_puts(s, "\n"); continue; } seq_printf(s, " %8u %8u %8u %8u %8u\n", si->dev_stats[i].devstats[1][DEVSTAT_INUSE], si->dev_stats[i].devstats[1][DEVSTAT_DIRTY], si->dev_stats[i].devstats[1][DEVSTAT_FULL], si->dev_stats[i].devstats[1][DEVSTAT_FREE], si->dev_stats[i].devstats[1][DEVSTAT_PREFREE]); } seq_puts(s, "\n"); } seq_printf(s, "CP calls: %d (BG: %d)\n", si->cp_call_count[TOTAL_CALL], si->cp_call_count[BACKGROUND]); seq_printf(s, "CP count: %d\n", si->cp_count); seq_printf(s, " - cp blocks : %u\n", si->meta_count[META_CP]); seq_printf(s, " - sit blocks : %u\n", si->meta_count[META_SIT]); seq_printf(s, " - nat blocks : %u\n", si->meta_count[META_NAT]); seq_printf(s, " - ssa blocks : %u\n", si->meta_count[META_SSA]); seq_puts(s, "CP merge:\n"); seq_printf(s, " - Queued : %4d\n", si->nr_queued_ckpt); seq_printf(s, " - Issued : %4d\n", si->nr_issued_ckpt); seq_printf(s, " - Total : %4d\n", si->nr_total_ckpt); seq_printf(s, " - Cur time : %4d(ms)\n", si->cur_ckpt_time); seq_printf(s, " - Peak time : %4d(ms)\n", si->peak_ckpt_time); seq_printf(s, "GC calls: %d (gc_thread: %d)\n", si->gc_call_count[BACKGROUND] + si->gc_call_count[FOREGROUND], si->gc_call_count[BACKGROUND]); if (__is_large_section(sbi)) { seq_printf(s, " - data sections : %d (BG: %d)\n", si->gc_secs[DATA][BG_GC] + si->gc_secs[DATA][FG_GC], si->gc_secs[DATA][BG_GC]); seq_printf(s, " - node sections : %d (BG: %d)\n", si->gc_secs[NODE][BG_GC] + si->gc_secs[NODE][FG_GC], si->gc_secs[NODE][BG_GC]); } seq_printf(s, " - data segments : %d (BG: %d)\n", si->gc_segs[DATA][BG_GC] + si->gc_segs[DATA][FG_GC], si->gc_segs[DATA][BG_GC]); seq_printf(s, " - node segments : %d (BG: %d)\n", si->gc_segs[NODE][BG_GC] + si->gc_segs[NODE][FG_GC], si->gc_segs[NODE][BG_GC]); seq_puts(s, " - Reclaimed segs :\n"); seq_printf(s, " - Normal : %d\n", sbi->gc_reclaimed_segs[GC_NORMAL]); seq_printf(s, " - Idle CB : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_CB]); seq_printf(s, " - Idle Greedy : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_GREEDY]); seq_printf(s, " - Idle AT : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_AT]); seq_printf(s, " - Urgent High : %d\n", sbi->gc_reclaimed_segs[GC_URGENT_HIGH]); seq_printf(s, " - Urgent Mid : %d\n", sbi->gc_reclaimed_segs[GC_URGENT_MID]); seq_printf(s, " - Urgent Low : %d\n", sbi->gc_reclaimed_segs[GC_URGENT_LOW]); seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks, si->bg_data_blks + si->bg_node_blks); seq_printf(s, " - data blocks : %d (%d)\n", si->data_blks, si->bg_data_blks); seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, si->bg_node_blks); seq_printf(s, "BG skip : IO: %u, Other: %u\n", si->io_skip_bggc, si->other_skip_bggc); seq_puts(s, "\nExtent Cache (Read):\n"); seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached[EX_READ], si->hit_rbtree[EX_READ]); seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n", !si->total_ext[EX_READ] ? 0 : div64_u64(si->hit_total[EX_READ] * 100, si->total_ext[EX_READ]), si->hit_total[EX_READ], si->total_ext[EX_READ]); seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", si->ext_tree[EX_READ], si->zombie_tree[EX_READ], si->ext_node[EX_READ]); seq_puts(s, "\nExtent Cache (Block Age):\n"); seq_printf(s, " - Allocated Data Blocks: %llu\n", si->allocated_data_blocks); seq_printf(s, " - Hit Count: L1:%llu L2:%llu\n", si->hit_cached[EX_BLOCK_AGE], si->hit_rbtree[EX_BLOCK_AGE]); seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n", !si->total_ext[EX_BLOCK_AGE] ? 0 : div64_u64(si->hit_total[EX_BLOCK_AGE] * 100, si->total_ext[EX_BLOCK_AGE]), si->hit_total[EX_BLOCK_AGE], si->total_ext[EX_BLOCK_AGE]); seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", si->ext_tree[EX_BLOCK_AGE], si->zombie_tree[EX_BLOCK_AGE], si->ext_node[EX_BLOCK_AGE]); seq_puts(s, "\nBalancing F2FS Async:\n"); seq_printf(s, " - DIO (R: %4d, W: %4d)\n", si->nr_dio_read, si->nr_dio_write); seq_printf(s, " - IO_R (Data: %4d, Node: %4d, Meta: %4d\n", si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta); seq_printf(s, " - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), ", si->nr_wb_cp_data, si->nr_wb_data, si->nr_flushing, si->nr_flushed, si->flush_list_empty); seq_printf(s, "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n", si->nr_discarding, si->nr_discarded, si->nr_discard_cmd, si->undiscard_blks); seq_printf(s, " - atomic IO: %4d (Max. %4d)\n", si->aw_cnt, si->max_aw_cnt); seq_printf(s, " - compress: %4d, hit:%8d\n", si->compress_pages, si->compress_page_hit); seq_printf(s, " - nodes: %4d in %4d\n", si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n", si->ndirty_dent, si->ndirty_dirs, si->ndirty_all); seq_printf(s, " - data: %4d in files:%4d\n", si->ndirty_data, si->ndirty_files); seq_printf(s, " - quota data: %4d in quota files:%4d\n", si->ndirty_qdata, si->nquota_files); seq_printf(s, " - meta: %4d in %4d\n", si->ndirty_meta, si->meta_pages); seq_printf(s, " - imeta: %4d\n", si->ndirty_imeta); seq_printf(s, " - fsync mark: %4lld\n", percpu_counter_sum_positive( &sbi->rf_node_block_count)); seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n", si->dirty_nats, si->nats, si->dirty_sits, si->sits); seq_printf(s, " - free_nids: %9d/%9d\n - alloc_nids: %9d\n", si->free_nids, si->avail_nids, si->alloc_nids); seq_puts(s, "\nDistribution of User Blocks:"); seq_puts(s, " [ valid | invalid | free ]\n"); seq_puts(s, " ["); for (j = 0; j < si->util_valid; j++) seq_putc(s, '-'); seq_putc(s, '|'); for (j = 0; j < si->util_invalid; j++) seq_putc(s, '-'); seq_putc(s, '|'); for (j = 0; j < si->util_free; j++) seq_putc(s, '-'); seq_puts(s, "]\n\n"); seq_printf(s, "IPU: %u blocks\n", si->inplace_count); seq_printf(s, "SSR: %u blocks in %u segments\n", si->block_count[SSR], si->segment_count[SSR]); seq_printf(s, "LFS: %u blocks in %u segments\n", si->block_count[LFS], si->segment_count[LFS]); /* segment usage info */ f2fs_update_sit_info(sbi); seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n", si->bimodal, si->avg_vblocks); /* memory footprint */ update_mem_info(sbi); seq_printf(s, "\nMemory: %llu KB\n", (si->base_mem + si->cache_mem + si->page_mem) >> 10); seq_printf(s, " - static: %llu KB\n", si->base_mem >> 10); seq_printf(s, " - cached all: %llu KB\n", si->cache_mem >> 10); seq_printf(s, " - read extent cache: %llu KB\n", si->ext_mem[EX_READ] >> 10); seq_printf(s, " - block age extent cache: %llu KB\n", si->ext_mem[EX_BLOCK_AGE] >> 10); seq_printf(s, " - paged : %llu KB\n", si->page_mem >> 10); } spin_unlock(&f2fs_stat_lock); return 0; } DEFINE_SHOW_ATTRIBUTE(stat); #endif int f2fs_build_stats(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_stat_info *si; struct f2fs_dev_stats *dev_stats; int i; si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL); if (!si) return -ENOMEM; dev_stats = f2fs_kzalloc(sbi, sizeof(struct f2fs_dev_stats) * sbi->s_ndevs, GFP_KERNEL); if (!dev_stats) { kfree(si); return -ENOMEM; } si->dev_stats = dev_stats; si->all_area_segs = le32_to_cpu(raw_super->segment_count); si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit); si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat); si->ssa_area_segs = le32_to_cpu(raw_super->segment_count_ssa); si->main_area_segs = le32_to_cpu(raw_super->segment_count_main); si->main_area_sections = le32_to_cpu(raw_super->section_count); si->main_area_zones = si->main_area_sections / le32_to_cpu(raw_super->secs_per_zone); si->sbi = sbi; sbi->stat_info = si; /* general extent cache stats */ for (i = 0; i < NR_EXTENT_CACHES; i++) { atomic64_set(&sbi->total_hit_ext[i], 0); atomic64_set(&sbi->read_hit_rbtree[i], 0); atomic64_set(&sbi->read_hit_cached[i], 0); } /* read extent_cache only */ atomic64_set(&sbi->read_hit_largest, 0); atomic_set(&sbi->inline_xattr, 0); atomic_set(&sbi->inline_inode, 0); atomic_set(&sbi->inline_dir, 0); atomic_set(&sbi->compr_inode, 0); atomic64_set(&sbi->compr_blocks, 0); atomic_set(&sbi->swapfile_inode, 0); atomic_set(&sbi->atomic_files, 0); atomic_set(&sbi->inplace_count, 0); for (i = META_CP; i < META_MAX; i++) atomic_set(&sbi->meta_count[i], 0); for (i = 0; i < MAX_CALL_TYPE; i++) atomic_set(&sbi->cp_call_count[i], 0); atomic_set(&sbi->max_aw_cnt, 0); spin_lock(&f2fs_stat_lock); list_add_tail(&si->stat_list, &f2fs_stat_list); spin_unlock(&f2fs_stat_lock); return 0; } void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); spin_lock(&f2fs_stat_lock); list_del(&si->stat_list); spin_unlock(&f2fs_stat_lock); kfree(si->dev_stats); kfree(si); } void __init f2fs_create_root_stats(void) { #ifdef CONFIG_DEBUG_FS f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); debugfs_create_file("status", 0444, f2fs_debugfs_root, NULL, &stat_fops); #endif } void f2fs_destroy_root_stats(void) { #ifdef CONFIG_DEBUG_FS debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; #endif } |
| 111 111 36 36 36 19 19 19 19 301 32 32 32 32 32 32 32 32 303 19 19 19 19 19 19 19 19 19 19 19 19 5 5 5 5 2 3 5 5 5 2 35 35 35 35 35 35 19 32 32 19 19 19 19 19 19 19 19 19 32 32 32 3 3 3 1 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 | // SPDX-License-Identifier: GPL-2.0 /* * Devices PM QoS constraints management * * Copyright (C) 2011 Texas Instruments, Inc. * * This module exposes the interface to kernel space for specifying * per-device PM QoS dependencies. It provides infrastructure for registration * of: * * Dependents on a QoS value : register requests * Watchers of QoS value : get notified when target QoS value changes * * This QoS design is best effort based. Dependents register their QoS needs. * Watchers register to keep track of the current QoS needs of the system. * Watchers can register a per-device notification callback using the * dev_pm_qos_*_notifier API. The notification chain data is stored in the * per-device constraint data struct. * * Note about the per-device constraint data struct allocation: * . The per-device constraints data struct ptr is stored into the device * dev_pm_info. * . To minimize the data usage by the per-device constraints, the data struct * is only allocated at the first call to dev_pm_qos_add_request. * . The data is later free'd when the device is removed from the system. * . A global mutex protects the constraints users from the data being * allocated and free'd. */ #include <linux/pm_qos.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/err.h> #include <trace/events/power.h> #include "power.h" static DEFINE_MUTEX(dev_pm_qos_mtx); static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx); /** * __dev_pm_qos_flags - Check PM QoS flags for a given device. * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. * * This routine must be called with dev->power.lock held. */ enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) { struct dev_pm_qos *qos = dev->power.qos; struct pm_qos_flags *pqf; s32 val; lockdep_assert_held(&dev->power.lock); if (IS_ERR_OR_NULL(qos)) return PM_QOS_FLAGS_UNDEFINED; pqf = &qos->flags; if (list_empty(&pqf->list)) return PM_QOS_FLAGS_UNDEFINED; val = pqf->effective_flags & mask; if (val) return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME; return PM_QOS_FLAGS_NONE; } /** * dev_pm_qos_flags - Check PM QoS flags for a given device (locked). * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. */ enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { unsigned long irqflags; enum pm_qos_flags_status ret; spin_lock_irqsave(&dev->power.lock, irqflags); ret = __dev_pm_qos_flags(dev, mask); spin_unlock_irqrestore(&dev->power.lock, irqflags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_flags); /** * __dev_pm_qos_resume_latency - Get resume latency constraint for a given device. * @dev: Device to get the PM QoS constraint value for. * * This routine must be called with dev->power.lock held. */ s32 __dev_pm_qos_resume_latency(struct device *dev) { lockdep_assert_held(&dev->power.lock); return dev_pm_qos_raw_resume_latency(dev); } /** * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked). * @dev: Device to get the PM QoS constraint value for. * @type: QoS request type. */ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos *qos = dev->power.qos; unsigned long flags; s32 ret; spin_lock_irqsave(&dev->power.lock, flags); switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); break; default: WARN_ON(1); ret = 0; } spin_unlock_irqrestore(&dev->power.lock, flags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_read_value); /** * apply_constraint - Add/modify/remove device PM QoS request. * @req: Constraint request to apply * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. * * Internal function to update the constraints list using the PM QoS core * code and if needed call the per-device callbacks. */ static int apply_constraint(struct dev_pm_qos_request *req, enum pm_qos_req_action action, s32 value) { struct dev_pm_qos *qos = req->dev->power.qos; int ret; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: if (WARN_ON(action != PM_QOS_REMOVE_REQ && value < 0)) value = 0; ret = pm_qos_update_target(&qos->resume_latency, &req->data.pnode, action, value); break; case DEV_PM_QOS_LATENCY_TOLERANCE: ret = pm_qos_update_target(&qos->latency_tolerance, &req->data.pnode, action, value); if (ret) { value = pm_qos_read_value(&qos->latency_tolerance); req->dev->power.set_latency_tolerance(req->dev, value); } break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_apply(&req->data.freq, action, value); break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); break; default: ret = -EINVAL; } return ret; } /* * dev_pm_qos_constraints_allocate * @dev: device to allocate data for * * Called at the first call to add_request, for constraint data allocation * Must be called with the dev_pm_qos_mtx mutex held */ static int dev_pm_qos_constraints_allocate(struct device *dev) { struct dev_pm_qos *qos; struct pm_qos_constraints *c; struct blocking_notifier_head *n; qos = kzalloc(sizeof(*qos), GFP_KERNEL); if (!qos) return -ENOMEM; n = kcalloc(3, sizeof(*n), GFP_KERNEL); if (!n) { kfree(qos); return -ENOMEM; } c = &qos->resume_latency; plist_head_init(&c->list); c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; c->type = PM_QOS_MIN; c->notifiers = n; BLOCKING_INIT_NOTIFIER_HEAD(n); c = &qos->latency_tolerance; plist_head_init(&c->list); c->target_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->default_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; freq_constraints_init(&qos->freq); INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); dev->power.qos = qos; spin_unlock_irq(&dev->power.lock); return 0; } static void __dev_pm_qos_hide_latency_limit(struct device *dev); static void __dev_pm_qos_hide_flags(struct device *dev); /** * dev_pm_qos_constraints_destroy * @dev: target device * * Called from the device PM subsystem on device removal under device_pm_lock(). */ void dev_pm_qos_constraints_destroy(struct device *dev) { struct dev_pm_qos *qos; struct dev_pm_qos_request *req, *tmp; struct pm_qos_constraints *c; struct pm_qos_flags *f; mutex_lock(&dev_pm_qos_sysfs_mtx); /* * If the device's PM QoS resume latency limit or PM QoS flags have been * exposed to user space, they have to be hidden at this point. */ pm_qos_sysfs_remove_resume_latency(dev); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); __dev_pm_qos_hide_flags(dev); qos = dev->power.qos; if (!qos) goto out; /* Flush the constraints lists for the device. */ c = &qos->resume_latency; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { /* * Update constraints list and call the notification * callbacks if needed */ apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->latency_tolerance; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.min_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.max_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } spin_lock_irq(&dev->power.lock); dev->power.qos = ERR_PTR(-ENODEV); spin_unlock_irq(&dev->power.lock); kfree(qos->resume_latency.notifiers); kfree(qos); out: mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } static bool dev_pm_qos_invalid_req_type(struct device *dev, enum dev_pm_qos_req_type type) { return type == DEV_PM_QOS_LATENCY_TOLERANCE && !dev->power.set_latency_tolerance; } static int __dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret = 0; if (!dev || !req || dev_pm_qos_invalid_req_type(dev, type)) return -EINVAL; if (WARN(dev_pm_qos_request_active(req), "%s() called for already added request\n", __func__)) return -EINVAL; if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); if (ret) return ret; req->dev = dev; req->type = type; if (req->type == DEV_PM_QOS_MIN_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MIN, value); else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MAX, value); else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); return ret; } /** * dev_pm_qos_add_request - inserts new qos request into the list * @dev: target device for the constraint * @req: pointer to a preallocated handle * @type: type of the request * @value: defines the qos request * * This function inserts a new entry in the device constraints list of * requested qos performance characteristics. It recomputes the aggregate * QoS expectations of parameters and initializes the dev_pm_qos_request * handle. Caller needs to save this handle for later use in updates and * removal. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory * to allocate for data structures, -ENODEV if the device has just been removed * from the system. * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_add_request(dev, req, type, value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_request); /** * __dev_pm_qos_update_request - Modify an existing device PM QoS request. * @req : PM QoS request to modify. * @new_value: New value to request. */ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { s32 curr_value; int ret = 0; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: curr_value = req->data.freq.pnode.prio; break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; default: return -EINVAL; } trace_dev_pm_qos_update_request(dev_name(req->dev), req->type, new_value); if (curr_value != new_value) ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value); return ret; } /** * dev_pm_qos_update_request - modifies an existing qos request * @req : handle to list element holding a dev_pm_qos request to use * @new_value: defines the qos request * * Updates an existing dev PM qos request along with updating the * target value. * * Attempts are made to make this code callable on hot code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_update_request(req, new_value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_request); static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type, PM_QOS_DEFAULT_VALUE); ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); return ret; } /** * dev_pm_qos_remove_request - modifies an existing qos request * @req: handle to request list element * * Will remove pm qos request from the list of constraints and * recompute the current target value. Call this on slow code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_remove_request(req); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); /** * dev_pm_qos_add_notifier - sets notification entry for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block managed by caller. * @type: request type. * * Will register the notifier into a notification chain that gets called * upon changes to the target value for the device. * * If the device's constraints object doesn't exist when this routine is called, * it will be created (or error code will be returned if that fails). */ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); if (ret) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier); /** * dev_pm_qos_remove_notifier - deletes notification for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block to be removed. * @type: request type. * * Will remove the notifier from the notification chain that gets called * upon changes to the target value. */ int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); /* Silently return if the constraints object is not present. */ if (IS_ERR_OR_NULL(dev->power.qos)) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier); /** * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor. * @dev: Device whose ancestor to add the request for. * @req: Pointer to the preallocated handle. * @type: Type of the request. * @value: Constraint latency value. */ int dev_pm_qos_add_ancestor_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { struct device *ancestor = dev->parent; int ret = -ENODEV; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: while (ancestor && !ancestor->power.ignore_children) ancestor = ancestor->parent; break; case DEV_PM_QOS_LATENCY_TOLERANCE: while (ancestor && !ancestor->power.set_latency_tolerance) ancestor = ancestor->parent; break; default: ancestor = NULL; } if (ancestor) ret = dev_pm_qos_add_request(ancestor, req, type, value); if (ret < 0) req->dev = NULL; return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request); static void __dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos_request *req = NULL; switch(type) { case DEV_PM_QOS_RESUME_LATENCY: req = dev->power.qos->resume_latency_req; dev->power.qos->resume_latency_req = NULL; break; case DEV_PM_QOS_LATENCY_TOLERANCE: req = dev->power.qos->latency_tolerance_req; dev->power.qos->latency_tolerance_req = NULL; break; case DEV_PM_QOS_FLAGS: req = dev->power.qos->flags_req; dev->power.qos->flags_req = NULL; break; default: WARN_ON(1); return; } __dev_pm_qos_remove_request(req); kfree(req); } static void dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_drop_user_request(dev, type); mutex_unlock(&dev_pm_qos_mtx); } /** * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space. * @dev: Device whose PM QoS latency limit is to be exposed to user space. * @value: Initial value of the latency limit. */ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev) || value < 0) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_RESUME_LATENCY, value); if (ret < 0) { kfree(req); return ret; } mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->resume_latency_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->resume_latency_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_resume_latency(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit); static void __dev_pm_qos_hide_latency_limit(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->resume_latency_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); } /** * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space. * @dev: Device whose PM QoS latency limit is to be hidden from user space. */ void dev_pm_qos_hide_latency_limit(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_resume_latency(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit); /** * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space. * @dev: Device whose PM QoS flags are to be exposed to user space. * @val: Initial values of the flags. */ int dev_pm_qos_expose_flags(struct device *dev, s32 val) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev)) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val); if (ret < 0) { kfree(req); return ret; } pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->flags_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->flags_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_flags(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags); static void __dev_pm_qos_hide_flags(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->flags_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); } /** * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space. * @dev: Device whose PM QoS flags are to be hidden from user space. */ void dev_pm_qos_hide_flags(struct device *dev) { pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_flags(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags); /** * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space. * @dev: Device to update the PM QoS flags request for. * @mask: Flags to set/clear. * @set: Whether to set or clear the flags (true means set). */ int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set) { s32 value; int ret; pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->flags_req) { ret = -EINVAL; goto out; } value = dev_pm_qos_requested_flags(dev); if (set) value |= mask; else value &= ~mask; ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value); out: mutex_unlock(&dev_pm_qos_mtx); pm_runtime_put(dev); return ret; } /** * dev_pm_qos_get_user_latency_tolerance - Get user space latency tolerance. * @dev: Device to obtain the user space latency tolerance for. */ s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev) { s32 ret; mutex_lock(&dev_pm_qos_mtx); ret = IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req ? PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT : dev->power.qos->latency_tolerance_req->data.pnode.prio; mutex_unlock(&dev_pm_qos_mtx); return ret; } /** * dev_pm_qos_update_user_latency_tolerance - Update user space latency tolerance. * @dev: Device to update the user space latency tolerance for. * @val: New user space latency tolerance for @dev (negative values disable). */ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) { int ret; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req) { struct dev_pm_qos_request *req; if (val < 0) { if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT) ret = 0; else ret = -EINVAL; goto out; } req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) { ret = -ENOMEM; goto out; } ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val); if (ret < 0) { kfree(req); goto out; } dev->power.qos->latency_tolerance_req = req; } else { if (val < 0) { __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE); ret = 0; } else { ret = __dev_pm_qos_update_request(dev->power.qos->latency_tolerance_req, val); } } out: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance); /** * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace * @dev: Device whose latency tolerance to expose */ int dev_pm_qos_expose_latency_tolerance(struct device *dev) { int ret; if (!dev->power.set_latency_tolerance) return -EINVAL; mutex_lock(&dev_pm_qos_sysfs_mtx); ret = pm_qos_sysfs_add_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance); /** * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace * @dev: Device whose latency tolerance to hide */ void dev_pm_qos_hide_latency_tolerance(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); /* Remove the request from user space now */ pm_runtime_get_sync(dev); dev_pm_qos_update_user_latency_tolerance(dev, PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance); |
| 10 10 16 21 20 18 17 12 5 16 16 11 11 5 16 16 2 14 14 14 16 7 7 5 5 5 2 2 2 7 3 2 3 1 1 4 15 10 4 4 4 1 1 4 3 2 2 4 1 2 2 3 3 3 2 1 3 4 4 2 2 2 4 10 10 9 1 8 8 8 10 1 2 3 3 3 1 2 1 2 1 2 3 3 10 9 8 8 8 8 1 2 5 1 4 6 6 2 10 1 10 1 1 1 1 1 992 675 7 7 7 157 157 1 1 157 994 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2; roundup_pow_of_two() * can overflow into UB on 32-bit arches */ if (attr->max_entries > 1UL << 31) return -EINVAL; } return 0; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { bpf_map_area_free(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() * during NAPI callback and cleared after the XDP redirect. There is no * explicit RCU read section which protects bpf_redirect_info->map but * local_bh_disable() also marks the beginning an RCU section. This * makes the complete softirq callback RCU protected. Thus after * following synchronize_rcu() there no bpf_redirect_info->map == map * assignment. */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *tx_dev, struct net_device *rx_dev) { struct xdp_txq_info txq = { .dev = tx_dev }; struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(struct list_head *flush_list) { struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj) return false; if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return false; if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, const struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } return 0; } static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_NOWAIT, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP || !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static long __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); else atomic_inc((atomic_t *)&dtab->items); return 0; } static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static u64 dev_map_mem_usage(const struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u64 usage = sizeof(struct bpf_dtab); if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); else usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); usage += atomic_read((atomic_t *)&dtab->items) * (u64)sizeof(struct bpf_dtab_netdev); return usage; } BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } subsys_initcall(dev_map_init); |
| 2659 3123 3125 10274 10285 3124 3134 3122 2503 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. * * A context holding the printk_cpu_sync must not spin waiting for * another CPU. For legacy printing, it could be the console_lock * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi() || is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 23 2580 160 429 175 197 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JIFFIES_H #define _LINUX_JIFFIES_H #include <linux/cache.h> #include <linux/limits.h> #include <linux/math64.h> #include <linux/minmax.h> #include <linux/types.h> #include <linux/time.h> #include <linux/timex.h> #include <vdso/jiffies.h> #include <asm/param.h> /* for HZ */ #include <generated/timeconst.h> /* * The following defines establish the engineering parameters of the PLL * model. The HZ variable establishes the timer interrupt frequency, 100 Hz * for the SunOS kernel, 256 Hz for the Ultrix kernel and 1024 Hz for the * OSF/1 kernel. The SHIFT_HZ define expresses the same value as the * nearest power of two in order to avoid hardware multiply operations. */ #if HZ >= 12 && HZ < 24 # define SHIFT_HZ 4 #elif HZ >= 24 && HZ < 48 # define SHIFT_HZ 5 #elif HZ >= 48 && HZ < 96 # define SHIFT_HZ 6 #elif HZ >= 96 && HZ < 192 # define SHIFT_HZ 7 #elif HZ >= 192 && HZ < 384 # define SHIFT_HZ 8 #elif HZ >= 384 && HZ < 768 # define SHIFT_HZ 9 #elif HZ >= 768 && HZ < 1536 # define SHIFT_HZ 10 #elif HZ >= 1536 && HZ < 3072 # define SHIFT_HZ 11 #elif HZ >= 3072 && HZ < 6144 # define SHIFT_HZ 12 #elif HZ >= 6144 && HZ < 12288 # define SHIFT_HZ 13 #else # error Invalid value of HZ. #endif /* Suppose we want to divide two numbers NOM and DEN: NOM/DEN, then we can * improve accuracy by shifting LSH bits, hence calculating: * (NOM << LSH) / DEN * This however means trouble for large NOM, because (NOM << LSH) may no * longer fit in 32 bits. The following way of calculating this gives us * some slack, under the following conditions: * - (NOM / DEN) fits in (32 - LSH) bits. * - (NOM % DEN) fits in (32 - LSH) bits. */ #define SH_DIV(NOM,DEN,LSH) ( (((NOM) / (DEN)) << (LSH)) \ + ((((NOM) % (DEN)) << (LSH)) + (DEN) / 2) / (DEN)) /* LATCH is used in the interval timer and ftape setup. */ #define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ extern void register_refined_jiffies(long clock_tick_rate); /* TICK_USEC is the time between ticks in usec */ #define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) /* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ #define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) #ifndef __jiffy_arch_data #define __jiffy_arch_data #endif /* * The 64-bit value is not atomic on 32-bit systems - you MUST NOT read it * without sampling the sequence number in jiffies_lock. * get_jiffies_64() will do this for you as appropriate. * * jiffies and jiffies_64 are at the same address for little-endian systems * and for 64-bit big-endian systems. * On 32-bit big-endian systems, jiffies is the lower 32 bits of jiffies_64 * (i.e., at address @jiffies_64 + 4). * See arch/ARCH/kernel/vmlinux.lds.S */ extern u64 __cacheline_aligned_in_smp jiffies_64; extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void); #else /** * get_jiffies_64 - read the 64-bit non-atomic jiffies_64 value * * When BITS_PER_LONG < 64, this uses sequence number sampling using * jiffies_lock to protect the 64-bit read. * * Return: current 64-bit jiffies value */ static inline u64 get_jiffies_64(void) { return (u64)jiffies; } #endif /** * DOC: General information about time_* inlines * * These inlines deal with timer wrapping correctly. You are strongly encouraged * to use them: * * #. Because people otherwise forget * #. Because if the timer wrap changes in future you won't have to alter your * driver code. */ /** * time_after - returns true if the time a is after time b. * @a: first comparable as unsigned long * @b: second comparable as unsigned long * * Do this with "<0" and ">=0" to only test the sign of the result. A * good compiler would generate better code (and a really good compiler * wouldn't care). Gcc is currently neither. * * Return: %true is time a is after time b, otherwise %false. */ #define time_after(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ ((long)((b) - (a)) < 0)) /** * time_before - returns true if the time a is before time b. * @a: first comparable as unsigned long * @b: second comparable as unsigned long * * Return: %true is time a is before time b, otherwise %false. */ #define time_before(a,b) time_after(b,a) /** * time_after_eq - returns true if the time a is after or the same as time b. * @a: first comparable as unsigned long * @b: second comparable as unsigned long * * Return: %true is time a is after or the same as time b, otherwise %false. */ #define time_after_eq(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ ((long)((a) - (b)) >= 0)) /** * time_before_eq - returns true if the time a is before or the same as time b. * @a: first comparable as unsigned long * @b: second comparable as unsigned long * * Return: %true is time a is before or the same as time b, otherwise %false. */ #define time_before_eq(a,b) time_after_eq(b,a) /** * time_in_range - Calculate whether a is in the range of [b, c]. * @a: time to test * @b: beginning of the range * @c: end of the range * * Return: %true is time a is in the range [b, c], otherwise %false. */ #define time_in_range(a,b,c) \ (time_after_eq(a,b) && \ time_before_eq(a,c)) /** * time_in_range_open - Calculate whether a is in the range of [b, c). * @a: time to test * @b: beginning of the range * @c: end of the range * * Return: %true is time a is in the range [b, c), otherwise %false. */ #define time_in_range_open(a,b,c) \ (time_after_eq(a,b) && \ time_before(a,c)) /* Same as above, but does so with platform independent 64bit types. * These must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64()). */ /** * time_after64 - returns true if the time a is after time b. * @a: first comparable as __u64 * @b: second comparable as __u64 * * This must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64()). * * Return: %true is time a is after time b, otherwise %false. */ #define time_after64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ ((__s64)((b) - (a)) < 0)) /** * time_before64 - returns true if the time a is before time b. * @a: first comparable as __u64 * @b: second comparable as __u64 * * This must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64()). * * Return: %true is time a is before time b, otherwise %false. */ #define time_before64(a,b) time_after64(b,a) /** * time_after_eq64 - returns true if the time a is after or the same as time b. * @a: first comparable as __u64 * @b: second comparable as __u64 * * This must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64()). * * Return: %true is time a is after or the same as time b, otherwise %false. */ #define time_after_eq64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ ((__s64)((a) - (b)) >= 0)) /** * time_before_eq64 - returns true if the time a is before or the same as time b. * @a: first comparable as __u64 * @b: second comparable as __u64 * * This must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64()). * * Return: %true is time a is before or the same as time b, otherwise %false. */ #define time_before_eq64(a,b) time_after_eq64(b,a) /** * time_in_range64 - Calculate whether a is in the range of [b, c]. * @a: time to test * @b: beginning of the range * @c: end of the range * * Return: %true is time a is in the range [b, c], otherwise %false. */ #define time_in_range64(a, b, c) \ (time_after_eq64(a, b) && \ time_before_eq64(a, c)) /* * These eight macros compare jiffies[_64] and 'a' for convenience. */ /** * time_is_before_jiffies - return true if a is before jiffies * @a: time (unsigned long) to compare to jiffies * * Return: %true is time a is before jiffies, otherwise %false. */ #define time_is_before_jiffies(a) time_after(jiffies, a) /** * time_is_before_jiffies64 - return true if a is before jiffies_64 * @a: time (__u64) to compare to jiffies_64 * * Return: %true is time a is before jiffies_64, otherwise %false. */ #define time_is_before_jiffies64(a) time_after64(get_jiffies_64(), a) /** * time_is_after_jiffies - return true if a is after jiffies * @a: time (unsigned long) to compare to jiffies * * Return: %true is time a is after jiffies, otherwise %false. */ #define time_is_after_jiffies(a) time_before(jiffies, a) /** * time_is_after_jiffies64 - return true if a is after jiffies_64 * @a: time (__u64) to compare to jiffies_64 * * Return: %true is time a is after jiffies_64, otherwise %false. */ #define time_is_after_jiffies64(a) time_before64(get_jiffies_64(), a) /** * time_is_before_eq_jiffies - return true if a is before or equal to jiffies * @a: time (unsigned long) to compare to jiffies * * Return: %true is time a is before or the same as jiffies, otherwise %false. */ #define time_is_before_eq_jiffies(a) time_after_eq(jiffies, a) /** * time_is_before_eq_jiffies64 - return true if a is before or equal to jiffies_64 * @a: time (__u64) to compare to jiffies_64 * * Return: %true is time a is before or the same jiffies_64, otherwise %false. */ #define time_is_before_eq_jiffies64(a) time_after_eq64(get_jiffies_64(), a) /** * time_is_after_eq_jiffies - return true if a is after or equal to jiffies * @a: time (unsigned long) to compare to jiffies * * Return: %true is time a is after or the same as jiffies, otherwise %false. */ #define time_is_after_eq_jiffies(a) time_before_eq(jiffies, a) /** * time_is_after_eq_jiffies64 - return true if a is after or equal to jiffies_64 * @a: time (__u64) to compare to jiffies_64 * * Return: %true is time a is after or the same as jiffies_64, otherwise %false. */ #define time_is_after_eq_jiffies64(a) time_before_eq64(get_jiffies_64(), a) /* * Have the 32-bit jiffies value wrap 5 minutes after boot * so jiffies wrap bugs show up earlier. */ #define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) /* * Change timeval to jiffies, trying to avoid the * most obvious overflows.. * * And some not so obvious. * * Note that we don't want to return LONG_MAX, because * for various timeout reasons we often end up having * to wait "jiffies+1" in order to guarantee that we wait * at _least_ "jiffies" - so "jiffies+1" had better still * be positive. */ #define MAX_JIFFY_OFFSET ((LONG_MAX >> 1)-1) extern unsigned long preset_lpj; /* * We want to do realistic conversions of time so we need to use the same * values the update wall clock code uses as the jiffies size. This value * is: TICK_NSEC (which is defined in timex.h). This * is a constant and is in nanoseconds. We will use scaled math * with a set of scales defined here as SEC_JIFFIE_SC, USEC_JIFFIE_SC and * NSEC_JIFFIE_SC. Note that these defines contain nothing but * constants and so are computed at compile time. SHIFT_HZ (computed in * timex.h) adjusts the scaling for different HZ values. * Scaled math??? What is that? * * Scaled math is a way to do integer math on values that would, * otherwise, either overflow, underflow, or cause undesired div * instructions to appear in the execution path. In short, we "scale" * up the operands so they take more bits (more precision, less * underflow), do the desired operation and then "scale" the result back * by the same amount. If we do the scaling by shifting we avoid the * costly mpy and the dastardly div instructions. * Suppose, for example, we want to convert from seconds to jiffies * where jiffies is defined in nanoseconds as NSEC_PER_JIFFIE. The * simple math is: jiff = (sec * NSEC_PER_SEC) / NSEC_PER_JIFFIE; We * observe that (NSEC_PER_SEC / NSEC_PER_JIFFIE) is a constant which we * might calculate at compile time, however, the result will only have * about 3-4 bits of precision (less for smaller values of HZ). * * So, we scale as follows: * jiff = (sec) * (NSEC_PER_SEC / NSEC_PER_JIFFIE); * jiff = ((sec) * ((NSEC_PER_SEC * SCALE)/ NSEC_PER_JIFFIE)) / SCALE; * Then we make SCALE a power of two so: * jiff = ((sec) * ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) >> SCALE; * Now we define: * #define SEC_CONV = ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) * jiff = (sec * SEC_CONV) >> SCALE; * * Often the math we use will expand beyond 32-bits so we tell C how to * do this and pass the 64-bit result of the mpy through the ">> SCALE" * which should take the result back to 32-bits. We want this expansion * to capture as much precision as possible. At the same time we don't * want to overflow so we pick the SCALE to avoid this. In this file, * that means using a different scale for each range of HZ values (as * defined in timex.h). * * For those who want to know, gcc will give a 64-bit result from a "*" * operator if the result is a long long AND at least one of the * operands is cast to long long (usually just prior to the "*" so as * not to confuse it into thinking it really has a 64-bit operand, * which, buy the way, it can do, but it takes more code and at least 2 * mpys). * We also need to be aware that one second in nanoseconds is only a * couple of bits away from overflowing a 32-bit word, so we MUST use * 64-bits to get the full range time in nanoseconds. */ /* * Here are the scales we will use. One for seconds, nanoseconds and * microseconds. * * Within the limits of cpp we do a rough cut at the SEC_JIFFIE_SC and * check if the sign bit is set. If not, we bump the shift count by 1. * (Gets an extra bit of precision where we can use it.) * We know it is set for HZ = 1024 and HZ = 100 not for 1000. * Haven't tested others. * Limits of cpp (for #if expressions) only long (no long long), but * then we only need the most signicant bit. */ #define SEC_JIFFIE_SC (31 - SHIFT_HZ) #if !((((NSEC_PER_SEC << 2) / TICK_NSEC) << (SEC_JIFFIE_SC - 2)) & 0x80000000) #undef SEC_JIFFIE_SC #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) /* * The maximum jiffy value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, * so use the messy SH_DIV macro to do it. Still all constants. */ #if BITS_PER_LONG < 64 # define MAX_SEC_IN_JIFFIES \ (long)((u64)((u64)MAX_JIFFY_OFFSET * TICK_NSEC) / NSEC_PER_SEC) #else /* take care of overflow on 64-bit machines */ # define MAX_SEC_IN_JIFFIES \ (SH_DIV((MAX_JIFFY_OFFSET >> SEC_JIFFIE_SC) * TICK_NSEC, NSEC_PER_SEC, 1) - 1) #endif /* * Convert various time units to each other: */ extern unsigned int jiffies_to_msecs(const unsigned long j); extern unsigned int jiffies_to_usecs(const unsigned long j); /** * jiffies_to_nsecs - Convert jiffies to nanoseconds * @j: jiffies value * * Return: nanoseconds value */ static inline u64 jiffies_to_nsecs(const unsigned long j) { return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } extern u64 jiffies64_to_nsecs(u64 j); extern u64 jiffies64_to_msecs(u64 j); extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) /* * HZ is equal to or smaller than 1000, and 1000 is a nice round * multiple of HZ, divide with the factor between them, but round * upwards: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); } #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) /* * HZ is larger than 1000, and HZ is a nice round multiple of 1000 - * simply multiply with the factor between them. * * But first make sure the multiplication result cannot overflow: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return m * (HZ / MSEC_PER_SEC); } #else /* * Generic case - multiply, round and divide. But first check that if * we are doing a net multiplication, that we wouldn't overflow: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32; } #endif /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code. __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The HZ range specific helpers _msecs_to_jiffies() are called both * directly here and from __msecs_to_jiffies() in the case where * constant folding is not possible. * * Return: jiffies value */ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) { if (__builtin_constant_p(m)) { if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } else { return __msecs_to_jiffies(m); } } /** * secs_to_jiffies: - convert seconds to jiffies * @_secs: time in seconds * * Conversion is done by simple multiplication with HZ * * secs_to_jiffies() is defined as a macro rather than a static inline * function so it can be used in static initializers. * * Return: jiffies value */ #define secs_to_jiffies(_secs) (unsigned long)((_secs) * HZ) extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) static inline unsigned long _usecs_to_jiffies(const unsigned int u) { return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); } #else static inline unsigned long _usecs_to_jiffies(const unsigned int u) { return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) >> USEC_TO_HZ_SHR32; } #endif /** * usecs_to_jiffies: - convert microseconds to jiffies * @u: time in microseconds * * conversion is done as follows: * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows as for msecs_to_jiffies. * * usecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code. __usecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The HZ range specific helpers _usecs_to_jiffies() are called both * directly here and from __msecs_to_jiffies() in the case where * constant folding is not possible. * * Return: jiffies value */ static __always_inline unsigned long usecs_to_jiffies(const unsigned int u) { if (__builtin_constant_p(u)) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } else { return __usecs_to_jiffies(u); } } extern unsigned long timespec64_to_jiffies(const struct timespec64 *value); extern void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value); extern clock_t jiffies_to_clock_t(unsigned long x); static inline clock_t jiffies_delta_to_clock_t(long delta) { return jiffies_to_clock_t(max(0L, delta)); } static inline unsigned int jiffies_delta_to_msecs(long delta) { return jiffies_to_msecs(max(0L, delta)); } extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); extern u64 nsecs_to_jiffies64(u64 n); extern unsigned long nsecs_to_jiffies(u64 n); #define TIMESTAMP_SIZE 30 #endif |
| 752 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * inet6 interface/address list definitions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IF_INET6_H #define _NET_IF_INET6_H #include <net/snmp.h> #include <linux/ipv6.h> #include <linux/refcount.h> /* inet6_dev.if_flags */ #define IF_RA_OTHERCONF 0x80 #define IF_RA_MANAGED 0x40 #define IF_RA_RCVD 0x20 #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, INET6_IFADDR_STATE_POSTDAD, INET6_IFADDR_STATE_ERRDAD, INET6_IFADDR_STATE_DEAD, }; struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; __u32 rt_priority; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; refcount_t refcnt; spinlock_t lock; int state; __u32 flags; __u8 dad_probes; __u8 stable_privacy_retry; __u16 scope; __u64 dad_nonce; unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ struct delayed_work dad_work; struct inet6_dev *idev; struct fib6_info *rt; struct hlist_node addr_lst; struct list_head if_list; /* * Used to safely traverse idev->addr_list in process context * if the idev->lock needed to protect idev->addr_list cannot be held. * In that case, add the items to this list temporarily and iterate * without holding idev->lock. * See addrconf_ifdown and dev_forward_change. */ struct list_head if_list_aux; struct list_head tmp_list; struct inet6_ifaddr *ifpub; int regen_count; bool tokenized; u8 ifa_proto; struct rcu_head rcu; struct in6_addr peer_addr; }; struct ip6_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; struct in6_addr sl_addr[] __counted_by(sl_max); }; #define IP6_SFBLOCK 10 /* allocate this many at once */ struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ipv6_mc_socklist __rcu *next; struct ip6_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip6_sf_list { struct ip6_sf_list __rcu *sf_next; struct in6_addr sf_addr; unsigned long sf_count[2]; /* include/exclude counts */ unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ struct rcu_head rcu; }; #define MAF_TIMER_RUNNING 0x01 #define MAF_LAST_REPORTER 0x02 #define MAF_LOADED 0x04 #define MAF_NOREPORT 0x08 #define MAF_GSQUERY 0x10 struct ifmcaddr6 { struct in6_addr mca_addr; struct inet6_dev *idev; struct ifmcaddr6 __rcu *next; struct ip6_sf_list __rcu *mca_sources; struct ip6_sf_list __rcu *mca_tomb; unsigned int mca_sfmode; unsigned char mca_crcount; unsigned long mca_sfcount[2]; struct delayed_work mca_work; unsigned int mca_flags; int mca_users; refcount_t mca_refcnt; unsigned long mca_cstamp; unsigned long mca_tstamp; struct rcu_head rcu; }; /* Anycast stuff */ struct ipv6_ac_socklist { struct in6_addr acl_addr; int acl_ifindex; struct ipv6_ac_socklist *acl_next; }; struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 __rcu *aca_next; struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK #define IFA_LINK IPV6_ADDR_LINKLOCAL #define IFA_SITE IPV6_ADDR_SITELOCAL struct ipv6_devstat { struct proc_dir_entry *proc_dir_entry; DEFINE_SNMP_STAT(struct ipstats_mib, ipv6); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6_mib_device, icmpv6dev); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib_device, icmpv6msgdev); }; struct inet6_dev { struct net_device *dev; netdevice_tracker dev_tracker; struct list_head addr_list; struct ifmcaddr6 __rcu *mc_list; struct ifmcaddr6 __rcu *mc_tomb; unsigned char mc_qrv; /* Query Robustness Variable */ unsigned char mc_gq_running; unsigned char mc_ifc_count; unsigned char mc_dad_count; unsigned long mc_v1_seen; /* Max time we stay in MLDv1 mode */ unsigned long mc_qi; /* Query Interval */ unsigned long mc_qri; /* Query Response Interval */ unsigned long mc_maxdelay; struct delayed_work mc_gq_work; /* general query work */ struct delayed_work mc_ifc_work; /* interface change work */ struct delayed_work mc_dad_work; /* dad complete mc work */ struct delayed_work mc_query_work; /* mld query work */ struct delayed_work mc_report_work; /* mld report work */ struct sk_buff_head mc_query_queue; /* mld query queue */ struct sk_buff_head mc_report_queue; /* mld report queue */ spinlock_t mc_query_lock; /* mld query queue lock */ spinlock_t mc_report_lock; /* mld query report lock */ struct mutex mc_lock; /* mld global lock */ struct ifacaddr6 __rcu *ac_list; rwlock_t lock; refcount_t refcnt; __u32 if_flags; int dead; u32 desync_factor; struct list_head tempaddr_list; struct in6_addr token; struct neigh_parms *nd_parms; struct ipv6_devconf cnf; struct ipv6_devstat stats; struct timer_list rs_timer; __s32 rs_interval; /* in jiffies */ __u8 rs_probes; unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ struct rcu_head rcu; unsigned int ra_mtu; }; static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf) { /* * +-------+-------+-------+-------+-------+-------+ * | 33 | 33 | DST13 | DST14 | DST15 | DST16 | * +-------+-------+-------+-------+-------+-------+ */ buf[0]= 0x33; buf[1]= 0x33; memcpy(buf + 2, &addr->s6_addr32[3], sizeof(__u32)); } static inline void ipv6_arcnet_mc_map(const struct in6_addr *addr, char *buf) { buf[0] = 0x00; } static inline void ipv6_ib_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { unsigned char scope = broadcast[5] & 0xF; buf[0] = 0; /* Reserved */ buf[1] = 0xff; /* Multicast QPN */ buf[2] = 0xff; buf[3] = 0xff; buf[4] = 0xff; buf[5] = 0x10 | scope; /* scope from broadcast address */ buf[6] = 0x60; /* IPv6 signature */ buf[7] = 0x1b; buf[8] = broadcast[8]; /* P_Key */ buf[9] = broadcast[9]; memcpy(buf + 10, addr->s6_addr + 6, 10); } static inline int ipv6_ipgre_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) { memcpy(buf, broadcast, 4); } else { /* v4mapped? */ if ((addr->s6_addr32[0] | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x0000ffff))) != 0) return -EINVAL; memcpy(buf, &addr->s6_addr32[3], 4); } return 0; } #endif |
| 516 516 516 516 8 8 515 516 515 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto_tcp.c: TCP load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * * Network name space (netns) aware. * Global data moved to netns i.e struct netns_ipvs * tcp_timeouts table has copy per netns in a hash table per * protocol ip_vs_proto_data and is handled by netns */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> /* for tcphdr */ #include <net/ip.h> #include <net/tcp.h> /* for csum_tcpudp_magic */ #include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; struct tcphdr _tcph, *th; __be16 _ports[2], *ports = NULL; /* In the event of icmp, we're only guaranteed to have the first 8 * bytes of the transport header, so we only check the rest of the * TCP packet for non-ICMP packets */ if (likely(!ip_vs_iph_icmp(iph))) { th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th) { if (th->rst || !(sysctl_sloppy_tcp(ipvs) || th->syn)) return 1; ports = &th->source; } } else { ports = skb_header_pointer( skb, iph->len, sizeof(_ports), &_ports); } if (!ports) { *verdict = NF_DROP; return 0; } /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( */ *verdict = NF_DROP; return 0; } /* * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) *verdict = ip_vs_leave(svc, skb, pd, iph); else *verdict = NF_DROP; return 0; } } /* NF_ACCEPT */ return 1; } static inline void tcp_fast_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); else #endif tcph->check = csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); } static inline void tcp_partial_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldlen, __be16 newlen) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); else #endif tcph->check = ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); } INDIRECT_CALLABLE_SCOPE int tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->vaddr.in6, &cp->caddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->vaddr.ip, cp->caddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, tcph->check, (char*)&(tcph->check) - (char*)tcph); } return 1; } static int tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* * Attempt ip_vs_app call. * It will fix ip_vs_conn and iph ack_seq stuff */ if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->dest = cp->dport; /* * Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->caddr.in6, &cp->daddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->caddr.ip, cp->daddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int tcphoff; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcphoff = sizeof(struct ipv6hdr); else #endif tcphoff = ip_hdrlen(skb); switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - tcphoff, ipv6_hdr(skb)->nexthdr, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } } else #endif if (csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - tcphoff, ip_hdr(skb)->protocol, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } break; default: /* No need to checksum. */ break; } return 1; } #define TCP_DIR_INPUT 0 #define TCP_DIR_OUTPUT 4 #define TCP_DIR_INPUT_ONLY 8 static const int tcp_state_off[IP_VS_DIR_LAST] = { [IP_VS_DIR_INPUT] = TCP_DIR_INPUT, [IP_VS_DIR_OUTPUT] = TCP_DIR_OUTPUT, [IP_VS_DIR_INPUT_ONLY] = TCP_DIR_INPUT_ONLY, }; /* * Timeout table[state] */ static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = 2*HZ, [IP_VS_TCP_S_ESTABLISHED] = 15*60*HZ, [IP_VS_TCP_S_SYN_SENT] = 2*60*HZ, [IP_VS_TCP_S_SYN_RECV] = 1*60*HZ, [IP_VS_TCP_S_FIN_WAIT] = 2*60*HZ, [IP_VS_TCP_S_TIME_WAIT] = 2*60*HZ, [IP_VS_TCP_S_CLOSE] = 10*HZ, [IP_VS_TCP_S_CLOSE_WAIT] = 60*HZ, [IP_VS_TCP_S_LAST_ACK] = 30*HZ, [IP_VS_TCP_S_LISTEN] = 2*60*HZ, [IP_VS_TCP_S_SYNACK] = 120*HZ, [IP_VS_TCP_S_LAST] = 2*HZ, }; static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = "NONE", [IP_VS_TCP_S_ESTABLISHED] = "ESTABLISHED", [IP_VS_TCP_S_SYN_SENT] = "SYN_SENT", [IP_VS_TCP_S_SYN_RECV] = "SYN_RECV", [IP_VS_TCP_S_FIN_WAIT] = "FIN_WAIT", [IP_VS_TCP_S_TIME_WAIT] = "TIME_WAIT", [IP_VS_TCP_S_CLOSE] = "CLOSE", [IP_VS_TCP_S_CLOSE_WAIT] = "CLOSE_WAIT", [IP_VS_TCP_S_LAST_ACK] = "LAST_ACK", [IP_VS_TCP_S_LISTEN] = "LISTEN", [IP_VS_TCP_S_SYNACK] = "SYNACK", [IP_VS_TCP_S_LAST] = "BUG!", }; static const bool tcp_state_active_table[IP_VS_TCP_S_LAST] = { [IP_VS_TCP_S_NONE] = false, [IP_VS_TCP_S_ESTABLISHED] = true, [IP_VS_TCP_S_SYN_SENT] = true, [IP_VS_TCP_S_SYN_RECV] = true, [IP_VS_TCP_S_FIN_WAIT] = false, [IP_VS_TCP_S_TIME_WAIT] = false, [IP_VS_TCP_S_CLOSE] = false, [IP_VS_TCP_S_CLOSE_WAIT] = false, [IP_VS_TCP_S_LAST_ACK] = false, [IP_VS_TCP_S_LISTEN] = false, [IP_VS_TCP_S_SYNACK] = true, }; #define sNO IP_VS_TCP_S_NONE #define sES IP_VS_TCP_S_ESTABLISHED #define sSS IP_VS_TCP_S_SYN_SENT #define sSR IP_VS_TCP_S_SYN_RECV #define sFW IP_VS_TCP_S_FIN_WAIT #define sTW IP_VS_TCP_S_TIME_WAIT #define sCL IP_VS_TCP_S_CLOSE #define sCW IP_VS_TCP_S_CLOSE_WAIT #define sLA IP_VS_TCP_S_LAST_ACK #define sLI IP_VS_TCP_S_LISTEN #define sSA IP_VS_TCP_S_SYNACK struct tcp_states_t { int next_state[IP_VS_TCP_S_LAST]; }; static const char * tcp_state_name(int state) { if (state >= IP_VS_TCP_S_LAST) return "ERR!"; return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?"; } static bool tcp_state_active(int state) { if (state >= IP_VS_TCP_S_LAST) return false; return tcp_state_active_table[state]; } static struct tcp_states_t tcp_states[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSR, sSS, sSS, sSS, sSS, sSS, sLI, sSR }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static struct tcp_states_t tcp_states_dos[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }}, /*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSA, sSS, sSS, sSS, sSS, sSS, sLI, sSA }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags) { int on = (flags & 1); /* secure_tcp */ /* ** FIXME: change secure_tcp to independent sysctl var ** or make it per-service or per-app because it is valid ** for most if not for all of the applications. Something ** like "capabilities" (flags) for each object. */ pd->tcp_state_table = (on ? tcp_states_dos : tcp_states); } static inline int tcp_state_idx(struct tcphdr *th) { if (th->rst) return 3; if (th->syn) return 0; if (th->fin) return 1; if (th->ack) return 2; return -1; } static inline void set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, struct tcphdr *th) { int state_idx; int new_state = IP_VS_TCP_S_CLOSE; int state_off = tcp_state_off[direction]; /* * Update state offset to INPUT_ONLY if necessary * or delete NO_OUTPUT flag if output packet detected */ if (cp->flags & IP_VS_CONN_F_NOOUTPUT) { if (state_off == TCP_DIR_OUTPUT) cp->flags &= ~IP_VS_CONN_F_NOOUTPUT; else state_off = TCP_DIR_INPUT_ONLY; } if ((state_idx = tcp_state_idx(th)) < 0) { IP_VS_DBG(8, "tcp_state_idx=%d!!!\n", state_idx); goto tcp_state_out; } new_state = pd->tcp_state_table[state_off+state_idx].next_state[cp->state]; tcp_state_out: if (new_state != cp->state) { struct ip_vs_dest *dest = cp->dest; IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d " "d:%s:%d state: %s->%s conn->refcnt:%d\n", pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), th->syn ? 'S' : '.', th->fin ? 'F' : '.', th->ack ? 'A' : '.', th->rst ? 'R' : '.', IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), tcp_state_name(cp->state), tcp_state_name(new_state), refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } if (new_state == IP_VS_TCP_S_ESTABLISHED) ip_vs_control_assure_ct(cp); } if (likely(pd)) cp->timeout = pd->timeout_table[cp->state = new_state]; else /* What to do ? */ cp->timeout = tcp_timeouts[cp->state = new_state]; } /* * Handle state transitions */ static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { struct tcphdr _tcph, *th; #ifdef CONFIG_IP_VS_IPV6 int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); #else int ihl = ip_hdrlen(skb); #endif th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); if (th == NULL) return; spin_lock_bh(&cp->lock); set_tcp_state(pd, cp, direction, th); spin_unlock_bh(&cp->lock); } static inline __u16 tcp_app_hashkey(__be16 port) { return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port) & TCP_APP_TAB_MASK; } static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } list_add_rcu(&inc->p_list, &ipvs->tcp_apps[hash]); atomic_inc(&pd->appcnt); out: return ret; } static void tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); } static int tcp_app_conn_bind(struct ip_vs_conn *cp) { struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; /* Default binding: bind app only for NAT */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) return 0; /* Lookup application incarnations and bind the right one */ hash = tcp_app_hashkey(cp->vport); list_for_each_entry_rcu(inc, &ipvs->tcp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), inc->name, ntohs(inc->port)); cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); break; } } return result; } /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN] : tcp_timeouts[IP_VS_TCP_S_LISTEN]); spin_unlock_bh(&cp->lock); } /* --------------------------------------------- * timeouts is netns related now. * --------------------------------------------- */ static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); if (!pd->timeout_table) return -ENOMEM; pd->tcp_state_table = tcp_states; return 0; } static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_tcp = { .name = "TCP", .protocol = IPPROTO_TCP, .num_states = IP_VS_TCP_S_LAST, .dont_defrag = 0, .init = NULL, .exit = NULL, .init_netns = __ip_vs_tcp_init, .exit_netns = __ip_vs_tcp_exit, .register_app = tcp_register_app, .unregister_app = tcp_unregister_app, .conn_schedule = tcp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = tcp_snat_handler, .dnat_handler = tcp_dnat_handler, .state_name = tcp_state_name, .state_transition = tcp_state_transition, .app_conn_bind = tcp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = tcp_timeout_change, }; |
| 70 70 70 70 70 70 70 69 70 70 70 70 69 70 70 70 70 70 69 70 70 70 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/static_call.h> #include <linux/bug.h> #include <linux/smp.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/cpu.h> #include <linux/processor.h> #include <asm/sections.h> extern struct static_call_site __start_static_call_sites[], __stop_static_call_sites[]; extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; int static_call_initialized; /* * Must be called before early_initcall() to be effective. */ void static_call_force_reinit(void) { if (WARN_ON_ONCE(!static_call_initialized)) return; static_call_initialized++; } /* mutex to protect key modules/sites */ static DEFINE_MUTEX(static_call_mutex); static void static_call_lock(void) { mutex_lock(&static_call_mutex); } static void static_call_unlock(void) { mutex_unlock(&static_call_mutex); } static inline void *static_call_addr(struct static_call_site *site) { return (void *)((long)site->addr + (long)&site->addr); } static inline unsigned long __static_call_key(const struct static_call_site *site) { return (long)site->key + (long)&site->key; } static inline struct static_call_key *static_call_key(const struct static_call_site *site) { return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); } /* These assume the key is word-aligned. */ static inline bool static_call_is_init(struct static_call_site *site) { return __static_call_key(site) & STATIC_CALL_SITE_INIT; } static inline bool static_call_is_tail(struct static_call_site *site) { return __static_call_key(site) & STATIC_CALL_SITE_TAIL; } static inline void static_call_set_init(struct static_call_site *site) { site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - (long)&site->key; } static int static_call_site_cmp(const void *_a, const void *_b) { const struct static_call_site *a = _a; const struct static_call_site *b = _b; const struct static_call_key *key_a = static_call_key(a); const struct static_call_key *key_b = static_call_key(b); if (key_a < key_b) return -1; if (key_a > key_b) return 1; return 0; } static void static_call_site_swap(void *_a, void *_b, int size) { long delta = (unsigned long)_a - (unsigned long)_b; struct static_call_site *a = _a; struct static_call_site *b = _b; struct static_call_site tmp = *a; a->addr = b->addr - delta; a->key = b->key - delta; b->addr = tmp.addr + delta; b->key = tmp.key + delta; } static inline void static_call_sort_entries(struct static_call_site *start, struct static_call_site *stop) { sort(start, stop - start, sizeof(struct static_call_site), static_call_site_cmp, static_call_site_swap); } static inline bool static_call_key_has_mods(struct static_call_key *key) { return !(key->type & 1); } static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) { if (!static_call_key_has_mods(key)) return NULL; return key->mods; } static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) { if (static_call_key_has_mods(key)) return NULL; return (struct static_call_site *)(key->type & ~1); } void __static_call_update(struct static_call_key *key, void *tramp, void *func) { struct static_call_site *site, *stop; struct static_call_mod *site_mod, first; cpus_read_lock(); static_call_lock(); if (key->func == func) goto done; key->func = func; arch_static_call_transform(NULL, tramp, func, false); /* * If uninitialized, we'll not update the callsites, but they still * point to the trampoline and we just patched that. */ if (WARN_ON_ONCE(!static_call_initialized)) goto done; first = (struct static_call_mod){ .next = static_call_key_next(key), .mod = NULL, .sites = static_call_key_sites(key), }; for (site_mod = &first; site_mod; site_mod = site_mod->next) { bool init = system_state < SYSTEM_RUNNING; struct module *mod = site_mod->mod; if (!site_mod->sites) { /* * This can happen if the static call key is defined in * a module which doesn't use it. * * It also happens in the has_mods case, where the * 'first' entry has no sites associated with it. */ continue; } stop = __stop_static_call_sites; if (mod) { #ifdef CONFIG_MODULES stop = mod->static_call_sites + mod->num_static_call_sites; init = mod->state == MODULE_STATE_COMING; #endif } for (site = site_mod->sites; site < stop && static_call_key(site) == key; site++) { void *site_addr = static_call_addr(site); if (!init && static_call_is_init(site)) continue; if (!kernel_text_address((unsigned long)site_addr)) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!static_call_is_init(site), "can't patch static call site at %pS", site_addr); continue; } arch_static_call_transform(site_addr, tramp, func, static_call_is_tail(site)); } } done: static_call_unlock(); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(__static_call_update); static int __static_call_init(struct module *mod, struct static_call_site *start, struct static_call_site *stop) { struct static_call_site *site; struct static_call_key *key, *prev_key = NULL; struct static_call_mod *site_mod; if (start == stop) return 0; static_call_sort_entries(start, stop); for (site = start; site < stop; site++) { void *site_addr = static_call_addr(site); if ((mod && within_module_init((unsigned long)site_addr, mod)) || (!mod && init_section_contains(site_addr, 1))) static_call_set_init(site); key = static_call_key(site); if (key != prev_key) { prev_key = key; /* * For vmlinux (!mod) avoid the allocation by storing * the sites pointer in the key itself. Also see * __static_call_update()'s @first. * * This allows architectures (eg. x86) to call * static_call_init() before memory allocation works. */ if (!mod) { key->sites = site; key->type |= 1; goto do_transform; } site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); if (!site_mod) return -ENOMEM; /* * When the key has a direct sites pointer, extract * that into an explicit struct static_call_mod, so we * can have a list of modules. */ if (static_call_key_sites(key)) { site_mod->mod = NULL; site_mod->next = NULL; site_mod->sites = static_call_key_sites(key); key->mods = site_mod; site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); if (!site_mod) return -ENOMEM; } site_mod->mod = mod; site_mod->sites = site; site_mod->next = static_call_key_next(key); key->mods = site_mod; } do_transform: arch_static_call_transform(site_addr, NULL, key->func, static_call_is_tail(site)); } return 0; } static int addr_conflict(struct static_call_site *site, void *start, void *end) { unsigned long addr = (unsigned long)static_call_addr(site); if (addr <= (unsigned long)end && addr + CALL_INSN_SIZE > (unsigned long)start) return 1; return 0; } static int __static_call_text_reserved(struct static_call_site *iter_start, struct static_call_site *iter_stop, void *start, void *end, bool init) { struct static_call_site *iter = iter_start; while (iter < iter_stop) { if (init || !static_call_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifdef CONFIG_MODULES static int __static_call_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; scoped_guard(rcu) { mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; } if (!mod) return 0; ret = __static_call_text_reserved(mod->static_call_sites, mod->static_call_sites + mod->num_static_call_sites, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static unsigned long tramp_key_lookup(unsigned long addr) { struct static_call_tramp_key *start = __start_static_call_tramp_key; struct static_call_tramp_key *stop = __stop_static_call_tramp_key; struct static_call_tramp_key *tramp_key; for (tramp_key = start; tramp_key != stop; tramp_key++) { unsigned long tramp; tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; if (tramp == addr) return (long)tramp_key->key + (long)&tramp_key->key; } return 0; } static int static_call_add_module(struct module *mod) { struct static_call_site *start = mod->static_call_sites; struct static_call_site *stop = start + mod->num_static_call_sites; struct static_call_site *site; for (site = start; site != stop; site++) { unsigned long s_key = __static_call_key(site); unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; unsigned long key; /* * Is the key is exported, 'addr' points to the key, which * means modules are allowed to call static_call_update() on * it. * * Otherwise, the key isn't exported, and 'addr' points to the * trampoline so we need to lookup the key. * * We go through this dance to prevent crazy modules from * abusing sensitive static calls. */ if (!kernel_text_address(addr)) continue; key = tramp_key_lookup(addr); if (!key) { pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", static_call_addr(site)); return -EINVAL; } key |= s_key & STATIC_CALL_SITE_FLAGS; site->key = key - (long)&site->key; } return __static_call_init(mod, start, stop); } static void static_call_del_module(struct module *mod) { struct static_call_site *start = mod->static_call_sites; struct static_call_site *stop = mod->static_call_sites + mod->num_static_call_sites; struct static_call_key *key, *prev_key = NULL; struct static_call_mod *site_mod, **prev; struct static_call_site *site; for (site = start; site < stop; site++) { key = static_call_key(site); /* * If the key was not updated due to a memory allocation * failure in __static_call_init() then treating key::sites * as key::mods in the code below would cause random memory * access and #GP. In that case all subsequent sites have * not been touched either, so stop iterating. */ if (!static_call_key_has_mods(key)) break; if (key == prev_key) continue; prev_key = key; for (prev = &key->mods, site_mod = key->mods; site_mod && site_mod->mod != mod; prev = &site_mod->next, site_mod = site_mod->next) ; if (!site_mod) continue; *prev = site_mod->next; kfree(site_mod); } } static int static_call_module_notify(struct notifier_block *nb, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); static_call_lock(); switch (val) { case MODULE_STATE_COMING: ret = static_call_add_module(mod); if (ret) { pr_warn("Failed to allocate memory for static calls\n"); static_call_del_module(mod); } break; case MODULE_STATE_GOING: static_call_del_module(mod); break; } static_call_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block static_call_module_nb = { .notifier_call = static_call_module_notify, }; #else static inline int __static_call_mod_text_reserved(void *start, void *end) { return 0; } #endif /* CONFIG_MODULES */ int static_call_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __static_call_text_reserved(__start_static_call_sites, __stop_static_call_sites, start, end, init); if (ret) return ret; return __static_call_mod_text_reserved(start, end); } int __init static_call_init(void) { int ret; /* See static_call_force_reinit(). */ if (static_call_initialized == 1) return 0; cpus_read_lock(); static_call_lock(); ret = __static_call_init(NULL, __start_static_call_sites, __stop_static_call_sites); static_call_unlock(); cpus_read_unlock(); if (ret) { pr_err("Failed to allocate memory for static_call!\n"); BUG(); } #ifdef CONFIG_MODULES if (!static_call_initialized) register_module_notifier(&static_call_module_nb); #endif static_call_initialized = 1; return 0; } early_initcall(static_call_init); #ifdef CONFIG_STATIC_CALL_SELFTEST static int func_a(int x) { return x+1; } static int func_b(int x) { return x+2; } DEFINE_STATIC_CALL(sc_selftest, func_a); static struct static_call_data { int (*func)(int); int val; int expect; } static_call_data [] __initdata = { { NULL, 2, 3 }, { func_b, 2, 4 }, { func_a, 2, 3 } }; static int __init test_static_call_init(void) { int i; for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { struct static_call_data *scd = &static_call_data[i]; if (scd->func) static_call_update(sc_selftest, scd->func); WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); } return 0; } early_initcall(test_static_call_init); #endif /* CONFIG_STATIC_CALL_SELFTEST */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* net/atm/pvc.c - ATM PVC sockets */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ #include <linux/net.h> /* struct socket, struct proto_ops */ #include <linux/atm.h> /* ATM stuff */ #include <linux/atmdev.h> /* ATM devices */ #include <linux/errno.h> /* error codes */ #include <linux/kernel.h> /* printk */ #include <linux/init.h> #include <linux/skbuff.h> #include <linux/bitops.h> #include <linux/export.h> #include <net/sock.h> /* for sock_no_* */ #include "resources.h" /* devs and vccs */ #include "common.h" /* common for PVCs and SVCs */ static int pvc_shutdown(struct socket *sock, int how) { return 0; } static int pvc_bind(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len) { struct sock *sk = sock->sk; struct sockaddr_atmpvc *addr; struct atm_vcc *vcc; int error; if (sockaddr_len != sizeof(struct sockaddr_atmpvc)) return -EINVAL; addr = (struct sockaddr_atmpvc *)sockaddr; if (addr->sap_family != AF_ATMPVC) return -EAFNOSUPPORT; lock_sock(sk); vcc = ATM_SD(sock); if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } if (test_bit(ATM_VF_PARTIAL, &vcc->flags)) { if (vcc->vpi != ATM_VPI_UNSPEC) addr->sap_addr.vpi = vcc->vpi; if (vcc->vci != ATM_VCI_UNSPEC) addr->sap_addr.vci = vcc->vci; } error = vcc_connect(sock, addr->sap_addr.itf, addr->sap_addr.vpi, addr->sap_addr.vci); out: release_sock(sk); return error; } static int pvc_connect(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { return pvc_bind(sock, sockaddr, sockaddr_len); } static int pvc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int error; lock_sock(sk); error = vcc_setsockopt(sock, level, optname, optval, optlen); release_sock(sk); return error; } static int pvc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int error; lock_sock(sk); error = vcc_getsockopt(sock, level, optname, optval, optlen); release_sock(sk); return error; } static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr, int peer) { struct sockaddr_atmpvc *addr; struct atm_vcc *vcc = ATM_SD(sock); if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags)) return -ENOTCONN; addr = (struct sockaddr_atmpvc *)sockaddr; memset(addr, 0, sizeof(*addr)); addr->sap_family = AF_ATMPVC; addr->sap_addr.itf = vcc->dev->number; addr->sap_addr.vpi = vcc->vpi; addr->sap_addr.vci = vcc->vci; return sizeof(struct sockaddr_atmpvc); } static const struct proto_ops pvc_proto_ops = { .family = PF_ATMPVC, .owner = THIS_MODULE, .release = vcc_release, .bind = pvc_bind, .connect = pvc_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pvc_getname, .poll = vcc_poll, .ioctl = vcc_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = vcc_compat_ioctl, #endif .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = pvc_shutdown, .setsockopt = pvc_setsockopt, .getsockopt = pvc_getsockopt, .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, }; static int pvc_create(struct net *net, struct socket *sock, int protocol, int kern) { if (net != &init_net) return -EAFNOSUPPORT; sock->ops = &pvc_proto_ops; return vcc_create(net, sock, protocol, PF_ATMPVC, kern); } static const struct net_proto_family pvc_family_ops = { .family = PF_ATMPVC, .create = pvc_create, .owner = THIS_MODULE, }; /* * Initialize the ATM PVC protocol family */ int __init atmpvc_init(void) { return sock_register(&pvc_family_ops); } void atmpvc_exit(void) { sock_unregister(PF_ATMPVC); } |
| 4 4 4 2 2 4 2 2 2 3 1 3 42 20 19 18 17 3 49 49 48 48 41 42 20 1 1 1 1 3 2 1 2 2 2 2 1 1 2 2 1 1 2 2 2 1 1 1 3 3 2 1 1 3 3 2 2 2 2 1 3 1 6 7 6 4 4 4 4 3 4 7 23 6 23 5 4 4 17 7 10 10 9 8 6 2 1 1 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Ioctl handler * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/capability.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/if_bridge.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/times.h> #include <net/net_namespace.h> #include <linux/uaccess.h> #include "br_private.h" static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (i >= num) break; if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); return i; } /* called with RTNL */ static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->port_no < num) ifindices[p->port_no] = p->dev->ifindex; } } /* * Format up to a page worth of forwarding table entries * userbuf -- where to copy result * maxnum -- maximum number of entries desired * (limited to a page for sanity) * offset -- number of records to skip */ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, unsigned long maxnum, unsigned long offset) { int num; void *buf; size_t size; /* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */ if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry)) maxnum = PAGE_SIZE/sizeof(struct __fdb_entry); size = maxnum * sizeof(struct __fdb_entry); buf = kmalloc(size, GFP_USER); if (!buf) return -ENOMEM; num = br_fdb_fillbuf(br, buf, maxnum, offset); if (num > 0) { if (copy_to_user(userbuf, buf, array_size(num, sizeof(struct __fdb_entry)))) num = -EFAULT; } kfree(buf); return num; } /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { struct net *net = dev_net(br->dev); struct net_device *dev; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; if (isadd) ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); return ret; } #define BR_UARGS_MAX 4 static int br_dev_read_uargs(unsigned long *args, size_t nr_args, void __user **argp, void __user *data) { int ret; if (nr_args < 2 || nr_args > BR_UARGS_MAX) return -EINVAL; if (in_compat_syscall()) { unsigned int cargs[BR_UARGS_MAX]; int i; ret = copy_from_user(cargs, data, nr_args * sizeof(*cargs)); if (ret) goto fault; for (i = 0; i < nr_args; ++i) args[i] = cargs[i]; *argp = compat_ptr(args[1]); } else { ret = copy_from_user(args, data, nr_args * sizeof(*args)); if (ret) goto fault; *argp = (void __user *)args[1]; } return 0; fault: return -EFAULT; } /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult * to do the translation for 32/64bit ioctl compatibility. */ int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p = NULL; unsigned long args[4]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_ADD_IF: case BRCTL_DEL_IF: return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF); case BRCTL_GET_BRIDGE_INFO: { struct __bridge_info b; memset(&b, 0, sizeof(struct __bridge_info)); rcu_read_lock(); memcpy(&b.designated_root, &br->designated_root, 8); memcpy(&b.bridge_id, &br->bridge_id, 8); b.root_path_cost = br->root_path_cost; b.max_age = jiffies_to_clock_t(br->max_age); b.hello_time = jiffies_to_clock_t(br->hello_time); b.forward_delay = br->forward_delay; b.bridge_max_age = br->bridge_max_age; b.bridge_hello_time = br->bridge_hello_time; b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay); b.topology_change = br->topology_change; b.topology_change_detected = br->topology_change_detected; b.root_port = br->root_port; b.stp_enabled = (br->stp_enabled != BR_NO_STP); b.ageing_time = jiffies_to_clock_t(br->ageing_time); b.hello_timer_value = br_timer_value(&br->hello_timer); b.tcn_timer_value = br_timer_value(&br->tcn_timer); b.topology_change_timer_value = br_timer_value(&br->topology_change_timer); b.gc_timer_value = br_timer_value(&br->gc_work.timer); rcu_read_unlock(); if (copy_to_user((void __user *)args[1], &b, sizeof(b))) return -EFAULT; return 0; } case BRCTL_GET_PORT_LIST: { int num, *indices; num = args[2]; if (num < 0) return -EINVAL; if (num == 0) num = 256; if (num > BR_MAX_PORTS) num = BR_MAX_PORTS; indices = kcalloc(num, sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; get_port_ifindices(br, indices, num); if (copy_to_user(argp, indices, array_size(num, sizeof(int)))) num = -EFAULT; kfree(indices); return num; } case BRCTL_SET_BRIDGE_FORWARD_DELAY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_forward_delay(br, args[1]); break; case BRCTL_SET_BRIDGE_HELLO_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_hello_time(br, args[1]); break; case BRCTL_SET_BRIDGE_MAX_AGE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_max_age(br, args[1]); break; case BRCTL_SET_AGEING_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_ageing_time(br, args[1]); break; case BRCTL_GET_PORT_INFO: { struct __port_info p; struct net_bridge_port *pt; rcu_read_lock(); if ((pt = br_get_port(br, args[2])) == NULL) { rcu_read_unlock(); return -EINVAL; } memset(&p, 0, sizeof(struct __port_info)); memcpy(&p.designated_root, &pt->designated_root, 8); memcpy(&p.designated_bridge, &pt->designated_bridge, 8); p.port_id = pt->port_id; p.designated_port = pt->designated_port; p.path_cost = pt->path_cost; p.designated_cost = pt->designated_cost; p.state = pt->state; p.top_change_ack = pt->topology_change_ack; p.config_pending = pt->config_pending; p.message_age_timer_value = br_timer_value(&pt->message_age_timer); p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer); p.hold_timer_value = br_timer_value(&pt->hold_timer); rcu_read_unlock(); if (copy_to_user(argp, &p, sizeof(p))) return -EFAULT; return 0; } case BRCTL_SET_BRIDGE_STP_STATE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_stp_set_enabled(br, args[1], NULL); break; case BRCTL_SET_BRIDGE_PRIORITY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_bridge_priority(br, args[1]); ret = 0; break; case BRCTL_SET_PORT_PRIORITY: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_SET_PATH_COST: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_path_cost(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_GET_FDB_ENTRIES: return get_fdb_entries(br, argp, args[2], args[3]); default: ret = -EOPNOTSUPP; } if (!ret) { if (p) br_ifinfo_notify(RTM_NEWLINK, NULL, p); else netdev_state_change(br->dev); } return ret; } static int old_deviceless(struct net *net, void __user *data) { unsigned long args[3]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_GET_VERSION: return BRCTL_VERSION; case BRCTL_GET_BRIDGES: { int *indices; int ret = 0; if (args[2] >= 2048) return -ENOMEM; indices = kcalloc(args[2], sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; args[2] = get_bridge_ifindices(net, indices, args[2]); ret = copy_to_user(argp, indices, array_size(args[2], sizeof(int))) ? -EFAULT : args[2]; kfree(indices); return ret; } case BRCTL_ADD_BRIDGE: case BRCTL_DEL_BRIDGE: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, argp, IFNAMSIZ)) return -EFAULT; buf[IFNAMSIZ-1] = 0; if (args[0] == BRCTL_ADD_BRIDGE) return br_add_bridge(net, buf); return br_del_bridge(net, buf); } } return -EOPNOTSUPP; } int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg) { int ret = -EOPNOTSUPP; struct ifreq ifr; if (cmd == SIOCBRADDIF || cmd == SIOCBRDELIF) { void __user *data; char *colon; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (get_user_ifreq(&ifr, &data, uarg)) return -EFAULT; ifr.ifr_name[IFNAMSIZ - 1] = 0; colon = strchr(ifr.ifr_name, ':'); if (colon) *colon = 0; } rtnl_lock(); switch (cmd) { case SIOCGIFBR: case SIOCSIFBR: ret = old_deviceless(net, uarg); break; case SIOCBRADDBR: case SIOCBRDELBR: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } if (copy_from_user(buf, uarg, IFNAMSIZ)) { ret = -EFAULT; break; } buf[IFNAMSIZ-1] = 0; if (cmd == SIOCBRADDBR) ret = br_add_bridge(net, buf); else ret = br_del_bridge(net, buf); } break; case SIOCBRADDIF: case SIOCBRDELIF: { struct net_device *dev; dev = __dev_get_by_name(net, ifr.ifr_name); if (!dev || !netif_device_present(dev)) { ret = -ENODEV; break; } if (!netif_is_bridge_master(dev)) { ret = -EOPNOTSUPP; break; } ret = add_del_if(netdev_priv(dev), ifr.ifr_ifindex, cmd == SIOCBRADDIF); } break; } rtnl_unlock(); return ret; } |
| 4 4 1 1 11 11 2 2 5 5 1 1 6 9 11 11 11 11 8 9 6 6 1 1 14 14 12 14 1 1 1 1 11 11 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018, 2021-2025 Intel Corporation */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS #include <linux/rtnetlink.h> #include <net/cfg80211.h> #include "core.h" #include "trace.h" static inline int rdev_suspend(struct cfg80211_registered_device *rdev, struct cfg80211_wowlan *wowlan) { int ret; trace_rdev_suspend(&rdev->wiphy, wowlan); ret = rdev->ops->suspend(&rdev->wiphy, wowlan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_resume(struct cfg80211_registered_device *rdev) { int ret; trace_rdev_resume(&rdev->wiphy); ret = rdev->ops->resume(&rdev->wiphy); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev, bool enabled) { trace_rdev_set_wakeup(&rdev->wiphy, enabled); rdev->ops->set_wakeup(&rdev->wiphy, enabled); trace_rdev_return_void(&rdev->wiphy); } static inline struct wireless_dev *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct wireless_dev *ret; trace_rdev_add_virtual_intf(&rdev->wiphy, name, type); ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type, type, params); trace_rdev_return_wdev(&rdev->wiphy, ret); return ret; } static inline int rdev_del_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_del_virtual_intf(&rdev->wiphy, wdev); ret = rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_virtual_intf(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { int ret; trace_rdev_change_virtual_intf(&rdev->wiphy, dev, type); ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params) { int ret; trace_rdev_add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params->mode); ret = rdev->ops->add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params*)) { int ret; trace_rdev_get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, cookie, callback); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr) { int ret; trace_rdev_del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool unicast, bool multicast) { int ret; trace_rdev_set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); ret = rdev->ops->set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) { int ret; trace_rdev_start_ap(&rdev->wiphy, dev, settings); ret = rdev->ops->start_ap(&rdev->wiphy, dev, settings); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_beacon(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_update *info) { int ret; trace_rdev_change_beacon(&rdev->wiphy, dev, info); ret = rdev->ops->change_beacon(&rdev->wiphy, dev, info); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id) { int ret; trace_rdev_stop_ap(&rdev->wiphy, dev, link_id); ret = rdev->ops->stop_ap(&rdev->wiphy, dev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_add_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->add_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct station_del_parameters *params) { int ret; trace_rdev_del_station(&rdev->wiphy, dev, params); ret = rdev->ops->del_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_change_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->change_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_station(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_get_station(&rdev->wiphy, dev, mac); ret = rdev->ops->get_station(&rdev->wiphy, dev, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_dump_station(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_dump_station(&rdev->wiphy, dev, idx, mac); ret = rdev->ops->dump_station(&rdev->wiphy, dev, idx, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_add_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_add_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst) { int ret; trace_rdev_del_mpath(&rdev->wiphy, dev, dst); ret = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_change_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpp(&rdev->wiphy, dev, dst, mpp); ret = rdev->ops->get_mpp(&rdev->wiphy, dev, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop); ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpp(&rdev->wiphy, dev, idx, dst, mpp); ret = rdev->ops->dump_mpp(&rdev->wiphy, dev, idx, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct mesh_config *conf) { int ret; trace_rdev_get_mesh_config(&rdev->wiphy, dev); ret = rdev->ops->get_mesh_config(&rdev->wiphy, dev, conf); trace_rdev_return_int_mesh_config(&rdev->wiphy, ret, conf); return ret; } static inline int rdev_update_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { int ret; trace_rdev_update_mesh_config(&rdev->wiphy, dev, mask, nconf); ret = rdev->ops->update_mesh_config(&rdev->wiphy, dev, mask, nconf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { int ret; trace_rdev_join_mesh(&rdev->wiphy, dev, conf, setup); ret = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_mesh(&rdev->wiphy, dev); ret = rdev->ops->leave_mesh(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ocb_setup *setup) { int ret; trace_rdev_join_ocb(&rdev->wiphy, dev, setup); ret = rdev->ops->join_ocb(&rdev->wiphy, dev, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ocb(&rdev->wiphy, dev); ret = rdev->ops->leave_ocb(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_bss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct bss_parameters *params) { int ret; trace_rdev_change_bss(&rdev->wiphy, dev, params); ret = rdev->ops->change_bss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_inform_bss(struct cfg80211_registered_device *rdev, struct cfg80211_bss *bss, const struct cfg80211_bss_ies *ies, void *drv_data) { trace_rdev_inform_bss(&rdev->wiphy, bss); if (rdev->ops->inform_bss) rdev->ops->inform_bss(&rdev->wiphy, bss, ies, drv_data); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_txq_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_txq_params *params) { int ret; trace_rdev_set_txq_params(&rdev->wiphy, dev, params); ret = rdev->ops->set_txq_params(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_libertas_set_mesh_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan) { int ret; trace_rdev_libertas_set_mesh_channel(&rdev->wiphy, dev, chan); ret = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, dev, chan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_monitor_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_monitor_channel(&rdev->wiphy, dev, chandef); ret = rdev->ops->set_monitor_channel(&rdev->wiphy, dev, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_scan(struct cfg80211_registered_device *rdev, struct cfg80211_scan_request_int *request) { int ret; if (WARN_ON_ONCE(!request->req.n_ssids && request->req.ssids)) return -EINVAL; trace_rdev_scan(&rdev->wiphy, request); ret = rdev->ops->scan(&rdev->wiphy, &request->req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_scan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_abort_scan(&rdev->wiphy, wdev); rdev->ops->abort_scan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_auth_request *req) { int ret; trace_rdev_auth(&rdev->wiphy, dev, req); ret = rdev->ops->auth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_assoc_request *req) { int ret; trace_rdev_assoc(&rdev->wiphy, dev, req); ret = rdev->ops->assoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_deauth_request *req) { int ret; trace_rdev_deauth(&rdev->wiphy, dev, req); ret = rdev->ops->deauth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_disassoc_request *req) { int ret; trace_rdev_disassoc(&rdev->wiphy, dev, req); ret = rdev->ops->disassoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme) { int ret; trace_rdev_connect(&rdev->wiphy, dev, sme); ret = rdev->ops->connect(&rdev->wiphy, dev, sme); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_connect_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme, u32 changed) { int ret; trace_rdev_update_connect_params(&rdev->wiphy, dev, sme, changed); ret = rdev->ops->update_connect_params(&rdev->wiphy, dev, sme, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason_code) { int ret; trace_rdev_disconnect(&rdev->wiphy, dev, reason_code); ret = rdev->ops->disconnect(&rdev->wiphy, dev, reason_code); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ibss_params *params) { int ret; trace_rdev_join_ibss(&rdev->wiphy, dev, params); ret = rdev->ops->join_ibss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ibss(&rdev->wiphy, dev); ret = rdev->ops->leave_ibss(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, int radio_idx, u32 changed) { int ret = -EOPNOTSUPP; trace_rdev_set_wiphy_params(&rdev->wiphy, radio_idx, changed); if (rdev->ops->set_wiphy_params) ret = rdev->ops->set_wiphy_params(&rdev->wiphy, radio_idx, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, int radio_idx, enum nl80211_tx_power_setting type, int mbm) { int ret; trace_rdev_set_tx_power(&rdev->wiphy, wdev, radio_idx, type, mbm); ret = rdev->ops->set_tx_power(&rdev->wiphy, wdev, radio_idx, type, mbm); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, int radio_idx, unsigned int link_id, int *dbm) { int ret; trace_rdev_get_tx_power(&rdev->wiphy, wdev, radio_idx, link_id); ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, radio_idx, link_id, dbm); trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm); return ret; } static inline int rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, struct net_device *dev, const bool enabled) { int ret; trace_rdev_set_multicast_to_unicast(&rdev->wiphy, dev, enabled); ret = rdev->ops->set_multicast_to_unicast(&rdev->wiphy, dev, enabled); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_txq_stats(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats) { int ret; trace_rdev_get_txq_stats(&rdev->wiphy, wdev); ret = rdev->ops->get_txq_stats(&rdev->wiphy, wdev, txqstats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) { trace_rdev_rfkill_poll(&rdev->wiphy); rdev->ops->rfkill_poll(&rdev->wiphy); trace_rdev_return_void(&rdev->wiphy); } #ifdef CONFIG_NL80211_TESTMODE static inline int rdev_testmode_cmd(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, void *data, int len) { int ret; trace_rdev_testmode_cmd(&rdev->wiphy, wdev); ret = rdev->ops->testmode_cmd(&rdev->wiphy, wdev, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_testmode_dump(struct cfg80211_registered_device *rdev, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { int ret; trace_rdev_testmode_dump(&rdev->wiphy); ret = rdev->ops->testmode_dump(&rdev->wiphy, skb, cb, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } #endif static inline int rdev_set_bitrate_mask(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask) { int ret; trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_dump_survey(struct cfg80211_registered_device *rdev, struct net_device *netdev, int idx, struct survey_info *info) { int ret; trace_rdev_dump_survey(&rdev->wiphy, netdev, idx); ret = rdev->ops->dump_survey(&rdev->wiphy, netdev, idx, info); if (ret < 0) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_survey_info(&rdev->wiphy, ret, info); return ret; } static inline int rdev_set_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_set_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->set_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_del_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->del_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_flush_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev) { int ret; trace_rdev_flush_pmksa(&rdev->wiphy, netdev); ret = rdev->ops->flush_pmksa(&rdev->wiphy, netdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, u64 *cookie) { int ret; trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration); ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, duration, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); ret = rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_mgmt_tx_params *params, u64 *cookie) { int ret; trace_rdev_mgmt_tx(&rdev->wiphy, wdev, params); ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, params, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev, struct net_device *dev, const void *buf, size_t len, const u8 *dest, __be16 proto, const bool noencrypt, int link, u64 *cookie) { int ret; trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link); ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link, cookie); if (cookie) trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); else trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx_cancel_wait(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); ret = rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_power_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, bool enabled, int timeout) { int ret; trace_rdev_set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); ret = rdev->ops->set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { int ret; trace_rdev_set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); ret = rdev->ops->set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_range_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 low, s32 high) { int ret; trace_rdev_set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); ret = rdev->ops->set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_txe_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 rate, u32 pkts, u32 intvl) { int ret; trace_rdev_set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); ret = rdev->ops->set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_update_mgmt_frame_registrations(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct mgmt_frame_regs *upd) { might_sleep(); trace_rdev_update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); if (rdev->ops->update_mgmt_frame_registrations) rdev->ops->update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_antenna(struct cfg80211_registered_device *rdev, int radio_idx, u32 tx_ant, u32 rx_ant) { int ret; trace_rdev_set_antenna(&rdev->wiphy, radio_idx, tx_ant, rx_ant); ret = rdev->ops->set_antenna(&rdev->wiphy, -1, tx_ant, rx_ant); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_antenna(struct cfg80211_registered_device *rdev, int radio_idx, u32 *tx_ant, u32 *rx_ant) { int ret; trace_rdev_get_antenna(&rdev->wiphy, radio_idx); ret = rdev->ops->get_antenna(&rdev->wiphy, radio_idx, tx_ant, rx_ant); if (ret) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_tx_rx(&rdev->wiphy, ret, *tx_ant, *rx_ant); return ret; } static inline int rdev_sched_scan_start(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_sched_scan_request *request) { int ret; trace_rdev_sched_scan_start(&rdev->wiphy, dev, request->reqid); ret = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_sched_scan_stop(struct cfg80211_registered_device *rdev, struct net_device *dev, u64 reqid) { int ret; trace_rdev_sched_scan_stop(&rdev->wiphy, dev, reqid); ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev, reqid); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) { int ret; trace_rdev_set_rekey_data(&rdev->wiphy, dev); ret = rdev->ops->set_rekey_data(&rdev->wiphy, dev, data); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_oper(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, enum nl80211_tdls_operation oper) { int ret; trace_rdev_tdls_oper(&rdev->wiphy, dev, peer, oper); ret = rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, oper); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_client(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u64 *cookie) { int ret; trace_rdev_probe_client(&rdev->wiphy, dev, peer); ret = rdev->ops->probe_client(&rdev->wiphy, dev, peer, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 noack_map) { int ret; trace_rdev_set_noack_map(&rdev->wiphy, dev, noack_map); ret = rdev->ops->set_noack_map(&rdev->wiphy, dev, noack_map); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_get_channel(&rdev->wiphy, wdev, link_id); ret = rdev->ops->get_channel(&rdev->wiphy, wdev, link_id, chandef); trace_rdev_return_chandef(&rdev->wiphy, ret, chandef); return ret; } static inline int rdev_start_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_start_p2p_device(&rdev->wiphy, wdev); ret = rdev->ops->start_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_p2p_device(&rdev->wiphy, wdev); rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { int ret; trace_rdev_start_nan(&rdev->wiphy, wdev, conf); ret = rdev->ops->start_nan(&rdev->wiphy, wdev, conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_nan(&rdev->wiphy, wdev); rdev->ops->stop_nan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { int ret; trace_rdev_add_nan_func(&rdev->wiphy, wdev, nan_func); ret = rdev->ops->add_nan_func(&rdev->wiphy, wdev, nan_func); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { trace_rdev_del_nan_func(&rdev->wiphy, wdev, cookie); rdev->ops->del_nan_func(&rdev->wiphy, wdev, cookie); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_nan_change_conf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { int ret; trace_rdev_nan_change_conf(&rdev->wiphy, wdev, conf, changes); if (rdev->ops->nan_change_conf) ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf, changes); else ret = -EOPNOTSUPP; trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) { int ret; trace_rdev_set_mac_acl(&rdev->wiphy, dev, params); ret = rdev->ops->set_mac_acl(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_ft_ies(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie) { int ret; trace_rdev_update_ft_ies(&rdev->wiphy, dev, ftie); ret = rdev->ops->update_ft_ies(&rdev->wiphy, dev, ftie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_crit_proto_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_crit_proto_id protocol, u16 duration) { int ret; trace_rdev_crit_proto_start(&rdev->wiphy, wdev, protocol, duration); ret = rdev->ops->crit_proto_start(&rdev->wiphy, wdev, protocol, duration); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_crit_proto_stop(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_crit_proto_stop(&rdev->wiphy, wdev); rdev->ops->crit_proto_stop(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_csa_settings *params) { int ret; trace_rdev_channel_switch(&rdev->wiphy, dev, params); ret = rdev->ops->channel_switch(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_qos_map *qos_map) { int ret = -EOPNOTSUPP; if (rdev->ops->set_qos_map) { trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map); ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map); trace_rdev_return_int(&rdev->wiphy, ret); } return ret; } static inline int rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer, u8 user_prio, u16 admitted_time) { int ret = -EOPNOTSUPP; trace_rdev_add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); if (rdev->ops->add_tx_ts) ret = rdev->ops->add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer) { int ret = -EOPNOTSUPP; trace_rdev_del_tx_ts(&rdev->wiphy, dev, tsid, peer); if (rdev->ops->del_tx_ts) ret = rdev->ops->del_tx_ts(&rdev->wiphy, dev, tsid, peer); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr, u8 oper_class, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); ret = rdev->ops->tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_tdls_cancel_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr) { trace_rdev_tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); rdev->ops->tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_radar_detection(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms, int link_id) { int ret = -EOPNOTSUPP; trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms, link_id); if (rdev->ops->start_radar_detection) ret = rdev->ops->start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_end_cac(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id) { trace_rdev_end_cac(&rdev->wiphy, dev, link_id); if (rdev->ops->end_cac) rdev->ops->end_cac(&rdev->wiphy, dev, link_id); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, int mcast_rate[NUM_NL80211_BANDS]) { int ret = -EOPNOTSUPP; trace_rdev_set_mcast_rate(&rdev->wiphy, dev, mcast_rate); if (rdev->ops->set_mcast_rate) ret = rdev->ops->set_mcast_rate(&rdev->wiphy, dev, mcast_rate); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_coalesce(struct cfg80211_registered_device *rdev, struct cfg80211_coalesce *coalesce) { int ret = -EOPNOTSUPP; trace_rdev_set_coalesce(&rdev->wiphy, coalesce); if (rdev->ops->set_coalesce) ret = rdev->ops->set_coalesce(&rdev->wiphy, coalesce); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_pmk_conf *pmk_conf) { int ret = -EOPNOTSUPP; trace_rdev_set_pmk(&rdev->wiphy, dev, pmk_conf); if (rdev->ops->set_pmk) ret = rdev->ops->set_pmk(&rdev->wiphy, dev, pmk_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *aa) { int ret = -EOPNOTSUPP; trace_rdev_del_pmk(&rdev->wiphy, dev, aa); if (rdev->ops->del_pmk) ret = rdev->ops->del_pmk(&rdev->wiphy, dev, aa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_external_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_external_auth_params *params) { int ret = -EOPNOTSUPP; trace_rdev_external_auth(&rdev->wiphy, dev, params); if (rdev->ops->external_auth) ret = rdev->ops->external_auth(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_ftm_responder_stats(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats) { int ret = -EOPNOTSUPP; trace_rdev_get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); if (rdev->ops->get_ftm_responder_stats) ret = rdev->ops->get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { int ret = -EOPNOTSUPP; trace_rdev_start_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->start_pmsr) ret = rdev->ops->start_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { trace_rdev_abort_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->abort_pmsr) rdev->ops->abort_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_update_owe_info(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_owe_info *oweinfo) { int ret = -EOPNOTSUPP; trace_rdev_update_owe_info(&rdev->wiphy, dev, oweinfo); if (rdev->ops->update_owe_info) ret = rdev->ops->update_owe_info(&rdev->wiphy, dev, oweinfo); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *dest, const void *buf, size_t len) { int ret; trace_rdev_probe_mesh_link(&rdev->wiphy, dev, dest, buf, len); ret = rdev->ops->probe_mesh_link(&rdev->wiphy, dev, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_tid_config *tid_conf) { int ret; trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u8 tids) { int ret; trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev, struct cfg80211_sar_specs *sar) { int ret; trace_rdev_set_sar_specs(&rdev->wiphy, sar); ret = rdev->ops->set_sar_specs(&rdev->wiphy, sar); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_color_change(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_color_change_settings *params) { int ret; trace_rdev_color_change(&rdev->wiphy, dev, params); ret = rdev->ops->color_change(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_fils_aad(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_fils_aad *fils_aad) { int ret = -EOPNOTSUPP; trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); if (rdev->ops->set_fils_aad) ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_radar_background(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_radar_background(wiphy, chandef); if (rdev->ops->set_radar_background) ret = rdev->ops->set_radar_background(wiphy, chandef); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_add_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { int ret = 0; trace_rdev_add_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->add_intf_link) ret = rdev->ops->add_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { trace_rdev_del_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->del_intf_link) rdev->ops->del_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_add_link_station(&rdev->wiphy, dev, params); if (rdev->ops->add_link_station) ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mod_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_mod_link_station(&rdev->wiphy, dev, params); if (rdev->ops->mod_link_station) ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_del_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_del_link_station(&rdev->wiphy, dev, params); if (rdev->ops->del_link_station) ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_hw_timestamp(wiphy, dev, hwts); if (rdev->ops->set_hw_timestamp) ret = rdev->ops->set_hw_timestamp(wiphy, dev, hwts); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_set_ttlm(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ttlm_params *params) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_ttlm(wiphy, dev, params); if (rdev->ops->set_ttlm) ret = rdev->ops->set_ttlm(wiphy, dev, params); trace_rdev_return_int(wiphy, ret); return ret; } static inline u32 rdev_get_radio_mask(struct cfg80211_registered_device *rdev, struct net_device *dev) { struct wiphy *wiphy = &rdev->wiphy; if (!rdev->ops->get_radio_mask) return 0; return rdev->ops->get_radio_mask(wiphy, dev); } static inline int rdev_assoc_ml_reconf(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ml_reconf_req *req) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_assoc_ml_reconf(wiphy, dev, req); if (rdev->ops->assoc_ml_reconf) ret = rdev->ops->assoc_ml_reconf(wiphy, dev, req); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_set_epcs(struct cfg80211_registered_device *rdev, struct net_device *dev, bool val) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_epcs(wiphy, dev, val); if (rdev->ops->set_epcs) ret = rdev->ops->set_epcs(wiphy, dev, val); trace_rdev_return_int(wiphy, ret); return ret; } #endif /* __CFG80211_RDEV_OPS */ |
| 262 263 263 262 262 142 142 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/time.h> #include <linux/gcd.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/timer.h> #include "pcm_local.h" /* * Timer functions */ void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream) { unsigned long rate, mult, fsize, l, post; struct snd_pcm_runtime *runtime = substream->runtime; mult = 1000000000; rate = runtime->rate; if (snd_BUG_ON(!rate)) return; l = gcd(mult, rate); mult /= l; rate /= l; fsize = runtime->period_size; if (snd_BUG_ON(!fsize)) return; l = gcd(rate, fsize); rate /= l; fsize /= l; post = 1; while ((mult * fsize) / fsize != mult) { mult /= 2; post *= 2; } if (rate == 0) { pcm_err(substream->pcm, "pcm timer resolution out of range (rate = %u, period_size = %lu)\n", runtime->rate, runtime->period_size); runtime->timer_resolution = -1; return; } runtime->timer_resolution = (mult * fsize / rate) * post; } static unsigned long snd_pcm_timer_resolution(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = timer->private_data; return substream->runtime ? substream->runtime->timer_resolution : 0; } static int snd_pcm_timer_start(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = snd_timer_chip(timer); substream->timer_running = 1; return 0; } static int snd_pcm_timer_stop(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = snd_timer_chip(timer); substream->timer_running = 0; return 0; } static const struct snd_timer_hardware snd_pcm_timer = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_SLAVE, .resolution = 0, .ticks = 1, .c_resolution = snd_pcm_timer_resolution, .start = snd_pcm_timer_start, .stop = snd_pcm_timer_stop, }; /* * Init functions */ static void snd_pcm_timer_free(struct snd_timer *timer) { struct snd_pcm_substream *substream = timer->private_data; substream->timer = NULL; } void snd_pcm_timer_init(struct snd_pcm_substream *substream) { struct snd_timer_id tid; struct snd_timer *timer; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.dev_class = SNDRV_TIMER_CLASS_PCM; tid.card = substream->pcm->card->number; tid.device = substream->pcm->device; tid.subdevice = (substream->number << 1) | (substream->stream & 1); if (snd_timer_new(substream->pcm->card, "PCM", &tid, &timer) < 0) return; sprintf(timer->name, "PCM %s %i-%i-%i", snd_pcm_direction_name(substream->stream), tid.card, tid.device, tid.subdevice); timer->hw = snd_pcm_timer; if (snd_device_register(timer->card, timer) < 0) { snd_device_free(timer->card, timer); return; } timer->private_data = substream; timer->private_free = snd_pcm_timer_free; substream->timer = timer; } void snd_pcm_timer_done(struct snd_pcm_substream *substream) { if (substream->timer) { snd_device_free(substream->pcm->card, substream->timer); substream->timer = NULL; } } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pep-gprs.c * * GPRS over Phonet pipe end point socket * * Copyright (C) 2008 Nokia Corporation. * * Author: Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <net/sock.h> #include <linux/if_phonet.h> #include <net/tcp_states.h> #include <net/phonet/gprs.h> #include <trace/events/sock.h> #define GPRS_DEFAULT_MTU 1400 struct gprs_dev { struct sock *sk; void (*old_state_change)(struct sock *); void (*old_data_ready)(struct sock *); void (*old_write_space)(struct sock *); struct net_device *dev; }; static __be16 gprs_type_trans(struct sk_buff *skb) { const u8 *pvfc; u8 buf; pvfc = skb_header_pointer(skb, 0, 1, &buf); if (!pvfc) return htons(0); /* Look at IP version field */ switch (*pvfc >> 4) { case 4: return htons(ETH_P_IP); case 6: return htons(ETH_P_IPV6); } return htons(0); } static void gprs_writeable(struct gprs_dev *gp) { struct net_device *dev = gp->dev; if (pep_writeable(gp->sk)) netif_wake_queue(dev); } /* * Socket callbacks */ static void gprs_state_change(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (sk->sk_state == TCP_CLOSE_WAIT) { struct net_device *dev = gp->dev; netif_stop_queue(dev); netif_carrier_off(dev); } } static int gprs_recv(struct gprs_dev *gp, struct sk_buff *skb) { struct net_device *dev = gp->dev; int err = 0; __be16 protocol = gprs_type_trans(skb); if (!protocol) { err = -EINVAL; goto drop; } if (skb_headroom(skb) & 3) { struct sk_buff *rskb, *fs; int flen = 0; /* Phonet Pipe data header may be misaligned (3 bytes), * so wrap the IP packet as a single fragment of an head-less * socket buffer. The network stack will pull what it needs, * but at least, the whole IP payload is not memcpy'd. */ rskb = netdev_alloc_skb(dev, 0); if (!rskb) { err = -ENOBUFS; goto drop; } skb_shinfo(rskb)->frag_list = skb; rskb->len += skb->len; rskb->data_len += rskb->len; rskb->truesize += rskb->len; /* Avoid nested fragments */ skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; skb = rskb; } skb->protocol = protocol; skb_reset_mac_header(skb); skb->dev = dev; if (likely(dev->flags & IFF_UP)) { dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; netif_rx(skb); skb = NULL; } else err = -ENODEV; drop: if (skb) { dev_kfree_skb(skb); dev->stats.rx_dropped++; } return err; } static void gprs_data_ready(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct sk_buff *skb; trace_sk_data_ready(sk); while ((skb = pep_read(sk)) != NULL) { skb_orphan(skb); gprs_recv(gp, skb); } } static void gprs_write_space(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (netif_running(gp->dev)) gprs_writeable(gp); } /* * Network device callbacks */ static int gprs_open(struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); gprs_writeable(gp); return 0; } static int gprs_close(struct net_device *dev) { netif_stop_queue(dev); return 0; } static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); struct sock *sk = gp->sk; int len, err; switch (skb->protocol) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): break; default: dev_kfree_skb(skb); return NETDEV_TX_OK; } skb_orphan(skb); skb_set_owner_w(skb, sk); len = skb->len; err = pep_write(sk, skb); if (err) { net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err); dev->stats.tx_aborted_errors++; dev->stats.tx_errors++; } else { dev->stats.tx_packets++; dev->stats.tx_bytes += len; } netif_stop_queue(dev); if (pep_writeable(sk)) netif_wake_queue(dev); return NETDEV_TX_OK; } static const struct net_device_ops gprs_netdev_ops = { .ndo_open = gprs_open, .ndo_stop = gprs_close, .ndo_start_xmit = gprs_xmit, }; static void gprs_setup(struct net_device *dev) { dev->features = NETIF_F_FRAGLIST; dev->type = ARPHRD_PHONET_PIPE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = GPRS_DEFAULT_MTU; dev->min_mtu = 576; dev->max_mtu = (PHONET_MAX_MTU - 11); dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; dev->netdev_ops = &gprs_netdev_ops; dev->needs_free_netdev = true; } /* * External interface */ /* * Attach a GPRS interface to a datagram socket. * Returns the interface index on success, negative error code on error. */ int gprs_attach(struct sock *sk) { static const char ifname[] = "gprs%d"; struct gprs_dev *gp; struct net_device *dev; int err; if (unlikely(sk->sk_type == SOCK_STREAM)) return -EINVAL; /* need packet boundaries */ /* Create net device */ dev = alloc_netdev(sizeof(*gp), ifname, NET_NAME_UNKNOWN, gprs_setup); if (!dev) return -ENOMEM; gp = netdev_priv(dev); gp->sk = sk; gp->dev = dev; netif_stop_queue(dev); err = register_netdev(dev); if (err) { free_netdev(dev); return err; } lock_sock(sk); if (unlikely(sk->sk_user_data)) { err = -EBUSY; goto out_rel; } if (unlikely((1 << sk->sk_state & (TCPF_CLOSE|TCPF_LISTEN)) || sock_flag(sk, SOCK_DEAD))) { err = -EINVAL; goto out_rel; } sk->sk_user_data = gp; gp->old_state_change = sk->sk_state_change; gp->old_data_ready = sk->sk_data_ready; gp->old_write_space = sk->sk_write_space; sk->sk_state_change = gprs_state_change; sk->sk_data_ready = gprs_data_ready; sk->sk_write_space = gprs_write_space; release_sock(sk); sock_hold(sk); printk(KERN_DEBUG"%s: attached\n", dev->name); return dev->ifindex; out_rel: release_sock(sk); unregister_netdev(dev); return err; } void gprs_detach(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct net_device *dev = gp->dev; lock_sock(sk); sk->sk_user_data = NULL; sk->sk_state_change = gp->old_state_change; sk->sk_data_ready = gp->old_data_ready; sk->sk_write_space = gp->old_write_space; release_sock(sk); printk(KERN_DEBUG"%s: detached\n", dev->name); unregister_netdev(dev); sock_put(sk); } |
| 4 1 221 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count); #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } static inline u32 map_id_down(struct uid_gid_map *map, u32 id) { return id; } static inline u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) { return id; } static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 218 150 152 67 142 5 15 171 152 171 206 206 2 149 175 170 171 171 171 170 19 170 21 21 21 157 157 | 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 | /* 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 <linux/crc32c.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_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_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] */ ato |